{
 "schema": "cchp.pricing-table/v1",
 "version": "13509de2c745256c",
 "refreshed_at": "2026-07-09T08:06:21.617Z",
 "currency": "USD",
 "providers": {
  "360": {
   "name": "360",
   "icon": "ai360-color.svg"
  },
  "302ai": {
   "name": "302.AI",
   "doc": "https://302.ai",
   "icon": "ai302-color.svg"
  },
  "abacus": {
   "name": "Abacus",
   "doc": "https://abacus.ai/"
  },
  "abliteration-ai": {
   "name": "Abliteration.ai",
   "doc": "https://abliteration.ai"
  },
  "aihubmix": {
   "name": "AIHubMix",
   "doc": "https://docs.aihubmix.com",
   "icon": "aihubmix-color.svg"
  },
  "alibaba": {
   "name": "Alibaba (China)",
   "doc": "https://www.alibabacloud.com/help/en/model-studio/models",
   "icon": "alibaba-color.svg"
  },
  "alibaba-cn": {
   "name": "Alibaba (China)",
   "doc": "https://www.alibabacloud.com/help/en/model-studio/",
   "icon": "alibaba-color.svg"
  },
  "alibaba-coding-plan": {
   "name": "Alibaba Coding Plan",
   "doc": "https://www.alibabacloud.com/help/en/model-studio/coding-plan",
   "icon": "alibaba-color.svg"
  },
  "alibaba-coding-plan-cn": {
   "name": "Alibaba Coding Plan (China)",
   "doc": "https://help.aliyun.com/zh/model-studio/coding-plan",
   "icon": "alibaba-color.svg"
  },
  "alibaba-token-plan": {
   "name": "Alibaba Token Plan",
   "doc": "https://www.alibabacloud.com/help/en/model-studio/token-plan-overview",
   "icon": "alibaba-color.svg"
  },
  "alibaba-token-plan-cn": {
   "name": "Alibaba Token Plan (China)",
   "doc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
   "icon": "alibaba-color.svg"
  },
  "amazon-bedrock": {
   "name": "Amazon Bedrock",
   "doc": "https://docs.aws.amazon.com/bedrock/",
   "icon": "bedrock-color.svg"
  },
  "ambient": {
   "name": "Ambient",
   "doc": "https://ambient.xyz"
  },
  "anthropic": {
   "name": "Anthropic",
   "doc": "https://www.anthropic.com",
   "icon": "anthropic.svg",
   "icon_mono": true
  },
  "anyapi": {
   "name": "AnyAPI",
   "doc": "https://docs.anyapi.ai"
  },
  "api-airforce": {
   "name": "Api.Airforce",
   "doc": "https://api.airforce"
  },
  "atomic-chat": {
   "name": "Atomic Chat",
   "doc": "https://atomic.chat"
  },
  "auriko": {
   "name": "Auriko",
   "doc": "https://docs.auriko.ai"
  },
  "avian": {
   "name": "avian",
   "doc": "https://avian.io/"
  },
  "azure": {
   "name": "Azure",
   "doc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models",
   "icon": "azure-color.svg"
  },
  "azure-cognitive-services": {
   "name": "Azure Cognitive Services",
   "doc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models",
   "icon": "azure-color.svg"
  },
  "bailing": {
   "name": "Bailing",
   "doc": "https://alipaytbox.yuque.com/sxs0ba/ling/intro"
  },
  "baseten": {
   "name": "Basten",
   "doc": "https://baseten.co",
   "icon": "baseten.svg",
   "icon_mono": true
  },
  "berget": {
   "name": "Berget.AI",
   "doc": "https://berget.ai"
  },
  "cerebras": {
   "name": "Cerebras",
   "doc": "https://cerebras.ai/docs",
   "icon": "cerebras-color.svg"
  },
  "chutes": {
   "name": "Chutes",
   "doc": "https://llm.chutes.ai/v1/models"
  },
  "clarifai": {
   "name": "Clarifai",
   "doc": "https://docs.clarifai.com/compute/inference/"
  },
  "claudinio": {
   "name": "Claudinio",
   "doc": "https://claudin.io"
  },
  "cloudferro-sherlock": {
   "name": "CloudFerro Sherlock",
   "doc": "https://docs.sherlock.cloudferro.com/"
  },
  "cloudflare-ai-gateway": {
   "name": "Cloudflare AI Gateway",
   "doc": "https://developers.cloudflare.com/ai-gateway/",
   "icon": "cloudflare-color.svg"
  },
  "cloudflare-workers-ai": {
   "name": "Cloudflare Workers AI",
   "doc": "https://developers.cloudflare.com/workers-ai/models/",
   "icon": "workersai-color.svg"
  },
  "cohere": {
   "name": "Cohere",
   "doc": "https://docs.cohere.com/docs/models",
   "icon": "cohere-color.svg"
  },
  "cortecs": {
   "name": "Cortecs",
   "doc": "https://cortecs.ai"
  },
  "crof": {
   "name": "CrofAI",
   "doc": "https://crof.ai"
  },
  "databricks": {
   "name": "Databricks",
   "doc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/",
   "icon": "dbrx-color.svg"
  },
  "deepinfra": {
   "name": "Deep Infra",
   "doc": "https://deepinfra.com",
   "icon": "deepinfra-color.svg"
  },
  "deepseek": {
   "name": "DeepSeek",
   "doc": "https://api-docs.deepseek.com/quick_start/pricing",
   "icon": "deepseek-color.svg"
  },
  "digitalocean": {
   "name": "DigitalOcean",
   "doc": "https://docs.digitalocean.com/products/gradient-ai-platform/details/models/"
  },
  "dinference": {
   "name": "DInference",
   "doc": "https://dinference.com"
  },
  "drun": {
   "name": "D.Run (China)",
   "doc": "https://www.d.run"
  },
  "evroc": {
   "name": "evroc",
   "doc": "https://docs.evroc.com/products/think/overview.html"
  },
  "fastrouter": {
   "name": "FastRouter",
   "doc": "https://fastrouter.ai"
  },
  "fireworks-ai": {
   "name": "Fireworks AI",
   "doc": "https://fireworks.ai",
   "icon": "fireworks-color.svg"
  },
  "firmware": {
   "name": "Firmware",
   "doc": "https://docs.firmware.ai"
  },
  "freemodel": {
   "name": "FreeModel",
   "doc": "https://freemodel.dev"
  },
  "friendli": {
   "name": "Friendli",
   "doc": "https://friendli.ai",
   "icon": "friendli.svg",
   "icon_mono": true
  },
  "frogbot": {
   "name": "FrogBot",
   "doc": "https://docs.frogbot.ai"
  },
  "github-copilot": {
   "name": "GitHub Copilot",
   "doc": "https://docs.github.com/en/copilot",
   "icon": "githubcopilot.svg",
   "icon_mono": true
  },
  "github-models": {
   "name": "GitHub Models",
   "doc": "https://docs.github.com/en/github-models",
   "icon": "github.svg",
   "icon_mono": true
  },
  "gitlab": {
   "name": "GitLab Duo",
   "doc": "https://docs.gitlab.com/user/duo_agent_platform/"
  },
  "gmicloud": {
   "name": "GMI Cloud",
   "doc": "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"
  },
  "google": {
   "name": "Google",
   "doc": "https://ai.google.dev/docs",
   "icon": "google-color.svg"
  },
  "google-vertex": {
   "name": "Google Vertex AI",
   "doc": "https://cloud.google.com/vertex-ai/docs",
   "icon": "vertexai-color.svg"
  },
  "google-vertex-anthropic": {
   "name": "Vertex (Anthropic)",
   "doc": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude",
   "icon": "vertexai-color.svg"
  },
  "groq": {
   "name": "Groq",
   "doc": "https://groq.com",
   "icon": "groq.svg",
   "icon_mono": true
  },
  "helicone": {
   "name": "Helicone",
   "doc": "https://helicone.ai"
  },
  "hpc-ai": {
   "name": "HPC-AI",
   "doc": "https://www.hpc-ai.com/doc/docs/quickstart/"
  },
  "huggingface": {
   "name": "Hugging Face",
   "doc": "https://huggingface.co",
   "icon": "huggingface-color.svg"
  },
  "hyperstack": {
   "name": "Hyperstack",
   "doc": "https://www.hyperstack.cloud/"
  },
  "iflowcn": {
   "name": "iFlow",
   "doc": "https://platform.iflow.cn/en/docs"
  },
  "inception": {
   "name": "Inception",
   "doc": "https://platform.inceptionlabs.ai/docs",
   "icon": "inception.svg",
   "icon_mono": true
  },
  "inceptron": {
   "name": "Inceptron",
   "doc": "https://docs.inceptron.io"
  },
  "inference": {
   "name": "Inference",
   "doc": "https://inference.net/models",
   "icon": "inference.svg",
   "icon_mono": true
  },
  "io-net": {
   "name": "IO.NET",
   "doc": "https://io.net/docs/guides/intelligence/io-intelligence"
  },
  "ionet": {
   "name": "IO.NET",
   "doc": "https://io.net/"
  },
  "jiekou": {
   "name": "Jiekou.AI",
   "doc": "https://jiekou.ai"
  },
  "kenari": {
   "name": "Kenari",
   "doc": "https://kenari.id/docs"
  },
  "kilo": {
   "name": "Kilo Gateway",
   "doc": "https://kilo.ai",
   "icon": "kilocode.svg",
   "icon_mono": true
  },
  "kimi-for-coding": {
   "name": "Kimi For Coding",
   "doc": "https://www.kimi.com/code/docs/en/third-party-tools/other-coding-agents.html",
   "icon": "kimi-color.svg"
  },
  "kuae-cloud-coding-plan": {
   "name": "KUAE Cloud Coding Plan",
   "doc": "https://docs.mthreads.com/kuaecloud/kuaecloud-doc-online/coding_plan/"
  },
  "lilac": {
   "name": "Lilac",
   "doc": "https://docs.getlilac.com/inference/models"
  },
  "llama": {
   "name": "Llama",
   "doc": "https://llama.developer.meta.com/docs/models",
   "icon": "meta-color.svg"
  },
  "llmgateway": {
   "name": "LLM Gateway",
   "doc": "https://llmgateway.io"
  },
  "llmtr": {
   "name": "LLMTR",
   "doc": "https://llmtr.com"
  },
  "lmstudio": {
   "name": "LMStudio",
   "doc": "https://lmstudio.ai/models",
   "icon": "lmstudio.svg",
   "icon_mono": true
  },
  "longcat": {
   "name": "LongCat",
   "doc": "https://longcat.chat/platform/docs/",
   "icon": "longcat-color.svg"
  },
  "lucidquery": {
   "name": "LucidQuery",
   "doc": "https://lucidquery.com/docs"
  },
  "meganova": {
   "name": "Meganova",
   "doc": "https://docs.meganova.ai"
  },
  "merge-gateway": {
   "name": "Merge Gateway",
   "doc": "https://docs.merge.dev/merge-gateway"
  },
  "minimax": {
   "name": "MiniMax (minimaxi.com)",
   "doc": "https://platform.minimaxi.com/docs/guides/quickstart",
   "icon": "minimax-color.svg"
  },
  "minimax-cn": {
   "name": "MiniMax (minimaxi.com)",
   "doc": "https://platform.minimaxi.com/docs/guides/quickstart",
   "icon": "minimax-color.svg"
  },
  "minimax-cn-coding-plan": {
   "name": "MiniMax Token Plan (minimaxi.com)",
   "doc": "https://platform.minimaxi.com/docs/token-plan/intro",
   "icon": "minimax-color.svg"
  },
  "minimax-coding-plan": {
   "name": "MiniMax Token Plan (minimax.io)",
   "doc": "https://platform.minimax.io/docs/token-plan/intro",
   "icon": "minimax-color.svg"
  },
  "mistral": {
   "name": "Mistral",
   "doc": "https://docs.mistral.ai/getting-started/models/",
   "icon": "mistral-color.svg"
  },
  "mixlayer": {
   "name": "Mixlayer",
   "doc": "https://docs.mixlayer.com"
  },
  "moark": {
   "name": "Moark",
   "doc": "https://moark.com"
  },
  "modelscope": {
   "name": "ModelScope",
   "doc": "https://modelscope.cn/docs/model-service/API-Inference/intro",
   "icon": "modelscope-color.svg"
  },
  "moonshotai": {
   "name": "Moonshot AI (China)",
   "doc": "https://platform.moonshot.cn/docs/api/chat",
   "icon": "moonshot.svg",
   "icon_mono": true
  },
  "moonshotai-cn": {
   "name": "Moonshot AI (China)",
   "doc": "https://platform.moonshot.cn/docs/api/chat",
   "icon": "moonshot.svg",
   "icon_mono": true
  },
  "morph": {
   "name": "Morph",
   "doc": "https://docs.morphllm.com/api-reference/introduction",
   "icon": "morph-color.svg"
  },
  "nano-gpt": {
   "name": "NanoGPT",
   "doc": "https://docs.nano-gpt.com"
  },
  "nearai": {
   "name": "NEAR AI Cloud",
   "doc": "https://near.ai"
  },
  "nebius": {
   "name": "Nebius Token Factory",
   "doc": "https://docs.tokenfactory.nebius.com/",
   "icon": "nebius.svg",
   "icon_mono": true
  },
  "neon": {
   "name": "Neon",
   "doc": "https://neon.com/docs"
  },
  "neuralwatt": {
   "name": "Neuralwatt",
   "doc": "https://neuralwatt.com"
  },
  "nova": {
   "name": "Nova",
   "doc": "https://nova.amazon.com/dev/documentation",
   "icon": "nova-color.svg"
  },
  "novita": {
   "name": "Novita",
   "doc": "https://novita.ai",
   "icon": "novita-color.svg"
  },
  "novita-ai": {
   "name": "NovitaAI",
   "doc": "https://novita.ai/docs/guides/introduction",
   "icon": "novita-color.svg"
  },
  "nvidia": {
   "name": "Nvidia",
   "doc": "https://docs.api.nvidia.com/nim/",
   "icon": "nvidia-color.svg"
  },
  "ollama-cloud": {
   "name": "Ollama Cloud",
   "doc": "https://docs.ollama.com/cloud",
   "icon": "ollama.svg",
   "icon_mono": true
  },
  "openai": {
   "name": "OpenAI",
   "doc": "https://openai.com",
   "icon": "openai.svg",
   "icon_mono": true
  },
  "opencode": {
   "name": "OpenCode Zen",
   "doc": "https://opencode.ai/docs/zen",
   "icon": "opencode.svg",
   "icon_mono": true
  },
  "opencode-go": {
   "name": "OpenCode Go",
   "doc": "https://opencode.ai/docs/zen",
   "icon": "opencode.svg",
   "icon_mono": true
  },
  "opencode-zen": {
   "name": "OpenCode Zen",
   "doc": "https://opencode.ai",
   "icon": "opencode.svg",
   "icon_mono": true
  },
  "openrouter": {
   "name": "OpenRouter",
   "doc": "https://openrouter.ai/docs",
   "icon": "openrouter.svg",
   "icon_mono": true
  },
  "orcarouter": {
   "name": "OrcaRouter",
   "doc": "https://orcarouter.ai"
  },
  "ovhcloud": {
   "name": "OVHcloud AI Endpoints",
   "doc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//"
  },
  "perplexity": {
   "name": "Perplexity",
   "doc": "https://docs.perplexity.ai",
   "icon": "perplexity-color.svg"
  },
  "perplexity-agent": {
   "name": "Perplexity Agent",
   "doc": "https://docs.perplexity.ai/docs/agent-api/models",
   "icon": "perplexity-color.svg"
  },
  "poe": {
   "name": "Poe",
   "doc": "https://poe.com",
   "icon": "poe-color.svg"
  },
  "poolside": {
   "name": "Poolside",
   "doc": "https://platform.poolside.ai"
  },
  "privatemode-ai": {
   "name": "Privatemode AI",
   "doc": "https://docs.privatemode.ai/api/overview"
  },
  "qihang-ai": {
   "name": "QiHang",
   "doc": "https://www.qhaigc.net/docs"
  },
  "qiniu": {
   "name": "Qiniu",
   "doc": "https://www.qiniu.com",
   "icon": "qiniu-color.svg"
  },
  "qiniu-ai": {
   "name": "Qiniu",
   "doc": "https://developer.qiniu.com/aitokenapi",
   "icon": "qiniu-color.svg"
  },
  "regolo-ai": {
   "name": "Regolo AI",
   "doc": "https://docs.regolo.ai/"
  },
  "replicate": {
   "name": "Replicate",
   "doc": "https://replicate.com",
   "icon": "replicate.svg",
   "icon_mono": true
  },
  "requesty": {
   "name": "Requesty",
   "doc": "https://requesty.ai"
  },
  "routing-run": {
   "name": "routing.run",
   "doc": "https://docs.routing.run/api-reference/models"
  },
  "sakana": {
   "name": "Sakana AI",
   "doc": "https://console.sakana.ai/models"
  },
  "sap-ai-core": {
   "name": "SAP AI Core",
   "doc": "https://help.sap.com/docs/sap-ai-core"
  },
  "sarvam": {
   "name": "Sarvam AI",
   "doc": "https://docs.sarvam.ai/api-reference-docs/getting-started/models"
  },
  "scaleway": {
   "name": "Scaleway",
   "doc": "https://www.scaleway.com/"
  },
  "siliconflow": {
   "name": "SiliconFlow (China)",
   "doc": "https://cloud.siliconflow.com/models",
   "icon": "siliconcloud-color.svg"
  },
  "siliconflow-cn": {
   "name": "SiliconFlow (China)",
   "doc": "https://cloud.siliconflow.com/models",
   "icon": "siliconcloud-color.svg"
  },
  "snowflake-cortex": {
   "name": "Snowflake Cortex",
   "doc": "https://docs.snowflake.com/en/user-guide/snowflake-cortex/cortex-rest-api",
   "icon": "snowflake-color.svg"
  },
  "stackit": {
   "name": "STACKIT",
   "doc": "https://docs.stackit.cloud/products/data-and-ai/ai-model-serving/basics/available-shared-models"
  },
  "stepfun": {
   "name": "StepFun",
   "doc": "https://platform.stepfun.com/docs/zh/overview/concept",
   "icon": "stepfun-color.svg"
  },
  "stepfun-ai": {
   "name": "StepFun AI",
   "doc": "https://platform.stepfun.ai/docs/en/step-plan/integrations/open-code",
   "icon": "stepfun-color.svg"
  },
  "subconscious": {
   "name": "Subconscious",
   "doc": "https://docs.subconscious.dev"
  },
  "submodel": {
   "name": "submodel",
   "doc": "https://submodel.gitbook.io",
   "icon": "submodel-color.svg"
  },
  "synthetic": {
   "name": "Synthetic",
   "doc": "https://synthetic.new/pricing"
  },
  "tencent-coding-plan": {
   "name": "Tencent Coding Plan (China)",
   "doc": "https://cloud.tencent.com/document/product/1772/128947",
   "icon": "tencent-color.svg"
  },
  "tencent-token-plan": {
   "name": "Tencent Token Plan",
   "doc": "https://cloud.tencent.com/document/product/1823/130060",
   "icon": "tencent-color.svg"
  },
  "tencent-tokenhub": {
   "name": "Tencent TokenHub",
   "doc": "https://cloud.tencent.com/document/product/1823/130050",
   "icon": "tencent-color.svg"
  },
  "tetrate": {
   "name": "Tetrate Agent Router Service",
   "doc": "https://tetrate.ai/"
  },
  "the-grid-ai": {
   "name": "The Grid AI",
   "doc": "https://thegrid.ai/docs"
  },
  "tinfoil": {
   "name": "Tinfoil",
   "doc": "https://docs.tinfoil.sh"
  },
  "togetherai": {
   "name": "Together AI",
   "doc": "https://together.ai",
   "icon": "together-color.svg"
  },
  "tokenrouter": {
   "name": "TokenRouter",
   "doc": "https://tokenrouter.com"
  },
  "trustedrouter": {
   "name": "TrustedRouter",
   "doc": "https://trustedrouter.com/docs"
  },
  "umans-ai": {
   "name": "Umans AI",
   "doc": "https://app.umans.ai/offers/code/docs/orgs"
  },
  "umans-ai-coding-plan": {
   "name": "Umans AI Coding Plan",
   "doc": "https://app.umans.ai/offers/code/docs"
  },
  "upstage": {
   "name": "Upstage",
   "doc": "https://developers.upstage.ai/docs/apis/chat",
   "icon": "upstage-color.svg"
  },
  "v0": {
   "name": "v0",
   "doc": "https://sdk.vercel.ai/providers/ai-sdk-providers/vercel",
   "icon": "v0.svg",
   "icon_mono": true
  },
  "venice": {
   "name": "Venice AI",
   "doc": "https://docs.venice.ai",
   "icon": "venice-color.svg"
  },
  "vercel": {
   "name": "Vercel AI Gateway",
   "doc": "https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway",
   "icon": "vercel.svg",
   "icon_mono": true
  },
  "vivgrid": {
   "name": "Vivgrid",
   "doc": "https://docs.vivgrid.com/models"
  },
  "vultr": {
   "name": "Vultr",
   "doc": "https://api.vultrinference.com/"
  },
  "wafer": {
   "name": "Wafer",
   "doc": "https://www.wafer.ai"
  },
  "wafer-ai": {
   "name": "Wafer",
   "doc": "https://wafer.ai"
  },
  "wafer.ai": {
   "name": "Wafer",
   "doc": "https://docs.wafer.ai/wafer-pass"
  },
  "wandb": {
   "name": "Weights & Biases",
   "doc": "https://wandb.ai"
  },
  "xai": {
   "name": "xAI",
   "doc": "https://x.ai",
   "icon": "xai.svg",
   "icon_mono": true
  },
  "xiaomi": {
   "name": "Xiaomi",
   "doc": "https://platform.xiaomimimo.com/#/docs",
   "icon": "xiaomimimo.svg",
   "icon_mono": true
  },
  "xiaomi-token-plan-ams": {
   "name": "Xiaomi Token Plan (Europe)",
   "doc": "https://platform.xiaomimimo.com/#/docs",
   "icon": "xiaomimimo.svg",
   "icon_mono": true
  },
  "xiaomi-token-plan-cn": {
   "name": "Xiaomi Token Plan (China)",
   "doc": "https://platform.xiaomimimo.com/#/docs",
   "icon": "xiaomimimo.svg",
   "icon_mono": true
  },
  "xiaomi-token-plan-sgp": {
   "name": "Xiaomi Token Plan (Singapore)",
   "doc": "https://platform.xiaomimimo.com/#/docs",
   "icon": "xiaomimimo.svg",
   "icon_mono": true
  },
  "xpersona": {
   "name": "Xpersona",
   "doc": "https://www.xpersona.co/"
  },
  "zai": {
   "name": "Z.AI",
   "doc": "https://docs.z.ai/guides/overview/pricing",
   "icon": "zai.svg",
   "icon_mono": true
  },
  "zai-coding-plan": {
   "name": "Z.AI Coding Plan",
   "doc": "https://docs.z.ai/devpack/overview",
   "icon": "zai.svg",
   "icon_mono": true
  },
  "zeldoc": {
   "name": "Zeldoc",
   "doc": "https://docs.zeldoc.ai"
  },
  "zenifra": {
   "name": "Zenifra",
   "doc": "https://docs.zenifra.com"
  },
  "zenmux": {
   "name": "ZenMux",
   "doc": "https://zenmux.ai",
   "icon": "zenmux.svg",
   "icon_mono": true
  },
  "zhipuai": {
   "name": "Zhipu AI",
   "doc": "https://docs.z.ai/guides/overview/pricing",
   "icon": "zhipu-color.svg"
  },
  "zhipuai-coding-plan": {
   "name": "Zhipu AI Coding Plan",
   "doc": "https://docs.bigmodel.cn/cn/coding-plan/overview",
   "icon": "zhipu-color.svg"
  },
  "ppio": {
   "name": "ppio",
   "icon": "ppio-color.svg"
  },
  "fireworksai": {
   "name": "fireworksai",
   "icon": "fireworks-color.svg"
  },
  "higress": {
   "name": "higress",
   "icon": "higress-color.svg"
  },
  "zeroone": {
   "name": "zeroone",
   "icon": "zeroone-color.svg"
  },
  "ai360": {
   "name": "ai360",
   "icon": "ai360-color.svg"
  },
  "ai21": {
   "name": "ai21",
   "icon": "ai21.svg",
   "icon_mono": true
  },
  "azure-ai-foundry": {
   "name": "azure-ai-foundry",
   "icon": "azure-color.svg"
  },
  "vercelaigateway": {
   "name": "vercelaigateway",
   "icon": "vercel.svg",
   "icon_mono": true
  },
  "fal": {
   "name": "fal",
   "icon": "fal-color.svg"
  },
  "siliconcloud": {
   "name": "siliconcloud",
   "icon": "siliconcloud-color.svg"
  },
  "wenxin": {
   "name": "wenxin",
   "icon": "wenxin-color.svg"
  },
  "hyperbolic": {
   "name": "hyperbolic",
   "icon": "hyperbolic-color.svg"
  },
  "sambanova": {
   "name": "sambanova",
   "icon": "sambanova-color.svg"
  },
  "lambda": {
   "name": "lambda",
   "icon": "lambda.svg",
   "icon_mono": true
  },
  "infiniai": {
   "name": "infiniai",
   "icon": "infinigence-color.svg"
  },
  "aws-bedrock-mantle": {
   "name": "aws-bedrock-mantle",
   "icon": "bedrock-color.svg"
  },
  "canopywave": {
   "name": "canopywave"
  },
  "opencodeZen": {
   "name": "opencodeZen"
  },
  "streamlake": {
   "name": "streamlake",
   "icon": "streamlake-color.svg"
  },
  "opencodeCodingPlan": {
   "name": "opencodeCodingPlan"
  },
  "amazon": {
   "name": "amazon",
   "icon": "aws-color.svg"
  },
  "antgroup": {
   "name": "antgroup",
   "icon": "antgroup-color.svg"
  },
  "bedrock": {
   "name": "bedrock",
   "icon": "bedrock-color.svg"
  },
  "snowflake": {
   "name": "snowflake",
   "icon": "snowflake-color.svg"
  },
  "baichuan": {
   "name": "baichuan",
   "icon": "baichuan-color.svg"
  },
  "bfl": {
   "name": "bfl",
   "icon": "bfl.svg",
   "icon_mono": true
  },
  "volcengine": {
   "name": "volcengine",
   "icon": "volcengine-color.svg"
  },
  "bytedance": {
   "name": "bytedance",
   "icon": "bytedance-color.svg"
  },
  "azureai": {
   "name": "azureai",
   "icon": "azureai-color.svg"
  },
  "tencentcloud": {
   "name": "tencentcloud",
   "icon": "tencentcloud-color.svg"
  },
  "hunyuan": {
   "name": "hunyuan",
   "icon": "hunyuan-color.svg"
  },
  "sensenova": {
   "name": "sensenova",
   "icon": "sensenova-color.svg"
  },
  "vertexai": {
   "name": "vertexai",
   "icon": "vertexai-color.svg"
  },
  "ibm-watsonx": {
   "name": "ibm-watsonx",
   "icon": "ibm.svg",
   "icon_mono": true
  },
  "jina": {
   "name": "jina",
   "icon": "jina.svg",
   "icon_mono": true
  },
  "github": {
   "name": "github",
   "icon": "github.svg",
   "icon_mono": true
  },
  "internlm": {
   "name": "internlm",
   "icon": "internlm-color.svg"
  },
  "taichu": {
   "name": "taichu"
  },
  "xiaomimimo": {
   "name": "xiaomimimo",
   "icon": "xiaomimimo.svg",
   "icon_mono": true
  },
  "01-ai": {
   "name": "01-ai",
   "icon": "zeroone-color.svg"
  },
  "arcee": {
   "name": "Arcee AI",
   "icon": "arcee-color.svg"
  },
  "baai": {
   "name": "BAAI",
   "icon": "baai.svg",
   "icon_mono": true
  },
  "baidu": {
   "name": "baidu",
   "icon": "baidu-color.svg"
  },
  "deepgram": {
   "name": "Deepgram"
  },
  "elevenlabs": {
   "name": "ElevenLabs",
   "icon": "elevenlabs.svg",
   "icon_mono": true
  },
  "essentialai": {
   "name": "Essential AI",
   "icon": "essentialai-color.svg"
  },
  "ibm": {
   "name": "ibm",
   "icon": "ibm.svg",
   "icon_mono": true
  },
  "ideogram": {
   "name": "Ideogram",
   "icon": "ideogram.svg",
   "icon_mono": true
  },
  "inflection": {
   "name": "Inflection AI",
   "icon": "inflection.svg",
   "icon_mono": true
  },
  "kling": {
   "name": "Kling",
   "icon": "kling-color.svg"
  },
  "kwaipilot": {
   "name": "Kwaipilot",
   "icon": "kwaipilot-color.svg"
  },
  "liquid": {
   "name": "liquid",
   "icon": "liquid.svg",
   "icon_mono": true
  },
  "llava": {
   "name": "LLaVA",
   "icon": "llava-color.svg"
  },
  "luma": {
   "name": "Luma AI",
   "icon": "luma-color.svg"
  },
  "meta": {
   "name": "meta",
   "icon": "meta-color.svg"
  },
  "microsoft": {
   "name": "Microsoft",
   "icon": "microsoft-color.svg"
  },
  "myshell": {
   "name": "MyShell",
   "icon": "myshell-color.svg"
  },
  "nousresearch": {
   "name": "Nous Research",
   "icon": "nousresearch.svg",
   "icon_mono": true
  },
  "openchat": {
   "name": "OpenChat",
   "icon": "openchat-color.svg"
  },
  "other": {
   "name": "Other"
  },
  "pixverse": {
   "name": "PixVerse",
   "icon": "pixverse-color.svg"
  },
  "recraft": {
   "name": "Recraft",
   "icon": "recraft.svg",
   "icon_mono": true
  },
  "reka": {
   "name": "reka"
  },
  "runway": {
   "name": "Runway",
   "icon": "runway.svg",
   "icon_mono": true
  },
  "skywork": {
   "name": "Skywork",
   "icon": "skywork-color.svg"
  },
  "stability": {
   "name": "Stability AI",
   "icon": "stability-color.svg"
  },
  "suno": {
   "name": "Suno"
  },
  "tencent": {
   "name": "tencent",
   "icon": "tencent-color.svg"
  },
  "vidu": {
   "name": "Vidu",
   "icon": "vidu-color.svg"
  },
  "voyage": {
   "name": "Voyage AI",
   "icon": "voyage-color.svg"
  }
 },
 "models": [
  {
   "slug": "01-ai/01ai-yi-lightning",
   "model_name": "01ai-yi-lightning",
   "display_name": "yi-lightning",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "released_at": "2024-10-16",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "yi-lightning"
    }
   ]
  },
  {
   "slug": "01-ai/01ai-yi-vision-v2",
   "model_name": "01ai-yi-vision-v2",
   "display_name": "yi-vision-v2",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    }
   ],
   "released_at": "2024-05-13",
   "max_input_tokens": 16000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "yi-vision-v2"
    }
   ]
  },
  {
   "slug": "01-ai/llava-yi-34b",
   "model_name": "llava-yi-34b",
   "display_name": "llava-yi-34b",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "vision_understanding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llava-yi-34b"
    }
   ]
  },
  {
   "slug": "01-ai/Nous-Hermes-2-Yi-34B",
   "model_name": "Nous-Hermes-2-Yi-34B",
   "display_name": "Nous-Hermes-2-Yi-34B",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "nous-hermes-2-yi-34b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "NousResearch/Nous-Hermes-2-Yi-34B"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Nous-Hermes-2-Yi-34B",
    "nous-hermes-2-yi-34b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nous-Hermes-2-Yi-34B"
    }
   ]
  },
  {
   "slug": "01-ai/yi-1.5-34b-chat",
   "model_name": "yi-1.5-34b-chat",
   "display_name": "01-ai/yi-1.5-34b-chat",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.161765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.161765"
      }
     },
     "provider_model_id": "01-ai/yi-1.5-34b-chat"
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "01-ai/yi-1.5-34b-chat"
   ],
   "intro_i18n": {
    "zh-CN": "01.AI 最新开源微调模型，拥有 340 亿参数，支持多种对话场景，基于高质量数据训练，并对齐人类偏好。",
    "zh-TW": "01.AI 最新開源微調模型，擁有 340 億參數，支援多種對話場景，訓練於高品質資料，並對齊人類偏好。",
    "ja-JP": "01.AIの最新のオープンソース微調整モデル。34Bパラメータを持ち、複数の対話シナリオに対応。高品質なデータで学習され、人間の好みに合わせて調整されています。",
    "ru-RU": "Последняя открытая модель 01.AI с 34 миллиардами параметров, адаптированная для различных сценариев диалога, обученная на высококачественных данных и согласованная с человеческими предпочтениями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "01-ai/yi-1.5-34b-chat"
    }
   ]
  },
  {
   "slug": "01-ai/yi-1.5-9b-chat",
   "model_name": "yi-1.5-9b-chat",
   "display_name": "01-ai/yi-1.5-9b-chat",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      }
     },
     "provider_model_id": "01-ai/yi-1.5-9b-chat"
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "01-ai/yi-1.5-9b-chat"
   ],
   "intro_i18n": {
    "zh-CN": "01.AI 最新开源微调模型，拥有 90 亿参数，支持多种对话场景，基于高质量数据训练，并对齐人类偏好。",
    "zh-TW": "01.AI 最新開源微調模型，擁有 90 億參數，支援多種對話場景，訓練於高品質資料，並對齊人類偏好。",
    "ja-JP": "01.AIの最新のオープンソース微調整モデル。9Bパラメータを持ち、複数の対話シナリオに対応。高品質なデータで学習され、人間の好みに合わせて調整されています。",
    "ru-RU": "Последняя открытая модель 01.AI с 9 миллиардами параметров, адаптированная для различных сценариев диалога, обученная на высококачественных данных и согласованная с человеческими предпочтениями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "01-ai/yi-1.5-9b-chat"
    }
   ]
  },
  {
   "slug": "01-ai/Yi-34B",
   "model_name": "Yi-34B",
   "display_name": "Yi-34B",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "yi-34b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "zero-one-ai/Yi-34B"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "yi-34b",
    "zero-one-ai/Yi-34B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi-34B"
    }
   ]
  },
  {
   "slug": "01-ai/yi-34b-200k-capybara",
   "model_name": "yi-34b-200k-capybara",
   "display_name": "yi-34b-200k-capybara",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 200000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "yi-34b-200k-capybara"
    }
   ]
  },
  {
   "slug": "01-ai/yi-34b-chat",
   "model_name": "yi-34b-chat",
   "display_name": "yi-34b-chat",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Yi-1.5-34B在保留系列强大通用语言能力的基础上，通过对5000亿高质量token的增量训练，显著提升数学逻辑与编程能力。",
    "zh-TW": "Yi-1.5-34B 延續該系列強大的通用語言能力，並透過對 5000 億高品質語料的增量訓練，顯著提升數學邏輯與程式碼能力。",
    "ja-JP": "Yi-1.5-34Bは、シリーズの強力な言語能力を維持しつつ、500Bの高品質トークンによる段階的トレーニングにより、数学的論理とコーディング能力を大幅に向上させています。",
    "ru-RU": "Yi-1.5-34B сохраняет сильные языковые способности серии, а также использует инкрементальное обучение на 500 миллиардах высококачественных токенов для значительного улучшения логики, математики и программирования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "yi-34b-chat"
    }
   ]
  },
  {
   "slug": "01-ai/Yi-6B",
   "model_name": "Yi-6B",
   "display_name": "Yi-6B",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "yi-6b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "zero-one-ai/Yi-6B"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "yi-6b",
    "zero-one-ai/Yi-6B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi-6B"
    }
   ]
  },
  {
   "slug": "01-ai/yi-large",
   "model_name": "yi-large",
   "display_name": "Yi Large",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "accounts/yi-01-ai/models/yi-large"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.196"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.196"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "01-ai/yi-large"
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-05-13",
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "structured_output": true
   },
   "docs_url": "https://fireworks.ai/pricing",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "01-ai/yi-large",
    "accounts/yi-01-ai/models/yi-large"
   ],
   "intro_i18n": {
    "zh-CN": "Yi-Large 是一款顶级大语言模型，在 LMSYS 排行榜上仅次于 GPT-4、Gemini 1.5 Pro 和 Claude 3 Opus。该模型在多语言能力方面表现出色，尤其擅长西班牙语、中文、日语、德语和法语。Yi-Large 也非常适合开发者使用，采用与 OpenAI 相同的 API 架构，便于集成。",
    "zh-TW": "Yi-Large 是一款頂尖的大型語言模型，在 LMSYS 排行榜上僅次於 GPT-4、Gemini 1.5 Pro 與 Claude 3 Opus。其多語言能力出色，特別擅長西班牙語、中文、日語、德語與法語。Yi-Large 也對開發者友好，採用與 OpenAI 相同的 API 架構，便於整合。",
    "ja-JP": "Yi-Largeは、LMSYSリーダーボードにおいてGPT-4、Gemini 1.5 Pro、Claude 3 Opusに次ぐ上位にランクインする高性能LLMです。多言語対応に優れ、特にスペイン語、中国語、日本語、ドイツ語、フランス語で高い性能を発揮します。OpenAIと同じAPIスキーマを採用しており、開発者にとって統合が容易です。",
    "ru-RU": "Yi-Large — это высококлассная LLM, занимающая позицию сразу за GPT-4, Gemini 1.5 Pro и Claude 3 Opus в рейтинге LMSYS. Отличается выдающимися многоязычными возможностями, особенно в испанском, китайском, японском, немецком и французском языках. Yi-Large также удобна для разработчиков, так как использует ту же схему API, что и OpenAI, обеспечивая легкую интеграцию."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Large"
    }
   ]
  },
  {
   "slug": "01-ai/yi-large-fc",
   "model_name": "yi-large-fc",
   "display_name": "Yi Large FC",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "基于 yi-large 构建，增强了工具调用能力，适用于智能体和工作流场景。",
    "zh-TW": "基於 yi-large，增強工具調用能力，適用於代理與工作流程場景。",
    "ja-JP": "yi-largeをベースにツール呼び出し機能を強化し、エージェントやワークフローシナリオに適しています。",
    "ru-RU": "Построена на базе yi-large с расширенными возможностями вызова инструментов, подходит для сценариев агентов и рабочих процессов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Large FC"
    }
   ]
  },
  {
   "slug": "01-ai/yi-large-preview",
   "model_name": "yi-large-preview",
   "display_name": "Yi Large Preview",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "早期版本，推荐使用更新的 yi-large。",
    "zh-TW": "早期版本；建議使用更新的 yi-large。",
    "ja-JP": "初期バージョンです。より新しいyi-largeの使用を推奨します。",
    "ru-RU": "Ранняя версия; рекомендуется использовать более новую yi-large."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Large Preview"
    }
   ]
  },
  {
   "slug": "01-ai/yi-large-rag",
   "model_name": "yi-large-rag",
   "display_name": "Yi Large RAG",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.676471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.676471"
      }
     }
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.676471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.676471"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "基于 yi-large 的高级服务，结合检索与生成，支持实时网页搜索，提供精准答案。",
    "zh-TW": "基於 yi-large 的進階服務，結合檢索與生成，透過即時網頁搜尋提供精準答案。",
    "ja-JP": "yi-largeをベースにした高度なサービスで、検索と生成を組み合わせ、リアルタイムWeb検索による正確な回答を提供します。",
    "ru-RU": "Продвинутая служба на базе yi-large, объединяющая поиск и генерацию для точных ответов с поддержкой веб-поиска в реальном времени."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Large RAG"
    }
   ]
  },
  {
   "slug": "01-ai/yi-large-turbo",
   "model_name": "yi-large-turbo",
   "display_name": "Yi Large Turbo",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "在质量、速度和成本之间实现出色平衡，具备卓越性价比和性能。",
    "zh-TW": "具備卓越性價比與效能，兼顧品質、速度與成本。",
    "ja-JP": "品質、速度、コストのバランスに優れた高性能モデルです。",
    "ru-RU": "Исключительное соотношение цены и качества, настроено для оптимального баланса между качеством, скоростью и стоимостью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Large Turbo"
    }
   ]
  },
  {
   "slug": "01-ai/yi-lightning",
   "model_name": "yi-lightning",
   "display_name": "Yi Lightning",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.145588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.145588"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      }
     }
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.145588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.145588"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-10-16",
   "max_input_tokens": 12000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "knowledge_cutoff": "2024",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "最新高性能模型，推理速度更快，输出质量更高。",
    "zh-TW": "最新高效能模型，推理速度更快，輸出品質更高。",
    "ja-JP": "高速推論と高品質出力を実現した最新の高性能モデルです。",
    "ru-RU": "Новая высокопроизводительная модель с быстрой генерацией и высоким качеством вывода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Lightning"
    }
   ]
  },
  {
   "slug": "01-ai/yi-lightning-lite",
   "model_name": "yi-lightning-lite",
   "display_name": "Yi Lightning Lite",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.145588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.145588"
      }
     }
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.145588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.145588"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "轻量版本，推荐使用 yi-lightning。",
    "zh-TW": "輕量版本；建議使用 yi-lightning。",
    "ja-JP": "軽量版です。より高性能なyi-lightningの使用を推奨します。",
    "ru-RU": "Облегченная версия; рекомендуется использовать yi-lightning."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Lightning Lite"
    }
   ]
  },
  {
   "slug": "01-ai/yi-medium",
   "model_name": "yi-medium",
   "display_name": "Yi Medium",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      }
     }
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "调优后的中型模型，能力与性价比平衡，优化用于指令跟随任务。",
    "zh-TW": "調校後的中型模型，能力與性價比平衡，優化指令遵循表現。",
    "ja-JP": "指示追従に最適化された中規模モデルで、性能とコストのバランスに優れています。",
    "ru-RU": "Настроенная модель среднего размера с балансом возможностей и стоимости, оптимизирована для следования инструкциям."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Medium"
    }
   ]
  },
  {
   "slug": "01-ai/yi-medium-200k",
   "model_name": "yi-medium-200k",
   "display_name": "Yi Medium 200k",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.499"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.499"
      }
     }
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-03-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "支持 200K 长上下文的模型，适用于深度长文本理解与生成。",
    "zh-TW": "支援 200K 長上下文的模型，適用於深度長文理解與生成。",
    "ja-JP": "200Kの長文コンテキストに対応し、長文理解と生成に優れたモデルです。",
    "ru-RU": "Модель с длинным контекстом (200K) для глубокого понимания и генерации длинных текстов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Medium 200k"
    }
   ]
  },
  {
   "slug": "01-ai/yi-spark",
   "model_name": "yi-spark",
   "display_name": "Yi Spark",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      }
     }
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "紧凑快速的模型，强化了数学和编程能力。",
    "zh-TW": "緊湊快速的模型，強化數學與編碼能力。",
    "ja-JP": "コンパクトで高速なモデルで、数学とコーディング能力が強化されています。",
    "ru-RU": "Компактная и быстрая модель с усиленными возможностями в математике и программировании."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Spark"
    }
   ]
  },
  {
   "slug": "01-ai/yi-vision",
   "model_name": "yi-vision",
   "display_name": "Yi Vision",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    },
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "适用于复杂任务的视觉模型，具备强大的图像理解与分析能力。",
    "zh-TW": "適用於複雜任務的視覺模型，具備強大的圖像理解與分析能力。",
    "ja-JP": "複雑なタスクに対応するビジョンモデルで、画像理解と分析に優れています。",
    "ru-RU": "Модель компьютерного зрения для сложных задач с мощным пониманием изображений и анализом."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Vision"
    }
   ]
  },
  {
   "slug": "01-ai/yi-vision-v2",
   "model_name": "yi-vision-v2",
   "display_name": "Yi Vision V2",
   "vendor": "01-ai",
   "pricing": [
    {
     "provider": "zeroone",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "适用于复杂任务的视觉模型，具备强大的多图理解与分析能力。",
    "zh-TW": "適用於複雜任務的視覺模型，具備強大的多圖理解與分析能力。",
    "ja-JP": "複雑なタスクに対応するビジョンモデルで、複数画像の理解と分析に優れています。",
    "ru-RU": "Модель компьютерного зрения для сложных задач с мощным пониманием и анализом нескольких изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Yi Vision V2"
    }
   ]
  },
  {
   "slug": "360/360gpt-pro",
   "model_name": "360gpt-pro",
   "display_name": "360GPT Pro",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "max_output_tokens": 7000,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "360GPT Pro 是 360 的核心 AI 模型，具备高效文本处理能力，适用于多种自然语言处理场景，支持长文本理解和多轮对话。",
    "zh-TW": "360GPT Pro 是 360 AI 的核心模型，具備高效文本處理能力，適用於多樣化 NLP 應用場景，支援長文本理解與多輪對話。",
    "ja-JP": "360GPT Proは、さまざまなNLPシナリオに対応する効率的なテキスト処理を備えた360の主要AIモデルで、長文理解やマルチターン対話をサポートします。",
    "ru-RU": "360GPT Pro — ключевая модель ИИ от 360 с эффективной обработкой текста для различных задач обработки естественного языка, поддерживает понимание длинных текстов и многотуровой диалог."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360GPT Pro"
    }
   ]
  },
  {
   "slug": "360/360gpt-pro-trans",
   "model_name": "360gpt-pro-trans",
   "display_name": "360GPT Pro Trans",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "专为翻译任务优化的模型，深度微调以实现领先的翻译质量。",
    "zh-TW": "專為翻譯任務設計的模型，經深度微調以實現領先的翻譯品質。",
    "ja-JP": "高品質な翻訳性能を実現するために深く微調整された、翻訳特化型モデルです。",
    "ru-RU": "Специализированная модель для перевода, глубоко дообученная для достижения передового качества перевода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360GPT Pro Trans"
    }
   ]
  },
  {
   "slug": "360/360gpt-turbo",
   "model_name": "360gpt-turbo",
   "display_name": "360GPT Turbo",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {},
   "max_output_tokens": 7000,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "360GPT Turbo 具备强大的计算与对话能力，语义理解与生成效率出色，适合企业与开发者使用。",
    "zh-TW": "360GPT Turbo 具備強大運算與對話能力，語義理解與生成效率優異，適合企業與開發者使用。",
    "ja-JP": "360GPT Turboは、優れた意味理解と生成効率を備えた高性能な計算・対話能力を提供し、企業や開発者に最適です。",
    "ru-RU": "360GPT Turbo обеспечивает высокую вычислительную и диалоговую производительность с отличным пониманием семантики и эффективной генерацией, идеально подходит для бизнеса и разработчиков."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360GPT Turbo"
    }
   ]
  },
  {
   "slug": "360/360gpt-turbo-responsibility-8k",
   "model_name": "360gpt-turbo-responsibility-8k",
   "display_name": "360GPT Turbo Responsibility 8K",
   "vendor": "360",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "360GPT Turbo Responsibility 8K 强调语义安全与内容责任，适用于内容敏感型应用，确保用户体验的准确性与稳健性。",
    "zh-TW": "360GPT Turbo Responsibility 8K 著重語義安全與內容責任，適用於敏感應用場景，確保準確且穩健的使用者體驗。",
    "ja-JP": "360GPT Turbo Responsibility 8Kは、意味的な安全性と責任ある出力を重視し、コンテンツに敏感なアプリケーションにおいて正確で堅牢なユーザー体験を提供します。",
    "ru-RU": "360GPT Turbo Responsibility 8K делает акцент на семантической безопасности и ответственности в чувствительных к контенту приложениях, обеспечивая точный и надежный пользовательский опыт."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360GPT Turbo Responsibility 8K"
    }
   ]
  },
  {
   "slug": "360/360gpt2-o1",
   "model_name": "360gpt2-o1",
   "display_name": "360GPT2 o1",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "360gpt2-o1 通过树搜索构建思维链，结合反思机制与强化学习训练，实现自我反思与自我纠错。",
    "zh-TW": "360gpt2-o1 結合樹狀搜尋與反思機制，透過強化學習訓練建立思維鏈，實現自我反思與修正能力。",
    "ja-JP": "360gpt2-o1は、ツリー探索と内省メカニズム、強化学習を組み合わせて思考の連鎖を構築し、自己内省と自己修正を可能にします。",
    "ru-RU": "360gpt2-o1 формирует цепочку рассуждений с помощью древовидного поиска, механизма рефлексии и обучения с подкреплением, позволяя модели к саморефлексии и самокоррекции."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360GPT2 o1"
    }
   ]
  },
  {
   "slug": "360/360gpt2-pro",
   "model_name": "360gpt2-pro",
   "display_name": "360GPT2 Pro",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "max_output_tokens": 7000,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "360GPT2 Pro 是 360 推出的高级自然语言处理模型，擅长文本生成与理解，尤其适用于创意任务，能处理复杂转换与角色扮演。",
    "zh-TW": "360GPT2 Pro 是 360 推出的進階 NLP 模型，擅長創意生成與文本理解，能處理複雜轉換與角色扮演任務。",
    "ja-JP": "360GPT2 Proは、360が開発した高度なNLPモデルで、創造的なタスクにおいて優れたテキスト生成と理解を実現し、複雑な変換やロールプレイにも対応します。",
    "ru-RU": "360GPT2 Pro — продвинутая модель обработки естественного языка от 360 с выдающимися возможностями генерации и понимания текста, особенно в творческих задачах, включая сложные преобразования и ролевые сценарии."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360GPT2 Pro"
    }
   ]
  },
  {
   "slug": "360/360zhinao-pro-32k-thinking-vision",
   "model_name": "360zhinao-pro-32k-thinking-vision",
   "display_name": "360Zhinao Pro 32K Thinking Vision",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360Zhinao Pro 32K Thinking Vision"
    }
   ]
  },
  {
   "slug": "360/360zhinao-turbo",
   "model_name": "360zhinao-turbo",
   "display_name": "360Zhinao Turbo",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360Zhinao Turbo"
    }
   ]
  },
  {
   "slug": "360/360zhinao-turbo-qwen-plus",
   "model_name": "360zhinao-turbo-qwen-plus",
   "display_name": "360Zhinao Turbo Qwen Plus",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360Zhinao Turbo Qwen Plus"
    }
   ]
  },
  {
   "slug": "360/360zhinao2-o1",
   "model_name": "360zhinao2-o1",
   "display_name": "360Zhinao2 o1",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "360zhinao2-o1 通过树搜索构建思维链，结合反思机制与强化学习训练，实现自我反思与自我纠错。",
    "zh-TW": "360zhinao2-o1 結合樹狀搜尋與反思機制，透過強化學習訓練建立思維鏈，實現自我反思與修正能力。",
    "ja-JP": "360zhinao2-o1は、ツリー探索と内省メカニズム、強化学習を通じて思考の連鎖を構築し、自己内省と自己修正を可能にします。",
    "ru-RU": "360zhinao2-o1 формирует цепочку рассуждений с помощью древовидного поиска, механизма рефлексии и обучения с подкреплением, позволяя модели к саморефлексии и самокоррекции."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360Zhinao2 o1"
    }
   ]
  },
  {
   "slug": "360/360zhinao2-o1.5",
   "model_name": "360zhinao2-o1.5",
   "display_name": "360Zhinao2 o1.5",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "360智脑最强大的推理模型，具备最强能力，支持工具调用和高级推理。",
    "zh-TW": "360智腦最強大的推理模型，具備最強的能力，支持工具調用和高級推理。",
    "ja-JP": "360智脑の最強推論モデル。最強の能力を備え、ツール呼び出しと高度な推論の両方をサポートします。",
    "ru-RU": "360 Zhinao — самая мощная модель рассуждений, обладающая сильнейшими возможностями и поддерживающая как вызов инструментов, так и продвинутые рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360Zhinao2 o1.5"
    }
   ]
  },
  {
   "slug": "360/360zhinao3-o1.5",
   "model_name": "360zhinao3-o1.5",
   "display_name": "360Zhinao3 o1.5",
   "vendor": "360",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "360智脑下一代推理模型。",
    "zh-TW": "360智腦下一代推理模型。",
    "ja-JP": "360智脳次世代推論モデル。",
    "ru-RU": "360 Zhinao — модель рассуждений следующего поколения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "360Zhinao3 o1.5"
    }
   ]
  },
  {
   "slug": "ai21/ai21-jamba-1.5-large",
   "model_name": "ai21-jamba-1.5-large",
   "display_name": "AI21 Jamba 1.5 Large",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ai21-labs/ai21-jamba-1.5-large"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2024-08-29",
   "knowledge_cutoff": "2024-03",
   "max_input_tokens": 256000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "jamba",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ai21-labs/ai21-jamba-1.5-large"
   ],
   "intro_i18n": {
    "zh-CN": "一个拥有 3980 亿参数（其中 940 亿激活）的多语言模型，支持 256K 上下文窗口、函数调用、结构化输出和基于事实的生成。",
    "zh-TW": "一款具備 398B 參數（94B 啟用）的多語言模型，支援 256K 上下文視窗、函式呼叫、結構化輸出與基於事實的生成。",
    "ja-JP": "398Bパラメータ（うち94Bがアクティブ）の多言語モデルで、256Kのコンテキストウィンドウ、関数呼び出し、構造化出力、根拠に基づく生成をサポートします。",
    "ru-RU": "Многоязычная модель с 398 миллиардами параметров (94 миллиарда активных), поддерживающая контекст до 256 тысяч токенов, вызов функций, структурированный вывод и генерацию с привязкой к источникам."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AI21 Jamba 1.5 Large"
    }
   ]
  },
  {
   "slug": "ai21/ai21-jamba-1.5-mini",
   "model_name": "ai21-jamba-1.5-mini",
   "display_name": "AI21 Jamba 1.5 Mini",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ai21-labs/ai21-jamba-1.5-mini"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-08-29",
   "knowledge_cutoff": "2024-03",
   "max_input_tokens": 256000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "jamba",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ai21-labs/ai21-jamba-1.5-mini"
   ],
   "intro_i18n": {
    "zh-CN": "一个拥有 520 亿参数（其中 120 亿激活）的多语言模型，支持 256K 上下文窗口、函数调用、结构化输出和基于事实的生成。",
    "zh-TW": "一款具備 52B 參數（12B 啟用）的多語言模型，支援 256K 上下文視窗、函式呼叫、結構化輸出與基於事實的生成。",
    "ja-JP": "52Bパラメータ（うち12Bがアクティブ）の多言語モデルで、256Kのコンテキストウィンドウ、関数呼び出し、構造化出力、根拠に基づく生成をサポートします。",
    "ru-RU": "Многоязычная модель с 52 миллиардами параметров (12 миллиардов активных), поддерживающая контекст до 256 тысяч токенов, вызов функций, структурированный вывод и генерацию с привязкой к источникам."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AI21 Jamba 1.5 Mini"
    }
   ]
  },
  {
   "slug": "ai21/ai21.j2-mid-v1",
   "model_name": "ai21.j2-mid-v1",
   "display_name": "ai21.j2-mid-v1",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 8191,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ai21.j2-mid-v1"
    }
   ]
  },
  {
   "slug": "ai21/ai21.j2-ultra-v1",
   "model_name": "ai21.j2-ultra-v1",
   "display_name": "ai21.j2-ultra-v1",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "18.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18.8"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "18.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18.8"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "18.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18.8"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 8191,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ai21.j2-ultra-v1"
    }
   ]
  },
  {
   "slug": "ai21/aihubmix-Jamba-1-5-Large",
   "model_name": "aihubmix-Jamba-1-5-Large",
   "display_name": "aihubmix-Jamba-1-5-Large",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.8"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Jamba-1-5-Large"
    }
   ]
  },
  {
   "slug": "ai21/j2-light",
   "model_name": "j2-light",
   "display_name": "j2-light",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "ai21/j2-mid",
   "model_name": "j2-mid",
   "display_name": "j2-mid",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "ai21/j2-ultra",
   "model_name": "j2-ultra",
   "display_name": "j2-ultra",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "ai21/jamba-1.5",
   "model_name": "jamba-1.5",
   "display_name": "jamba-1.5",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "ai21/jamba-1.5-large",
   "model_name": "jamba-1.5-large",
   "display_name": "jamba-1.5-large",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "ai21.jamba-1-5-large-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "ai21.jamba-1-5-large-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "ai21/jamba-1-5-large"
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-08-15",
   "knowledge_cutoff": "2024-08",
   "family": "jamba",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ai21.jamba-1-5-large-v1:0",
    "ai21/jamba-1-5-large"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "open_weights: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "ai21/jamba-1.5-large@001",
   "model_name": "jamba-1.5-large@001",
   "display_name": "jamba-1.5-large@001",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "ai21/jamba-1.5-mini",
   "model_name": "jamba-1.5-mini",
   "display_name": "jamba-1.5-mini",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry+pricetoken",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "ai21.jamba-1-5-mini-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "ai21.jamba-1-5-mini-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "ai21/jamba-1-5-mini"
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "released_at": "2025-06-01",
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2024-08",
   "family": "jamba",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ai21.jamba-1-5-mini-v1:0",
    "ai21/jamba-1-5-mini"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "open_weights: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "ai21/jamba-1.5-mini@001",
   "model_name": "jamba-1.5-mini@001",
   "display_name": "jamba-1.5-mini@001",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "ai21/jamba-1.6-large",
   "model_name": "jamba-1.6-large",
   "display_name": "jamba-1.6-large",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "ai21/jamba-1.6-large"
    }
   ],
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "max_input_tokens": 256000,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ai21/jamba-1.6-large"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jamba-1.6-large"
    }
   ]
  },
  {
   "slug": "ai21/jamba-1.6-mini",
   "model_name": "jamba-1.6-mini",
   "display_name": "jamba-1.6-mini",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "ai21/jamba-1.6-mini"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ai21/jamba-1.6-mini"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jamba-1.6-mini"
    }
   ]
  },
  {
   "slug": "ai21/jamba-instruct",
   "model_name": "jamba-instruct",
   "display_name": "jamba-instruct",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "ai21.jamba-instruct-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "ai21.jamba-instruct-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "ai21/jamba-instruct"
    }
   ],
   "max_input_tokens": 70000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ai21.jamba-instruct-v1:0",
    "ai21/jamba-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jamba-instruct"
    }
   ]
  },
  {
   "slug": "ai21/jamba-large",
   "model_name": "jamba-large",
   "display_name": "Jamba Large",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.99"
      }
     }
    }
   ],
   "released_at": "2025-03-06",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "我们最强大、最先进的模型，专为复杂企业任务设计，性能卓越。",
    "zh-TW": "我們最強大、最先進的模型，專為複雜企業任務設計，具備卓越效能。",
    "ja-JP": "Jamba Large は、複雑な企業向けタスクに対応する最も強力で高度なモデルです。",
    "ru-RU": "Наша самая мощная и продвинутая модель, предназначенная для сложных корпоративных задач с выдающейся производительностью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Jamba Large"
    }
   ]
  },
  {
   "slug": "ai21/jamba-large-1.6",
   "model_name": "jamba-large-1.6",
   "display_name": "jamba-large-1.6",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.99"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {},
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-03-12",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "ai21/jamba-large-1.7",
   "model_name": "jamba-large-1.7",
   "display_name": "jamba-large-1.7",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry+pricetoken",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "ai21/jamba-large-1.7"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.99"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "ai21/jamba-large-1.7"
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-08-01",
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "knowledge_cutoff": "2024-08",
   "family": "jamba",
   "parameters": {
    "supported": [
     "max_tokens",
     "response_format",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ai21/jamba-large-1.7",
    "jamba-large-1-7"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "ai21/jamba-mini",
   "model_name": "jamba-mini",
   "display_name": "Jamba Mini",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      }
     }
    }
   ],
   "released_at": "2025-03-06",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "同类中效率最高的模型，在速度与质量之间实现平衡，占用资源更少。",
    "zh-TW": "同級中最具效率的模型，在速度與品質之間取得平衡，佔用資源更少。",
    "ja-JP": "Jamba Mini は、速度と品質のバランスに優れた、同クラスで最も効率的なモデルです。",
    "ru-RU": "Самая эффективная модель в своем классе, обеспечивающая баланс между скоростью и качеством при минимальных ресурсах."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Jamba Mini"
    }
   ]
  },
  {
   "slug": "ai21/jamba-mini-1.6",
   "model_name": "jamba-mini-1.6",
   "display_name": "jamba-mini-1.6",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {},
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-03-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "ai21/jamba-mini-1.7",
   "model_name": "jamba-mini-1.7",
   "display_name": "jamba-mini-1.7",
   "vendor": "ai21",
   "pricing": [
    {
     "provider": "ai21",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {},
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "alibaba/alibaba-qwen3-32b",
   "model_name": "alibaba-qwen3-32b",
   "display_name": "Qwen3-32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-30",
   "max_input_tokens": 131000,
   "max_output_tokens": 40960,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-32B"
    }
   ]
  },
  {
   "slug": "alibaba/bai-qwen3-vl-235b-a22b-instruct",
   "model_name": "bai-qwen3-vl-235b-a22b-instruct",
   "display_name": "bai-qwen3-vl-235b-a22b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.274"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.096"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bai-qwen3-vl-235b-a22b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/code-qwen-1p5-7b",
   "model_name": "code-qwen-1p5-7b",
   "display_name": "CodeQwen 1.5 7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-qwen-1p5-7b"
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-qwen-1p5-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CodeQwen 1.5 7B"
    }
   ]
  },
  {
   "slug": "alibaba/cogito-v1-preview-qwen-14b",
   "model_name": "cogito-v1-preview-qwen-14b",
   "display_name": "Cogito v1 Preview Qwen 14B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/cogito-v1-preview-qwen-14b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/cogito-v1-preview-qwen-14b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cogito v1 Preview Qwen 14B"
    }
   ]
  },
  {
   "slug": "alibaba/cogito-v1-preview-qwen-32B",
   "model_name": "cogito-v1-preview-qwen-32B",
   "display_name": "Cogito v1 Preview Qwen 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "cogito-v1-preview-qwen-32b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.7999999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7999999999999998"
      }
     },
     "provider_model_id": "deepcogito/cogito-v1-preview-qwen-32B"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-05-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/cogito-v1-preview-qwen-32b",
    "cogito-v1-preview-qwen-32b",
    "deepcogito/cogito-v1-preview-qwen-32B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cogito v1 Preview Qwen 32B"
    }
   ]
  },
  {
   "slug": "alibaba/dolphin-2-9-2-qwen2-72b",
   "model_name": "dolphin-2-9-2-qwen2-72b",
   "display_name": "Dolphin 72b",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/dolphin-2-9-2-qwen2-72b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "cognitivecomputations/dolphin-2.9.2-qwen2-72b"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-02-27",
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/dolphin-2-9-2-qwen2-72b",
    "cognitivecomputations/dolphin-2.9.2-qwen2-72b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Dolphin 72b"
    }
   ]
  },
  {
   "slug": "alibaba/e2ee-qwen-2-5-7b-p",
   "model_name": "e2ee-qwen-2-5-7b-p",
   "display_name": "Qwen 2.5 7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    }
   ],
   "released_at": "2026-03-18",
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 7B"
    }
   ]
  },
  {
   "slug": "alibaba/e2ee-qwen3-30b-a3b-p",
   "model_name": "e2ee-qwen3-30b-a3b-p",
   "display_name": "Qwen3 30B A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.69"
      }
     }
    }
   ],
   "released_at": "2026-03-18",
   "max_input_tokens": 256000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 30B A3B"
    }
   ]
  },
  {
   "slug": "alibaba/e2ee-qwen3-6-27b",
   "model_name": "e2ee-qwen3-6-27b",
   "display_name": "Qwen 3.6 27B FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.346"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.46"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.171"
      }
     }
    }
   ],
   "released_at": "2026-07-07",
   "max_input_tokens": 256000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "Qwen 3.6 27B FP8"
    }
   ]
  },
  {
   "slug": "alibaba/e2ee-qwen3-6-35b-a3b",
   "model_name": "e2ee-qwen3-6-35b-a3b",
   "display_name": "Qwen 3.6 35B A3B FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.182"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    }
   ],
   "released_at": "2026-05-20",
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.6 35B A3B FP8"
    }
   ]
  },
  {
   "slug": "alibaba/e2ee-qwen3-6-35b-a3b-uncensored-p",
   "model_name": "e2ee-qwen3-6-35b-a3b-uncensored-p",
   "display_name": "Qwen3.6 35B A3B Uncensored",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.88"
      }
     }
    }
   ],
   "released_at": "2026-05-24",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 35B A3B Uncensored"
    }
   ]
  },
  {
   "slug": "alibaba/e2ee-qwen3-vl-30b-a3b-p",
   "model_name": "e2ee-qwen3-vl-30b-a3b-p",
   "display_name": "Qwen3 VL 30B A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "released_at": "2026-03-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 VL 30B A3B"
    }
   ]
  },
  {
   "slug": "alibaba/eva-qwen-2.5-32b",
   "model_name": "eva-qwen-2.5-32b",
   "display_name": "eva-qwen-2.5-32b",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.4"
      }
     },
     "provider_model_id": "eva-unit-01/eva-qwen-2.5-32b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "eva-unit-01/eva-qwen-2.5-32b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "eva-qwen-2.5-32b"
    }
   ]
  },
  {
   "slug": "alibaba/eva-qwen-2.5-72b",
   "model_name": "eva-qwen-2.5-72b",
   "display_name": "eva-qwen-2.5-72b",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "eva-unit-01/eva-qwen-2.5-72b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "eva-unit-01/eva-qwen-2.5-72b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "eva-qwen-2.5-72b"
    }
   ]
  },
  {
   "slug": "alibaba/EVA-Qwen2.5-32B-v0.2",
   "model_name": "EVA-Qwen2.5-32B-v0.2",
   "display_name": "EVA-Qwen2.5-32B-v0.2",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7989999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7989999999999999"
      }
     },
     "provider_model_id": "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-07-26",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "EVA-Qwen2.5-32B-v0.2"
    }
   ]
  },
  {
   "slug": "alibaba/EVA-Qwen2.5-72B-v0.2",
   "model_name": "EVA-Qwen2.5-72B-v0.2",
   "display_name": "EVA-Qwen2.5-72B-v0.2",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7989999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7989999999999999"
      }
     },
     "provider_model_id": "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-09-25",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "EVA-Qwen2.5-72B-v0.2"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen2p5-14b-instruct",
   "model_name": "fireworks/models/qwen2p5-14b-instruct",
   "display_name": "Qwen2.5 14B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-14b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-14b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 14B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen2p5-7b",
   "model_name": "fireworks/models/qwen2p5-7b",
   "display_name": "Qwen2.5 7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-7b"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-7b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 7B"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen3-reranker-0p6b",
   "model_name": "fireworks/models/qwen3-reranker-0p6b",
   "display_name": "Qwen3 Reranker 0.6B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-reranker-0p6b"
    }
   ],
   "max_input_tokens": 40960,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3-reranker-0p6b"
   ],
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Reranker 0.6B"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen3p5-122b-a10b",
   "model_name": "fireworks/models/qwen3p5-122b-a10b",
   "display_name": "Qwen 3.5 122B A10B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3p5-122b-a10b"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3p5-122b-a10b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.5 122B A10B"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen3p5-27b",
   "model_name": "fireworks/models/qwen3p5-27b",
   "display_name": "Qwen3.5 27B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3p5-27b"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3p5-27b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen3p5-35b-a3b",
   "model_name": "fireworks/models/qwen3p5-35b-a3b",
   "display_name": "Qwen 3.5 35B A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3p5-35b-a3b"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3p5-35b-a3b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.5 35B A3B"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen3p5-397b-a17b",
   "model_name": "fireworks/models/qwen3p5-397b-a17b",
   "display_name": "Qwen3.5 397B A17B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3p5-397b-a17b"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3p5-397b-a17b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 397B A17B"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen3p5-9b",
   "model_name": "fireworks/models/qwen3p5-9b",
   "display_name": "Qwen3.5 9B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3p5-9b"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3p5-9b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 9B"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen3p6-27b",
   "model_name": "fireworks/models/qwen3p6-27b",
   "display_name": "Qwen3.6 27B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3p6-27b"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3p6-27b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 27B"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen3p6-35b-a3b",
   "model_name": "fireworks/models/qwen3p6-35b-a3b",
   "display_name": "Qwen3.6-35B-A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3p6-35b-a3b"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3p6-35b-a3b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6-35B-A3B"
    }
   ]
  },
  {
   "slug": "alibaba/fireworks/models/qwen3p7-max",
   "model_name": "fireworks/models/qwen3p7-max",
   "display_name": "Qwen3.7 Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3p7-max"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3p7-max"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.7 Max"
    }
   ]
  },
  {
   "slug": "alibaba/gme-qwen2-vl-2b-instruct",
   "model_name": "gme-qwen2-vl-2b-instruct",
   "display_name": "gme-qwen2-vl-2b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.138"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.138"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gme-qwen2-vl-2b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/GrayLine-Qwen3-8B",
   "model_name": "GrayLine-Qwen3-8B",
   "display_name": "Grayline Qwen3 8B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "soob3123/GrayLine-Qwen3-8B"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-09-25",
   "max_input_tokens": 16384,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "soob3123/GrayLine-Qwen3-8B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grayline Qwen3 8B"
    }
   ]
  },
  {
   "slug": "alibaba/happyhorse-1.0-i2v",
   "model_name": "happyhorse-1.0-i2v",
   "display_name": "HappyHorse-1.0-I2V",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.235294"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "alibaba/happyhorse-1.0-i2v"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.2"
      }
     }
    }
   ],
   "released_at": "2026-04-22",
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/happyhorse-1.0-i2v"
   ],
   "intro_i18n": {
    "zh-CN": "HappyHorse-1.0-I2V 支持图生视频，能够生成高度逼真的动态画面。它能准确理解文本语义，生成流畅自然、细节丰富的高质量视频。",
    "zh-TW": "HappyHorse-1.0-I2V 支援圖像轉影片生成，呈現高度真實的動態畫面。能精準理解文字語意，生成流暢、自然且細節豐富的高品質影片。",
    "ja-JP": "HappyHorse-1.0-I2Vは、テキストから動画生成をサポートし、非常に忠実な動的ビジュアルを提供します。テキストの意味を正確に理解し、滑らかで自然で詳細に富んだ高品質な動画を生成します。",
    "ru-RU": "HappyHorse-1.0-I2V поддерживает генерацию видео по изображению, создавая высококачественные динамические сцены. Модель точно понимает текстовые описания и создаёт реалистичные, плавные и детализированные видеоролики."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HappyHorse-1.0-I2V"
    }
   ]
  },
  {
   "slug": "alibaba/happyhorse-1.0-r2v",
   "model_name": "happyhorse-1.0-r2v",
   "display_name": "HappyHorse-1.0-R2V",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.235294"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "alibaba/happyhorse-1.0-r2v"
    }
   ],
   "released_at": "2026-04-26",
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/happyhorse-1.0-r2v"
   ],
   "intro_i18n": {
    "zh-CN": "HappyHorse-1.0-R2V 支持基于参考图的视频生成，主体与场景稳定性更强。支持最多 9 张参考图，在忠实呈现创意意图的同时增强表现力。",
    "zh-TW": "HappyHorse-1.0-R2V 支援基於參考圖像的影片生成，主體與場景一致性更強。支持最多 9 張參考圖像，準確保留創意意圖並呈現更高的表現力。",
    "ja-JP": "HappyHorse-1.0-R2Vは、参照ベースの動画生成をサポートし、より安定した被写体とシーンの一貫性を提供します。最大9枚の参照画像をサポートし、創造的な意図を正確に保持し、表現力を強化します。",
    "ru-RU": "HappyHorse-1.0-R2V поддерживает генерацию видео на основе референсов, обеспечивая более стабильную передачу внешнего вида объектов и сцены. Поддерживает до 9 референсных изображений, точно сохраняет творческий замысел и обладает усиленной выразительностью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HappyHorse-1.0-R2V"
    }
   ]
  },
  {
   "slug": "alibaba/happyhorse-1.0-t2v",
   "model_name": "happyhorse-1.0-t2v",
   "display_name": "HappyHorse-1.0-T2V",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.235294"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.24"
      }
     },
     "provider_model_id": "alibaba/happyhorse-1.0-t2v"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "released_at": "2026-04-21",
   "model_type": "video_generation",
   "capabilities": {
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/happyhorse-1.0-t2v"
   ],
   "intro_i18n": {
    "zh-CN": "HappyHorse-1.0-T2V 支持文生视频，能够生成高度逼真的动态画面。它能准确理解文本语义，生成流畅自然、细节丰富的高质量视频。",
    "zh-TW": "HappyHorse-1.0-T2V 支援文本轉影片生成，呈現高度真實的動態畫面。能精準理解文字語意，生成流暢、自然且細節豐富的高品質影片。",
    "ja-JP": "HappyHorse-1.0-T2Vは、テキストから動画生成をサポートし、非常に忠実な動的ビジュアルを提供します。テキストの意味を正確に理解し、滑らかで自然で詳細に富んだ高品質な動画を生成します。",
    "ru-RU": "HappyHorse-1.0-T2V поддерживает генерацию видео по тексту, создавая реалистичные динамические сцены. Она точно интерпретирует текстовую семантику и генерирует высококачественные плавные и детализированные видеоролики."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HappyHorse-1.0-T2V"
    }
   ]
  },
  {
   "slug": "alibaba/happyhorse-1.1-i2v",
   "model_name": "happyhorse-1.1-i2v",
   "display_name": "happyhorse-1.1-i2v",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "alibaba/happyhorse-1.1-i2v"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/happyhorse-1.1-i2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "happyhorse-1.1-i2v"
    }
   ]
  },
  {
   "slug": "alibaba/happyhorse-1.1-r2v",
   "model_name": "happyhorse-1.1-r2v",
   "display_name": "happyhorse-1.1-r2v",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "alibaba/happyhorse-1.1-r2v"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/happyhorse-1.1-r2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "happyhorse-1.1-r2v"
    }
   ]
  },
  {
   "slug": "alibaba/meta-marco-o1",
   "model_name": "meta-marco-o1",
   "display_name": "marco-o1",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "released_at": "2025-08-06",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "marco-o1"
    }
   ]
  },
  {
   "slug": "alibaba/parasail-qwen25-vl-72b-instruct",
   "model_name": "parasail-qwen25-vl-72b-instruct",
   "display_name": "parasail/parasail-qwen25-vl-72b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "parasail/parasail-qwen25-vl-72b-instruct"
    }
   ],
   "released_at": "2025-02-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "parasail/parasail-qwen25-vl-72b-instruct"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "parasail/parasail-qwen25-vl-72b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/parasail-qwen3-235b-a22b-instruct-2507",
   "model_name": "parasail-qwen3-235b-a22b-instruct-2507",
   "display_name": "parasail/parasail-qwen3-235b-a22b-instruct-2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "parasail/parasail-qwen3-235b-a22b-instruct-2507"
    }
   ],
   "released_at": "2025-07-21",
   "max_input_tokens": 262144,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "parasail/parasail-qwen3-235b-a22b-instruct-2507"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "parasail/parasail-qwen3-235b-a22b-instruct-2507"
    }
   ]
  },
  {
   "slug": "alibaba/ppio-qwen-qwen-2-5-72b-instruct",
   "model_name": "ppio-qwen-qwen-2-5-72b-instruct",
   "display_name": "qwen/qwen-2.5-72b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-06-10",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen-2.5-72b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/ppio-qwen-qwen2.5-vl-72b-instruct",
   "model_name": "ppio-qwen-qwen2.5-vl-72b-instruct",
   "display_name": "qwen/qwen2.5-vl-72b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen2.5-vl-72b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/ppio-qwen-qwen3-235b-a22b-fp8",
   "model_name": "ppio-qwen-qwen3-235b-a22b-fp8",
   "display_name": "qwen/qwen3-235b-a22b-fp8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "released_at": "2025-06-10",
   "max_input_tokens": 40960,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen3-235b-a22b-fp8"
    }
   ]
  },
  {
   "slug": "alibaba/ppio-qwen-qwen3-30b-a3b-fp8",
   "model_name": "ppio-qwen-qwen3-30b-a3b-fp8",
   "display_name": "qwen/qwen3-30b-a3b-fp8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2025-06-10",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen3-30b-a3b-fp8"
    }
   ]
  },
  {
   "slug": "alibaba/ppio-qwen-qwen3-32b-fp8",
   "model_name": "ppio-qwen-qwen3-32b-fp8",
   "display_name": "qwen/qwen3-32b-fp8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2025-06-10",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen3-32b-fp8"
    }
   ]
  },
  {
   "slug": "alibaba/ppio-qwen-qwen3-coder-480b-a35b-instruct",
   "model_name": "ppio-qwen-qwen3-coder-480b-a35b-instruct",
   "display_name": "qwen/qwen3-coder-480b-a35b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.14"
      }
     }
    }
   ],
   "released_at": "2025-07-23",
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen3-coder-480b-a35b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/ppio-qwen-qwen3-coder-next",
   "model_name": "ppio-qwen-qwen3-coder-next",
   "display_name": "qwen/qwen3-coder-next",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "released_at": "2026-02-04",
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen3-coder-next"
    }
   ]
  },
  {
   "slug": "alibaba/ppio-qwen-qwen3-vl-8b-instruct",
   "model_name": "ppio-qwen-qwen3-vl-8b-instruct",
   "display_name": "qwen/qwen3-vl-8b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 131027,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen3-vl-8b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/ppio-qwen3-vl-235b-a22b-instruct",
   "model_name": "ppio-qwen3-vl-235b-a22b-instruct",
   "display_name": "qwen/qwen3-vl-235b-a22b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.143"
      }
     }
    }
   ],
   "released_at": "2025-09-30",
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen3-vl-235b-a22b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/ppio-qwen3-vl-235b-a22b-thinking",
   "model_name": "ppio-qwen3-vl-235b-a22b-thinking",
   "display_name": "qwen/qwen3-vl-235b-a22b-thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.86"
      }
     }
    }
   ],
   "released_at": "2025-09-30",
   "max_input_tokens": 98304,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen3-vl-235b-a22b-thinking"
    }
   ]
  },
  {
   "slug": "alibaba/QVQ-72B-Preview",
   "model_name": "QVQ-72B-Preview",
   "display_name": "QVQ 72B Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.294118"
      }
     },
     "provider_model_id": "qvq-72b-preview"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.143"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Qwen/QVQ-72B-Preview"
    }
   ],
   "released_at": "2024-12-25",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "reasoning": true,
    "vision": true,
    "image_output": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/QVQ-72B-Preview",
    "qvq-72b-preview"
   ],
   "intro_i18n": {
    "zh-CN": "QVQ-72B-Preview 是 Qwen 推出的实验性研究模型，专注于提升视觉推理能力。",
    "zh-TW": "QVQ-72B-Preview 是 Qwen 推出的實驗性研究模型，專注於提升視覺推理能力。",
    "ja-JP": "QVQ-72B-Previewは、視覚的推論の向上を目的としたQwenの実験的研究モデルです。",
    "ru-RU": "QVQ-72B-Preview — это экспериментальная исследовательская модель от Qwen, направленная на улучшение визуального рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "QVQ 72B Preview"
    }
   ]
  },
  {
   "slug": "alibaba/qvq-max",
   "model_name": "qvq-max",
   "display_name": "QVQ Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.8"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.58"
      }
     },
     "provider_model_id": "qvq-max-2025-03-25"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.147"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.588"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.3"
      }
     }
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-03-25",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qvq",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qvq-max-2025-03-25",
    "qvq-max-2025-05-15"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen QVQ 视觉推理模型支持视觉输入与链式思维输出，在数学、编程、视觉分析、创意及通用任务中表现出色。",
    "zh-TW": "Qwen QVQ 視覺推理模型支援視覺輸入與思維鏈式輸出，在數學、程式碼、視覺分析、創意與通用任務中表現更強。",
    "ja-JP": "Qwen QVQ視覚推論モデルは、視覚入力と連想的思考出力に対応し、数学、コーディング、視覚分析、創造的タスク、一般タスクにおいて高い性能を発揮します。",
    "ru-RU": "Модель визуального рассуждения Qwen QVQ поддерживает ввод изображений и вывод в виде цепочки рассуждений, демонстрируя высокую производительность в математике, программировании, визуальном анализе, творческих и общих задачах."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qvq-max-latest",
   "model_name": "qvq-max-latest",
   "display_name": "qvq-max-latest",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.58"
      }
     }
    }
   ],
   "released_at": "2025-12-30",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qvq-max-latest"
    }
   ]
  },
  {
   "slug": "alibaba/qvq-plus",
   "model_name": "qvq-plus",
   "display_name": "QVQ Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "qvq-plus-2025-05-15"
    }
   ],
   "released_at": "2025-05-15",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "reasoning": true,
    "vision": true,
    "image_output": true,
    "video_input": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qvq-plus-2025-05-15"
   ],
   "intro_i18n": {
    "zh-CN": "视觉推理模型，支持视觉输入与链式思维输出。qvq-plus 系列延续 qvq-max，推理更快，质量与成本更优平衡。",
    "zh-TW": "具備視覺輸入與思維鏈式輸出的視覺推理模型。qvq-plus 系列延續 qvq-max，提供更快速的推理能力與更佳的品質成本平衡。",
    "ja-JP": "視覚入力と連想的思考出力に対応する視覚推論モデル。qvq-plusシリーズはqvq-maxの後継で、より高速な推論と優れたコストパフォーマンスを実現します。",
    "ru-RU": "Модель визуального рассуждения с вводом изображений и выводом в виде цепочки рассуждений. Серия qvq-plus следует за qvq-max и обеспечивает более быстрое рассуждение с лучшим соотношением качества и стоимости."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "QVQ Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qvq-plus-latest",
   "model_name": "qvq-plus-latest",
   "display_name": "qvq-plus-latest",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     }
    }
   ],
   "released_at": "2025-12-30",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qvq-plus-latest"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2-1.5b-instruct",
   "model_name": "qwen-2-1.5b-instruct",
   "display_name": "Arize AI Qwen 2 1.5B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "arize-ai/qwen-2-1.5b-instruct"
    }
   ],
   "released_at": "2025-04-24",
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "arize-ai/qwen-2-1.5b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Arize AI Qwen 2 1.5B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2-5-14b",
   "model_name": "qwen-2-5-14b",
   "display_name": "Qwen 2.5 14B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "family": "Qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 14B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2-5-72b",
   "model_name": "qwen-2-5-72b",
   "display_name": "Qwen 2.5 72B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "knowledge_cutoff": "2024-03",
   "max_input_tokens": 128000,
   "family": "Qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 72B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2-5-7b",
   "model_name": "qwen-2-5-7b",
   "display_name": "Qwen 2.5 7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "family": "Qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 7B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2-5-coder-32b",
   "model_name": "qwen-2-5-coder-32b",
   "display_name": "Qwen 2.5 Coder 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.79"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "provider_model_id": "qwen-2.5-coder-32b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2024-11-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-03",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen-2.5-coder-32b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 Coder 32B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2-5-vl-72b",
   "model_name": "qwen-2-5-vl-72b",
   "display_name": "Qwen 2.5 VL 72B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "family": "Qwen",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 VL 72B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2-72b-instruct",
   "model_name": "qwen-2-72b-instruct",
   "display_name": "qwen-2-72b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "qwen/qwen-2-72b-instruct"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen-2-72b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen-2-72b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2-7b-instruct",
   "model_name": "qwen-2-7b-instruct",
   "display_name": "qwen/qwen-2-7b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.054"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.054"
      }
     },
     "provider_model_id": "qwen/qwen-2-7b-instruct"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.047059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.047059"
      }
     },
     "provider_model_id": "qwen/qwen-2-7b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2024-09-18",
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen-2-7b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2 是全新的 Qwen 大语言模型系列。Qwen2 7B 是一款基于 Transformer 架构的模型，擅长语言理解、多语言处理、编程、数学和推理。",
    "zh-TW": "Qwen2 是全新 Qwen LLM 系列。Qwen2 7B 是一款基於 Transformer 的模型，擅長語言理解、多語言處理、程式設計、數學與推理。",
    "ja-JP": "Qwen2は新しいQwen LLMシリーズです。Qwen2 7Bは、言語理解、多言語対応、プログラミング、数学、推論に優れたトランスフォーマーベースのモデルです。",
    "ru-RU": "Qwen2 — это новая серия языковых моделей Qwen. Qwen2 7B — это модель на основе трансформеров, превосходно справляющаяся с пониманием языка, многоязычностью, программированием, математикой и рассуждением."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen-2-7b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2-vl-72b-instruct",
   "model_name": "qwen-2-vl-72b-instruct",
   "display_name": "qwen/qwen-2-vl-72b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwen/qwen-2-vl-72b-instruct"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.661765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.661765"
      }
     },
     "provider_model_id": "qwen/qwen-2-vl-72b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "released_at": "2024-12-19",
   "max_output_tokens": 120000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen-2-vl-72b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2-VL 是 Qwen-VL 的最新版本，在 MathVista、DocVQA、RealWorldQA 和 MTVQA 等视觉基准测试中达到业界领先水平。支持 20 分钟以上视频的高质量问答、对话和内容创作，具备复杂推理与决策能力，可与移动设备和机器人集成，根据视觉上下文和文本指令执行操作。除中英文外，还支持图像中的多种语言文本识别，包括大多数欧洲语言、日语、韩语、阿拉伯语和越南语。",
    "zh-TW": "Qwen2-VL 是 Qwen-VL 的最新版本，在 MathVista、DocVQA、RealWorldQA、MTVQA 等視覺基準上達到 SOTA 表現。可理解超過 20 分鐘影片，進行高品質問答、對話與內容創作。支援複雜推理與決策，能與行動裝置與機器人整合，根據視覺上下文與文字指令執行操作。除中英文外，也能辨識多種語言的圖像文字，包括多數歐洲語言、日文、韓文、阿拉伯文與越南文。",
    "ja-JP": "Qwen2-VLは、Qwen-VLの最新バージョンで、MathVista、DocVQA、RealWorldQA、MTVQAなどの視覚ベンチマークで最先端の性能を達成しています。20分以上の動画を理解し、高品質な動画QA、対話、コンテンツ生成が可能です。複雑な推論や意思決定にも対応し、モバイルデバイスやロボットと連携して視覚コンテキストとテキスト指示に基づく行動が可能です。英語と中国語に加え、画像内の多言語テキスト（欧州言語、日本語、韓国語、アラビア語、ベトナム語など）も読み取れます。",
    "ru-RU": "Qwen2-VL — последняя итерация Qwen-VL, достигшая передовых результатов на визуальных бенчмарках, таких как MathVista, DocVQA, RealWorldQA и MTVQA. Понимает видео продолжительностью более 20 минут для качественного видео Q&A, диалогов и создания контента. Также справляется со сложным рассуждением и принятием решений, интегрируется с мобильными устройствами и роботами для действий на основе визуального контекста и текстовых инструкций. Помимо английского и китайского, распознаёт текст на изображениях на многих языках, включая большинство европейских, японский, корейский, арабский и вьетнамский."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen/qwen-2-vl-72b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2.5-14b-instruct",
   "model_name": "qwen-2.5-14b-instruct",
   "display_name": "Qwen 2.5 14B Instruct",
   "vendor": "alibaba",
   "pricing": [],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2024-09-19",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 14B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2.5-7b-instruct",
   "model_name": "qwen-2.5-7b-instruct",
   "display_name": "Qwen: Qwen2.5 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen/qwen-2.5-7b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen/qwen-2.5-7b-instruct"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2024-09",
   "max_input_tokens": 32768,
   "max_output_tokens": 6554,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-06",
   "family": "qwen",
   "deprecated": true,
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen-2.5-7b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen: Qwen2.5 7B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2.5-7b-vision-instruct",
   "model_name": "qwen-2.5-7b-vision-instruct",
   "display_name": "Qwen 2.5 7B Vision Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "inference",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen/qwen-2.5-7b-vision-instruct"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 125000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen-2.5-7b-vision-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 7B Vision Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2.5-coder-32b-instruct:free",
   "model_name": "qwen-2.5-coder-32b-instruct:free",
   "display_name": "Qwen2.5 Coder 32B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "qwen/qwen-2.5-coder-32b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "qwen/qwen-2.5-coder-32b-instruct"
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2024-11-11",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2024-06",
   "family": "qwen",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen-2.5-coder-32b-instruct",
    "qwen/qwen-2.5-coder-32b-instruct",
    "qwen/qwen-2.5-coder-32b-instruct:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 Coder 32B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2.5-vl-72b-instruct",
   "model_name": "qwen-2.5-vl-72b-instruct",
   "display_name": "qwen-2.5-vl-72b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen/qwen-2.5-vl-72b-instruct"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen-2.5-vl-72b-instruct"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen-2.5-vl-72b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-2.5-vl-7b-instruct",
   "model_name": "qwen-2.5-vl-7b-instruct",
   "display_name": "Qwen: Qwen2.5-VL 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen/qwen-2.5-vl-7b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen/qwen-2.5-vl-7b-instruct"
    }
   ],
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "released_at": "2024-08-28",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen-2.5-vl-7b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen: Qwen2.5-VL 7B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-14b",
   "model_name": "qwen-3-14b",
   "display_name": "Qwen3-14B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "alibaba/qwen-3-14b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "alibaba/qwen-3-14b"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-28",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 40960,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen-3-14b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 是 Qwen 系列的最新一代，提供全面的稠密与 MoE 模型组合。基于大规模训练，在推理、指令遵循、智能体能力和多语言支持方面实现突破。",
    "zh-TW": "Qwen3 是 Qwen 系列的最新一代，提供完整的密集與 MoE 模型組合。透過大規模訓練，在推理、指令遵循、代理能力與多語言支援方面實現突破。",
    "ja-JP": "Qwen3はQwenシリーズの最新世代で、密なモデルとMoEモデルの包括的なセットを提供します。広範なトレーニングに基づき、推論、命令追従、エージェント機能、多言語対応において大きな進歩を遂げています。",
    "ru-RU": "Qwen3 — это новейшее поколение в серии Qwen, предлагающее широкий набор плотных и MoE-моделей. Обученная на обширных данных, модель демонстрирует прорывные результаты в логике, следовании инструкциям, агентных возможностях и многоязычной поддержке."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-14B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-235b",
   "model_name": "qwen-3-235b",
   "display_name": "Qwen3 235B A22B Instruct 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1495"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.495"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8693"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.608"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "alibaba/qwen-3-235b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "alibaba/qwen-3-235b"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-28",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen-3-235b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 是 Qwen 系列的最新一代，提供全面的稠密与 MoE 模型组合。基于大规模训练，在推理、指令遵循、智能体能力和多语言支持方面实现突破。",
    "zh-TW": "Qwen3 是 Qwen 系列的最新一代，提供完整的密集與 MoE 模型組合。透過大規模訓練，在推理、指令遵循、代理能力與多語言支援方面實現突破。",
    "ja-JP": "Qwen3はQwenシリーズの最新世代で、密なモデルとMoEモデルの包括的なセットを提供します。広範なトレーニングに基づき、推論、命令追従、エージェント機能、多言語対応において大きな進歩を遂げています。",
    "ru-RU": "Qwen3 — это новейшее поколение в серии Qwen, предлагающее широкий набор плотных и MoE-моделей. Обученная на обширных данных, модель демонстрирует прорывные результаты в логике, следовании инструкциям, агентных возможностях и многоязычной поддержке."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "2.3",
     "new": "0.1"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.23",
     "new": "0.09"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.1",
     "new": "2.3"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.09",
     "new": "0.23"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "2.3",
     "new": "0.1"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.23",
     "new": "0.09"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 235B A22B Instruct 2507"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-235b-a22b-instruct-2507",
   "model_name": "qwen-3-235b-a22b-instruct-2507",
   "display_name": "Qwen 3 235B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    },
    {
     "provider": "cerebras",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "max_input_tokens": 131000,
   "max_output_tokens": 40000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "released_at": "2025-07-22",
   "knowledge_cutoff": "2025-04",
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3 235B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-235b-a22b-thinking-2507",
   "model_name": "qwen-3-235b-a22b-thinking-2507",
   "display_name": "qwen-3-235b-a22b-thinking-2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen-3-235b-a22b-thinking-2507"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-30b",
   "model_name": "qwen-3-30b",
   "display_name": "Qwen3-30B-A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "alibaba/qwen-3-30b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "alibaba/qwen-3-30b"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-28",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 40960,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen-3-30b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 是 Qwen 系列的最新一代，提供全面的稠密与 MoE 模型组合。基于大规模训练，在推理、指令遵循、智能体能力和多语言支持方面实现突破。",
    "zh-TW": "Qwen3 是 Qwen 系列的最新一代，提供完整的密集與 MoE 模型組合。透過大規模訓練，在推理、指令遵循、代理能力與多語言支援方面實現突破。",
    "ja-JP": "Qwen3はQwenシリーズの最新世代で、密なモデルとMoEモデルの包括的なセットを提供します。広範なトレーニングに基づき、推論、命令追従、エージェント機能、多言語対応において大きな進歩を遂げています。",
    "ru-RU": "Qwen3 — это новейшее поколение в серии Qwen, предлагающее широкий набор плотных и MoE-моделей. Обученная на обширных данных, модель демонстрирует прорывные результаты в логике, следовании инструкциям, агентных возможностях и многоязычной поддержке."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-30B-A3B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-32b",
   "model_name": "qwen-3-32b",
   "display_name": "Qwen 3.32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     }
    },
    {
     "provider": "cerebras",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.64"
      }
     },
     "provider_model_id": "alibaba/qwen-3-32b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "alibaba/qwen-3-32b"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-28",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "reasoning_config": {
    "budget_min": 1
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true
   },
   "docs_url": "https://inference-docs.cerebras.ai/support/pricing",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen-3-32b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 是 Qwen 系列的最新一代，提供全面的稠密与 MoE 模型组合。基于大规模训练，在推理、指令遵循、智能体能力和多语言支持方面实现突破。",
    "zh-TW": "Qwen3 是 Qwen 系列的最新一代，提供完整的密集與 MoE 模型組合。透過大規模訓練，在推理、指令遵循、代理能力與多語言支援方面實現突破。",
    "ja-JP": "Qwen3はQwenシリーズの最新世代で、密なモデルとMoEモデルの包括的なセットを提供します。広範なトレーニングに基づき、推論、命令追従、エージェント機能、多言語対応において大きな進歩を遂げています。",
    "ru-RU": "Qwen3 — это новейшее поколение в серии Qwen, предлагающее широкий набор плотных и MoE-моделей. Обученная на обширных данных, модель демонстрирует прорывные результаты в логике, следовании инструкциям, агентных возможностях и многоязычной поддержке."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.32B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-5-397b",
   "model_name": "qwen-3-5-397b",
   "display_name": "Qwen 3.5 397B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.385"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.45"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6955"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.1728"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "family": "Qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.5 397B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-6-27b",
   "model_name": "qwen-3-6-27b",
   "display_name": "Qwen 3.6 27B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.403"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.09"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2015"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.285"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "family": "Qwen 3.6",
   "capabilities": {
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.1984",
     "new": "0.2015"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "3.03",
     "new": "3.09"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.3968",
     "new": "0.403"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.1995",
     "new": "0.1984"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "3.19",
     "new": "3.03"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.399",
     "new": "0.3968"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.1845",
     "new": "0.1995"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.95",
     "new": "3.19"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.369",
     "new": "0.399"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.1854",
     "new": "0.1845"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "3.03",
     "new": "2.95"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.3708",
     "new": "0.369"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.1984",
     "new": "0.1854"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.3968",
     "new": "0.3708"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.6 27B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-6-plus",
   "model_name": "qwen-3-6-plus",
   "display_name": "Qwen3.6 Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen-3.6-plus",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.7"
      }
     },
     "provider_model_id": "qwen-3.6-plus"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.325"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.95"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0625"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
   "released_at": "2026-04-02",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen-3.6-plus"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-7-max",
   "model_name": "qwen-3-7-max",
   "display_name": "Qwen 3.7 Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.05"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.35"
      }
     }
    }
   ],
   "intro": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
   "released_at": "2026-05-22",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.7 Max"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-7-plus",
   "model_name": "qwen-3-7-plus",
   "display_name": "Qwen 3.7 Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3",
        "completion": "3",
        "cache_read": "3",
        "cache_write": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3",
        "completion": "3",
        "cache_read": "3",
        "cache_write": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
   "released_at": "2026-06-02",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.7 Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-coder-30b",
   "model_name": "qwen-3-coder-30b",
   "display_name": "Qwen 3 Coder 30B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9146"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "family": "Qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "0.9132",
     "new": "0.9146"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "0.2283",
     "new": "0.2287"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "0.9158",
     "new": "0.9132"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "0.229",
     "new": "0.2283"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3 Coder 30B"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "0.9106",
     "new": "0.9158"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "0.2277",
     "new": "0.229"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3-vl-32b",
   "model_name": "qwen-3-vl-32b",
   "display_name": "Qwen 3 VL 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.455"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "family": "Qwen",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3 VL 32B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-3.6-max-preview",
   "model_name": "qwen-3.6-max-preview",
   "display_name": "Qwen 3.6 Max Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.625"
      }
     },
     "provider_model_id": "alibaba/qwen-3.6-max-preview",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.538462",
        "completion": "1.538462",
        "cache_read": "0.769231",
        "cache_write": "1.538462"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
   "released_at": "2026-04-20",
   "max_input_tokens": 240000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "reasoning_config": {
    "budget_min": 1
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen-3.6-max-preview"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.6 Max Preview"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-coder",
   "model_name": "qwen-coder",
   "display_name": "qwen-coder",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models",
   "max_input_tokens": 1000000,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "alibaba/qwen-coder-plus",
   "model_name": "qwen-coder-plus",
   "display_name": "Qwen Coder Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.514706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "qwen-coder-plus-2024-11-06"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.502"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.004"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true
   },
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2024-09-18",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen-coder-plus-2024-11-06"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen 编程模型。",
    "zh-TW": "Qwen 程式碼模型。",
    "ja-JP": "Qwenコードモデル。",
    "ru-RU": "Модель программирования Qwen."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Coder Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-coder-plus-latest",
   "model_name": "qwen-coder-plus-latest",
   "display_name": "qwen-coder-plus-latest",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "released_at": "2025-12-30",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen-coder-plus-latest"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-coder-turbo",
   "model_name": "qwen-coder-turbo",
   "display_name": "Qwen Coder Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     },
     "provider_model_id": "qwen-coder-turbo-2024-09-19"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "released_at": "2025-12-30",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen-coder-turbo-2024-09-19"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen 编程模型。",
    "zh-TW": "Qwen 程式碼模型。",
    "ja-JP": "Qwenコードモデル。",
    "ru-RU": "Модель программирования Qwen."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Coder Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-coder-turbo-latest",
   "model_name": "qwen-coder-turbo-latest",
   "display_name": "Qwen Coder Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "released_at": "2025-12-30",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen 编程模型。",
    "zh-TW": "Qwen 程式碼模型。",
    "ja-JP": "Qwenコードモデル。",
    "ru-RU": "Модель программирования Qwen."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Coder Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-deep-research",
   "model_name": "qwen-deep-research",
   "display_name": "Qwen Deep Research",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.742"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "23.367"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.742"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "23.367"
      }
     }
    }
   ],
   "released_at": "2024-01",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Deep Research"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-doc-turbo",
   "model_name": "qwen-doc-turbo",
   "display_name": "Qwen Doc Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.087"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.144"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.086"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.143"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.087"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.144"
      }
     }
    }
   ],
   "released_at": "2024-01",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "intro": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Doc Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-flash",
   "model_name": "qwen-flash",
   "display_name": "Qwen Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.004412"
      }
     },
     "tracks": [
      {
       "label": ">256000000K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "24",
        "completion": "30",
        "cache_read": "8"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">128000000K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "12",
        "completion": "15",
        "cache_read": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.022"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "qwen-flash-2025-07-28"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen-flash-2025-07-28"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.022"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.216"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.002"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "qwen-flash-2025-07-28"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0625"
      }
     }
    }
   ],
   "intro": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
   "released_at": "2025-07-28",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "web_search": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen-flash-2025-07-28"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen Flash 是最快、成本最低的模型，适合处理简单任务。",
    "zh-TW": "Qwen 最快且成本最低的模型，適用於簡單任務。",
    "ja-JP": "Qwenモデルの中で最速かつ最も低コスト。シンプルなタスクに最適です。",
    "ru-RU": "Самая быстрая и недорогая модель Qwen, идеально подходит для простых задач."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-flash-2025-07-28-us",
   "model_name": "qwen-flash-2025-07-28-us",
   "display_name": "Qwen-Flash-2025-07-28-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-08-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen-Flash-2025-07-28-US"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-flash-us",
   "model_name": "qwen-flash-us",
   "display_name": "Qwen-Flash-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    }
   ],
   "released_at": "2025-08-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen-Flash-US"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen-Image",
   "model_name": "Qwen-Image",
   "display_name": "Qwen Image",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.036765"
      }
     },
     "provider_model_id": "qwen-image"
    },
    {
     "provider": "fal",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output_per_megapixel": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "provider_model_id": "fal-ai/qwen-image"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen-image"
    },
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "qwen-image"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.005882"
      }
     },
     "provider_model_id": "Qwen/Qwen-Image"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0058"
      }
     },
     "provider_model_id": "Qwen/Qwen-Image"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.036765"
      }
     },
     "provider_model_id": "qwen-image"
    }
   ],
   "released_at": "2025-08-13",
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true,
    "pdf_input": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen-Image",
    "fal-ai/qwen-image",
    "qwen-image",
    "qwen/qwen-image"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen-Image 是 Qwen 团队推出的 200 亿参数图像生成基础模型，在复杂文本渲染和精确图像编辑方面取得重大突破，尤其擅长高保真中英文文本渲染。支持多行及段落排版，保持排版一致性。除文本渲染外，还支持从写实风格到动漫风格的多种图像风格，以及风格迁移、对象添加/删除、细节增强、文本编辑和姿态控制等高级编辑功能，致力于打造全面的视觉创作基础模型。",
    "zh-TW": "Qwen-Image 是 Qwen 團隊推出的 20B 參數圖像生成基礎模型，在複雜文字渲染與精準圖像編輯方面取得重大突破，特別擅長中英文高保真文字處理。支援多行與段落排版，保持排版一致性。除文字渲染外，還支援從寫實風格到動漫風格的多樣圖像風格，以及進階編輯功能，如風格轉換、物件新增/刪除、細節增強、文字編輯與姿勢控制，致力於成為全面的視覺創作基礎模型。",
    "ja-JP": "Qwen-Image は、Qwen チームによる 20B パラメータの画像生成基盤モデルです。複雑なテキスト描画や精密な画像編集において大きな進歩を遂げており、特に中国語／英語の高忠実度テキストに強みを持ちます。複数行や段落レイアウトをサポートし、タイポグラフィの一貫性を保ちます。テキスト描画にとどまらず、写実的スタイルからアニメ風まで幅広いスタイルに対応し、スタイル変換、オブジェクトの追加／削除、ディテール強調、テキスト編集、ポーズ制御などの高度な編集も可能で、包括的なビジュアル創作基盤を目指しています。",
    "ru-RU": "Qwen-Image — базовая модель генерации изображений с 20 млрд параметров от команды Qwen. Обеспечивает значительный прогресс в сложной визуализации текста и точном редактировании изображений, особенно для китайского и английского языков. Поддерживает многострочные и абзацные макеты с сохранением типографики. Помимо визуализации текста, поддерживает широкий спектр стилей — от фотореализма до аниме, а также продвинутые функции редактирования: перенос стиля, добавление/удаление объектов, улучшение деталей, редактирование текста и управление позой. Стремится стать универсальной основой для визуального творчества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Image"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen-Image-2.0",
   "model_name": "Qwen-Image-2.0",
   "display_name": "Qwen Image 2.0",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     },
     "provider_model_id": "qwen-image-2.0"
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen-image-2.0"
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen-image-2.0"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Qwen/Qwen-Image-2.0"
    }
   ],
   "released_at": "2026-03-03",
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 8192,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen-Image-2.0",
    "qwen-image-2.0"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen-Image-2.0 系列加速版模型将图像生成和图像编辑整合为一体。它支持更专业的文本渲染，指令容量高达 1k token，提供更精细和逼真的视觉纹理，能够对真实场景进行细致入微的描绘，并展现出与提示更强的语义契合度。加速版在模型质量和性能之间实现了最佳平衡。",
    "zh-TW": "Qwen-Image-2.0 系列加速版模型將圖像生成與圖像編輯整合為一體。它支持更專業的文本渲染，指令容量高達 1k 字元，提供更精緻且逼真的視覺紋理，實現對真實場景的細緻描繪，並展現出與提示語更強的語義貼合性。加速版有效實現了模型質量與性能的最佳平衡。",
    "ja-JP": "Qwen-Image-2.0シリーズの高速版モデルは、画像生成と画像編集を統合した機能を備えています。最大1kトークンの指示容量で、より専門的なテキストレンダリングをサポートし、洗練されたリアルな視覚テクスチャを提供します。現実的なシーンの詳細な描写を可能にし、プロンプトとの意味的な整合性を強化します。この高速版モデルは、モデルの品質とパフォーマンスの最適なバランスを効果的に実現します。",
    "ru-RU": "Ускоренная версия модели серии Qwen-Image-2.0 объединяет генерацию изображений и их редактирование в единую функцию. Она поддерживает более профессиональную обработку текста с емкостью до 1k токенов, обеспечивает более утонченные и реалистичные визуальные текстуры, позволяет точно описывать реалистичные сцены и демонстрирует более сильное семантическое соответствие запросам. Ускоренная версия эффективно достигает оптимального баланса между качеством модели и производительностью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Image 2.0"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-image-2.0-pro-2026-04-22",
   "model_name": "qwen-image-2.0-pro-2026-04-22",
   "display_name": "Qwen Image 2.0 Pro",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.073529"
      }
     },
     "provider_model_id": "qwen-image-2.0-pro"
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen-image-2.0-pro"
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen-image-2.0-pro"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.08"
      }
     },
     "provider_model_id": "Qwen/Qwen-Image-2.0-Pro"
    }
   ],
   "released_at": "2026-03-03",
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 8192,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen-Image-2.0-Pro",
    "qwen-image-2.0-pro"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen-Image-2.0 系列完整版模型将图像生成与图像编辑能力融合一体。支持更专业的文字渲染，指令容量达 1k tokens；在视觉真实感、细节刻画与语义对齐方面整体大幅增强。完整版在 2.0 系列中提供最强文字呈现与最高真实度。",
    "zh-TW": "Qwen-Image-2.0 系列完整版將影像生成與影像編輯整合於同一模型，支援更專業的文字呈現（最高可處理 1000 token 指令），提供更細膩真實的視覺質感、精準寫實場景刻畫，並展現與提示詞更強的語意對齊能力。完整版提供 2.0 系列中最強的文字呈現能力及最高的寫實度。",
    "ja-JP": "Qwen-Image-2.0シリーズのフルバージョンモデルは、画像生成と画像編集を統合した能力を備えています。最大1kトークンの指示容量で、よりプロフェッショナルなテキストレンダリングをサポートし、より繊細でリアルな視覚テクスチャを提供します。リアルなシーンの細かい描写を可能にし、プロンプトとのセマンティックな整合性を強化します。フルバージョンモデルは、2.0シリーズ内で最も強力なテキストレンダリング能力と最高レベルのリアリズムを提供します。",
    "ru-RU": "Полноценная модель серии Qwen-Image-2.0 объединяет генерацию и редактирование изображений в единой системе. Поддерживает улучшенный рендеринг текста (до 1k токенов), создаёт более реалистичные и детализированные текстуры, обеспечивает точную передачу сцен и более сильное семантическое соответствие подсказкам. Полная версия модели обладает наилучшими возможностями рендеринга текста и реалистичностью в серии 2.0."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Image 2.0 Pro"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen-Image-Edit",
   "model_name": "Qwen-Image-Edit",
   "display_name": "Qwen Image Edit",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.044118"
      }
     },
     "provider_model_id": "qwen-image-edit"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.025"
      }
     },
     "provider_model_id": "Qwen/Qwen-Image-Edit"
    },
    {
     "provider": "fal",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output_per_megapixel": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "fal-ai/qwen-image-edit"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen-image-edit"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.044118"
      }
     },
     "provider_model_id": "qwen-image-edit"
    }
   ],
   "released_at": "2025-09-18",
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true,
    "pdf_input": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen-Image-Edit",
    "fal-ai/qwen-image-edit",
    "qwen-image-edit",
    "qwen/qwen-image-edit"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen 团队推出的专业图像编辑模型，支持语义和外观编辑，能够精准编辑中英文文本，并实现高质量的编辑效果，如风格迁移和物体旋转。",
    "zh-TW": "Qwen 團隊推出的專業圖像編輯模型，支持語義和外觀編輯，精確編輯中英文文本，並能進行高品質的編輯，例如風格轉換和物體旋轉。",
    "ja-JP": "Qwenチームが提供するプロフェッショナルな画像編集モデルで、意味的および外観的な編集をサポートし、中国語と英語のテキストを正確に編集します。スタイル変換やオブジェクトの回転など、高品質な編集が可能です。",
    "ru-RU": "Профессиональная модель редактирования изображений от команды Qwen, поддерживающая семантические и визуальные правки, точное редактирование текста на китайском и английском языках, а также высококачественные правки, такие как перенос стиля и вращение объектов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Image Edit"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen-Image-Edit-2509",
   "model_name": "Qwen-Image-Edit-2509",
   "display_name": "Qwen-Image-Edit (2509)",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.005882"
      }
     },
     "provider_model_id": "Qwen/Qwen-Image-Edit-2509"
    }
   ],
   "released_at": "2025-09-22",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen-Image-Edit-2509"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen-Image-Edit-2509 是 Qwen 团队推出的最新图像编辑版本，基于 200 亿参数的 Qwen-Image 模型构建，将强大的文本渲染能力扩展至图像编辑，实现精确的文本修改。该模型采用双重控制架构，输入分别传递至 Qwen2.5-VL 进行语义控制和 VAE 编码器进行外观控制，从而实现语义层与外观层的编辑。支持局部编辑（添加/删除/修改）及更高层次的语义编辑，如 IP 创作与风格迁移，同时保持语义一致性，在多个基准测试中取得 SOTA 表现。",
    "zh-TW": "Qwen-Image-Edit-2509 是 Qwen 團隊推出的最新圖像編輯版本。基於 20B 參數的 Qwen-Image 模型，該版本將強大的文字渲染能力擴展至圖像編輯，實現精準的文字修改。其採用雙重控制架構，將輸入分別送至 Qwen2.5-VL 進行語義控制，以及 VAE 編碼器進行外觀控制，實現語義與外觀層級的編輯。支援局部編輯（新增/刪除/修改）與高階語義編輯，如 IP 創作與風格轉換，同時保留語義一致性。該模型在多項基準測試中達到 SOTA 表現。",
    "ja-JP": "Qwen-Image-Edit-2509 は、Qwen チームによる Qwen-Image の最新編集バージョンです。20B パラメータの Qwen-Image モデルを基盤とし、強力なテキスト描画能力を画像編集に拡張し、精密なテキスト編集を可能にします。Qwen2.5-VL によるセマンティック制御と VAE エンコーダによる外観制御を組み合わせたデュアル制御アーキテクチャを採用し、意味レベルおよび外観レベルの編集を実現します。ローカル編集（追加／削除／修正）や、IP 作成やスタイル変換といった高次の意味編集にも対応し、意味を保持しながら編集が可能です。複数のベンチマークで SOTA（最先端）性能を達成しています。",
    "ru-RU": "Qwen-Image-Edit-2509 — последняя версия редактора изображений от команды Qwen. Основана на модели Qwen-Image с 20 млрд параметров и расширяет возможности точного редактирования текста в изображениях. Использует архитектуру двойного управления: Qwen2.5-VL для семантического контроля и VAE-энкодер для управления внешним видом, что позволяет редактировать как на уровне смысла, так и визуального оформления. Поддерживает локальные изменения (добавление/удаление/модификация) и высокоуровневые семантические правки, такие как создание IP и перенос стиля, сохраняя при этом смысл. Достигает SOTA-результатов на множестве тестов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen-Image-Edit (2509)"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen-Image-Edit-Max",
   "model_name": "Qwen-Image-Edit-Max",
   "display_name": "Qwen Image Edit Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.073529"
      }
     },
     "provider_model_id": "qwen-image-edit-max"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.075"
      }
     },
     "provider_model_id": "Qwen/Qwen-Image-Edit-Max"
    }
   ],
   "released_at": "2026-01-17",
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen-Image-Edit-Max",
    "qwen-image-edit-max"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen图像编辑模型支持多图输入和多图输出，能够精确进行图像内文字编辑、对象添加、移除或重新定位、主体动作修改、图像风格转换以及视觉细节增强。",
    "zh-TW": "Qwen 圖像編輯模型支持多圖輸入和多圖輸出，實現精確的圖像內文本編輯、物體添加、移除或重新定位、主體動作修改、圖像風格轉換以及增強視覺細節。",
    "ja-JP": "Qwen画像編集モデルは、複数画像の入力と出力をサポートし、画像内のテキスト編集、オブジェクトの追加、削除、移動、被写体のアクション変更、画像スタイルの転送、視覚的な詳細の強化を可能にします。",
    "ru-RU": "Модель редактирования изображений Qwen поддерживает ввод и вывод нескольких изображений, позволяя точно редактировать текст в изображениях, добавлять, удалять или перемещать объекты, изменять действия субъектов, переносить стили изображений и улучшать визуальные детали."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Image Edit Max"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-image-edit-plus",
   "model_name": "qwen-image-edit-plus",
   "display_name": "Qwen Image Edit Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     }
    }
   ],
   "released_at": "2025-12-23",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen图像编辑模型支持多图输入和多图输出，能够精确进行图像内文字编辑、对象添加、移除或重新定位、主体动作修改、图像风格转换以及视觉细节增强。",
    "zh-TW": "Qwen 圖像編輯模型支持多圖輸入和多圖輸出，實現精確的圖像內文本編輯、物體添加、移除或重新定位、主體動作修改、圖像風格轉換以及增強視覺細節。",
    "ja-JP": "Qwen画像編集モデルは、複数画像の入力と出力をサポートし、画像内のテキスト編集、オブジェクトの追加、削除、移動、被写体のアクション変更、画像スタイルの転送、視覚的な詳細の強化を可能にします。",
    "ru-RU": "Модель редактирования изображений Qwen поддерживает ввод и вывод нескольких изображений, позволяя точно редактировать текст в изображениях, добавлять, удалять или перемещать объекты, изменять действия субъектов, переносить стили изображений и улучшать визуальные детали."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Image Edit Plus"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen-Image-Max",
   "model_name": "Qwen-Image-Max",
   "display_name": "Qwen Image Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.073529"
      }
     },
     "provider_model_id": "qwen-image-max"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.075"
      }
     },
     "provider_model_id": "Qwen/Qwen-Image-Max"
    }
   ],
   "released_at": "2025-12-31",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen-Image-Max",
    "qwen-image-max"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen图像生成模型（Max系列）在视觉真实感和自然性方面相比Plus系列有显著提升，有效减少AI生成伪影，并在人物外观、纹理细节和文字渲染方面表现卓越。",
    "zh-TW": "Qwen 圖像生成模型（Max 系列）在真實感和視覺自然性方面相比 Plus 系列有顯著提升，有效減少 AI 生成的瑕疵，並在人物外觀、紋理細節和文本渲染方面表現出色。",
    "ja-JP": "Qwen画像生成モデル（Maxシリーズ）は、Plusシリーズと比較してリアリズムと視覚的自然さを強化し、AI生成アーティファクトを効果的に削減します。人間の外見、テクスチャの詳細、テキストレンダリングにおいて優れた性能を示します。",
    "ru-RU": "Модель генерации изображений Qwen (серия Max) обеспечивает улучшенный реализм и визуальную естественность по сравнению с серией Plus, эффективно снижая артефакты, создаваемые ИИ, и демонстрируя выдающиеся результаты в отображении внешности человека, текстурных деталей и рендеринге текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Image Max"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-image-plus",
   "model_name": "qwen-image-plus",
   "display_name": "Qwen Image Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     }
    }
   ],
   "released_at": "2026-01-12",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "支持广泛的艺术风格，特别擅长在图像中渲染复杂文字，能够实现图像与文字的集成布局设计。",
    "zh-TW": "支持多種藝術風格，特別擅長在圖像中渲染複雜文本，實現圖文一體化的佈局設計。",
    "ja-JP": "幅広い芸術的スタイルをサポートし、特に画像内の複雑なテキストのレンダリングに優れ、統合された画像とテキストのレイアウトデザインを可能にします。",
    "ru-RU": "Поддерживает широкий спектр художественных стилей и особенно хорошо справляется с рендерингом сложного текста в изображениях, позволяя интегрированное проектирование макета изображений и текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Image Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-long",
   "model_name": "qwen-long",
   "display_name": "Qwen Long",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     },
     "provider_model_id": "qwen-long-2025-01-25"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      }
     }
    }
   ],
   "released_at": "2025-01-25",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 10000000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "pdf_input": true
   },
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen-long-2025-01-25"
   ],
   "intro_i18n": {
    "zh-CN": "超大规模 Qwen 模型，支持长上下文与跨多文档场景的对话。",
    "zh-TW": "超大型 Qwen 模型，具備長上下文處理能力，適用於長篇與多文件對話場景。",
    "ja-JP": "超大規模なQwenモデルで、長文や複数文書にまたがるチャットに対応します。",
    "ru-RU": "Ультра-крупная модель Qwen с поддержкой длинного контекста и диалогов в рамках одного или нескольких документов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Long"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-long-latest",
   "model_name": "qwen-long-latest",
   "display_name": "qwen-long-latest",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    }
   ],
   "released_at": "2025-12-30",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen-long-latest"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-math-plus",
   "model_name": "qwen-math-plus",
   "display_name": "Qwen Math Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.721"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.72"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.721"
      }
     }
    }
   ],
   "released_at": "2024-08-16",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 4096,
   "max_output_tokens": 3072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen Math 是一款专注于数学问题求解的语言模型。",
    "zh-TW": "Qwen Math 是一款專門用於解決數學問題的語言模型。",
    "ja-JP": "Qwen Mathは、数学問題の解決に特化した言語モデルです。",
    "ru-RU": "Qwen Math — языковая модель, специализирующаяся на решении математических задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Math Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-math-plus-latest",
   "model_name": "qwen-math-plus-latest",
   "display_name": "Qwen Math Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen Math 是一款专注于数学问题求解的语言模型。",
    "zh-TW": "Qwen Math 是一款專門用於解決數學問題的語言模型。",
    "ja-JP": "Qwen Mathは、数学問題の解決に特化した言語モデルです。",
    "ru-RU": "Qwen Math — языковая модель, специализирующаяся на решении математических задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Math Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-math-turbo",
   "model_name": "qwen-math-turbo",
   "display_name": "Qwen Math Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     }
    }
   ],
   "released_at": "2024-09-19",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 4096,
   "max_output_tokens": 3072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "intro": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen Math 是一款专注于数学问题求解的语言模型。",
    "zh-TW": "Qwen Math 是一款專門用於解決數學問題的語言模型。",
    "ja-JP": "Qwen Mathは、数学問題の解決に特化した言語モデルです。",
    "ru-RU": "Qwen Math — языковая модель, специализирующаяся на решении математических задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Math Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-math-turbo-latest",
   "model_name": "qwen-math-turbo-latest",
   "display_name": "Qwen Math Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen Math 是一款专注于数学问题求解的语言模型。",
    "zh-TW": "Qwen Math 是一款專門用於解決數學問題的語言模型。",
    "ja-JP": "Qwen Mathは、数学問題の解決に特化した言語モデルです。",
    "ru-RU": "Qwen Math — языковая модель, специализирующаяся на решении математических задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Math Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-max",
   "model_name": "qwen-max",
   "display_name": "Qwen Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.070588"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.343"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.372"
      }
     },
     "provider_model_id": "qwen-max-2024-04-03"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.52"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.345"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.377"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.51"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.07"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.823529"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     },
     "provider_model_id": "qwen/qwen-max"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.4"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5997"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.392"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.64"
      }
     },
     "provider_model_id": "qwen/qwen-max"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34783"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3913"
      }
     },
     "provider_model_id": "qwen-max-2025-01-25"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.4"
      }
     },
     "provider_model_id": "alibaba/qwen-max"
    }
   ],
   "intro": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
   "released_at": "2024-04-03",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true,
    "web_search": true
   },
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models",
   "model_type": "text_generation",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen-max",
    "qwen-max-2024-04-03",
    "qwen-max-2024-04-28",
    "qwen-max-2024-09-19",
    "qwen-max-2025-01-25",
    "qwen/qwen-max"
   ],
   "intro_i18n": {
    "zh-CN": "千亿级超大 Qwen 模型，支持中文、英文等多语言，是当前 Qwen2.5 产品背后的 API 模型。",
    "zh-TW": "千億級超大型 Qwen 模型，支援中文、英文及其他語言；為目前 Qwen2.5 系列產品背後的 API 模型。",
    "ja-JP": "千億規模の超大規模Qwenモデルで、中国語、英語など多言語に対応。現在のQwen2.5製品のAPIモデルです。",
    "ru-RU": "Ультра-крупная модель Qwen с сотнями миллиардов параметров, поддерживающая китайский, английский и другие языки; API-модель, лежащая в основе текущих продуктов Qwen2.5."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-max-0125",
   "model_name": "qwen-max-0125",
   "display_name": "qwen-max-0125",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.52"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen-max-0125"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-max-latest",
   "model_name": "qwen-max-latest",
   "display_name": "Qwen-Max-Latest",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.343"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.372"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.4"
      }
     }
    }
   ],
   "intro": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
   "released_at": "2024-04-03",
   "knowledge_cutoff": "2024-11",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen-Max-Latest"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-max-longcontext",
   "model_name": "qwen-max-longcontext",
   "display_name": "qwen-max-longcontext",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "21"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen-max-longcontext"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-mt-flash",
   "model_name": "qwen-mt-flash",
   "display_name": "qwen-mt-flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.101"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49"
      }
     },
     "provider_model_id": "qwen/qwen-mt-flash"
    }
   ],
   "released_at": "2025-12-30",
   "max_input_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "max_output_tokens": 8192,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen-mt-flash"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen-mt-flash"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-mt-lite",
   "model_name": "qwen-mt-lite",
   "display_name": "qwen-mt-lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.086"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.086"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.229"
      }
     }
    }
   ],
   "released_at": "2025-12-30",
   "max_input_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "max_output_tokens": 8192,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen-mt-lite"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-mt-lite-us",
   "model_name": "qwen-mt-lite-us",
   "display_name": "Qwen-MT-Lite-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     }
    }
   ],
   "released_at": "2026-03-29",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen-MT-Lite-US"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-mt-plus",
   "model_name": "qwen-mt-plus",
   "display_name": "Qwen-MT Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.46"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.37"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.772"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.492"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.476"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.259"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.775"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "qwen/qwen-mt-plus"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.46"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.37"
      }
     },
     "provider_model_id": "qwen/qwen-mt-plus"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "qwen/qwen-mt-plus"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "qwen/qwen-mt-plus"
    }
   ],
   "intro": "Translation model for multilingual conversion, localization, and cross-language workflows",
   "released_at": "2025-01",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen-mt-plus"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "function_calling: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-mt-turbo",
   "model_name": "qwen-mt-turbo",
   "display_name": "Qwen-MT Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.279"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.192"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.534912"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.101"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    }
   ],
   "intro": "Translation model for multilingual conversion, localization, and cross-language workflows",
   "released_at": "2025-01",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation"
  },
  {
   "slug": "alibaba/qwen-omni-turbo",
   "model_name": "qwen-omni-turbo",
   "display_name": "Qwen-Omni Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "4.44"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "8.89"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.9"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3.584"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "7.168"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
   "released_at": "2025-01-19",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 32768,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "omni",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen-Omni 模型支持多模态输入（视频、音频、图像、文本）并输出音频与文本。",
    "zh-TW": "Qwen-Omni 模型支援多模態輸入（影片、音訊、圖片、文字）並輸出語音與文字。",
    "ja-JP": "Qwen-Omniモデルは、動画、音声、画像、テキストなどのマルチモーダル入力に対応し、音声とテキストを出力します。",
    "ru-RU": "Модели Qwen-Omni поддерживают мультимодальный ввод (видео, аудио, изображения, текст) и вывод в виде аудио и текста."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-omni-turbo-realtime",
   "model_name": "qwen-omni-turbo-realtime",
   "display_name": "Qwen-Omni Turbo Realtime",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "4.44"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "8.89"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.918"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3.584"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "7.168"
      }
     }
    }
   ],
   "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
   "released_at": "2025-05-08",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 32768,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "audio_input": true,
    "audio_output": true,
    "stream": true
   },
   "model_type": "realtime_omni",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-plus",
   "model_name": "qwen-plus",
   "display_name": "Qwen Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.023529"
      },
      "cache_read_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.070588"
      },
      "cache_read_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "0.141176"
      },
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.352941"
      },
      "prompt_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "0.705882"
      },
      "completion_0_0_128_false": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion_0_0_128_true": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_128_0_256_false": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion_0_128_0_256_true": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_256_infinity_false": {
       "unit": "per_M_tokens",
       "price": "7.058824"
      },
      "completion_0_256_infinity_true": {
       "unit": "per_M_tokens",
       "price": "9.411765"
      }
     },
     "provider_model_id": "qwen-plus-2025-01-25"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen-plus-2024-07-23"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1126"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.126"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02252"
      }
     },
     "provider_model_id": "qwen-plus-2025-04-28"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.115"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.147"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.012"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.144"
      }
     },
     "provider_model_id": "qwen-plus-2025-07-28"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/qwen-plus"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen/qwen-plus-2025-01-25"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3995"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2002"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.052"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.325"
      }
     },
     "provider_model_id": "qwen/qwen-plus",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "4.615385",
        "prompt": "4.615385",
        "completion": "4.615385"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "alibaba/qwen-plus"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.28"
      }
     }
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2024-01-25",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true,
    "web_search": true
   },
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models",
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "deprecated": true,
   "parameters": {
    "supported": [
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen-plus",
    "qwen-plus-2024-07-23",
    "qwen-plus-2024-08-06",
    "qwen-plus-2024-09-19",
    "qwen-plus-2024-11-25",
    "qwen-plus-2024-11-27",
    "qwen-plus-2024-12-20",
    "qwen-plus-2025-01-12",
    "qwen-plus-2025-01-25",
    "qwen-plus-2025-04-28",
    "qwen-plus-2025-07-14",
    "qwen-plus-2025-07-28",
    "qwen-plus-2025-09-11",
    "qwen-plus-2025-12-01",
    "qwen/qwen-plus",
    "qwen/qwen-plus-2025-01-25",
    "qwen/qwen-plus-2025-04-28",
    "qwen/qwen-plus-2025-07-14",
    "qwen/qwen-plus-2025-07-28",
    "qwen/qwen-plus-2025-07-28:thinking"
   ],
   "intro_i18n": {
    "zh-CN": "增强版超大 Qwen 模型，支持中文、英文等多语言。",
    "zh-TW": "增強版超大型 Qwen 模型，支援中文、英文及其他語言。",
    "ja-JP": "中国語、英語など多言語に対応した強化型超大規模Qwenモデルです。",
    "ru-RU": "Улучшенная ультра-крупная модель Qwen с поддержкой китайского, английского и других языков."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "open_weights: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-plus-2025-12-01-us",
   "model_name": "qwen-plus-2025-12-01-us",
   "display_name": "Qwen-Plus-2025-12-01-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen-Plus-2025-12-01-US"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-plus-character",
   "model_name": "qwen-plus-character",
   "display_name": "Qwen Plus Character",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.115"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.115"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     }
    }
   ],
   "released_at": "2024-01",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Plus Character"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-plus-character-ja",
   "model_name": "qwen-plus-character-ja",
   "display_name": "Qwen Plus Character (Japanese)",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen/qwen-plus-character-ja"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2024-01",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 8192,
   "max_output_tokens": 512,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen-plus-character-ja"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-plus-latest",
   "model_name": "qwen-plus-latest",
   "display_name": "Qwen Plus Latest",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1126"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.126"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02252"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-01-25",
   "max_input_tokens": 1000000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Plus Latest"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-plus-us",
   "model_name": "qwen-plus-us",
   "display_name": "Qwen-Plus-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    }
   ],
   "released_at": "2025-09-15",
   "max_input_tokens": 1000000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen-Plus-US"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-qwq-32b",
   "model_name": "qwen-qwq-32b",
   "display_name": "qwen-qwq-32b",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen-qwq-32b"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-qwq-32b-preview",
   "model_name": "qwen-qwq-32b-preview",
   "display_name": "Qwen Qwq 32b Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen-qwq-32b-preview"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen-qwq-32b-preview"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen-qwq-32b-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen QwQ 模型专注于推动 AI 推理能力，展示了开源模型在推理方面可与闭源前沿模型媲美。QwQ-32B-Preview 是一个实验性版本，在 GPQA、AIME、MATH-500 和 LiveCodeBench 等推理与分析任务中达到 o1 水平并超越 GPT-4o 和 Claude 3.5 Sonnet。注意：该模型目前作为无服务器模型实验性提供，Fireworks 可能会在短时间内终止部署，生产环境使用请注意。",
    "zh-TW": "Qwen QwQ 模型專注於推進 AI 推理能力，證明開源模型在推理方面可媲美封閉前沿模型。QwQ-32B-Preview 是一個實驗性版本，在 GPQA、AIME、MATH-500 與 LiveCodeBench 等推理與分析基準上，表現與 o1 相當，並超越 GPT-4o 與 Claude 3.5 Sonnet。注意：此模型目前以無伺服器方式實驗性提供，Fireworks 可能會在短時間內終止部署，請注意生產環境使用風險。",
    "ja-JP": "Qwen QwQモデルはAIの推論能力の向上に焦点を当てており、オープンモデルがクローズドな最先端モデルに匹敵する推論性能を持つことを示しています。QwQ-32B-Previewは実験的なリリースで、GPQA、AIME、MATH-500、LiveCodeBenchにおいてo1と同等、GPT-4oやClaude 3.5 Sonnetを上回る推論・分析性能を示します。注：このモデルは現在、サーバーレスモデルとして実験的に提供されています。商用利用を検討する場合、Fireworksが予告なく提供を終了する可能性がある点にご注意ください。",
    "ru-RU": "Модель Qwen QwQ направлена на развитие возможностей ИИ в области рассуждений, демонстрируя, что открытые модели могут конкурировать с закрытыми передовыми решениями. QwQ-32B-Preview — это экспериментальный выпуск, сопоставимый с o1 и превосходящий GPT-4o и Claude 3.5 Sonnet по рассуждению и анализу на метриках GPQA, AIME, MATH-500 и LiveCodeBench. Примечание: модель предоставляется в экспериментальном режиме как серверлесс-решение. Для использования в продакшене учтите, что Fireworks может прекратить развертывание без предварительного уведомления."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen Qwq 32b Preview"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen-SEA-LION-v4-32B-IT",
   "model_name": "Qwen-SEA-LION-v4-32B-IT",
   "display_name": "aisingapore/Qwen-SEA-LION-v4-32B-IT",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "aisingapore/Qwen-SEA-LION-v4-32B-IT"
    }
   ],
   "released_at": "2025-10-16",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "aisingapore/Qwen-SEA-LION-v4-32B-IT"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "structured_output: true→false"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aisingapore/Qwen-SEA-LION-v4-32B-IT"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-turbo",
   "model_name": "qwen-turbo",
   "display_name": "Qwen Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.008824"
      }
     },
     "provider_model_id": "qwen-turbo-2024-11-01"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     },
     "provider_model_id": "qwen-turbo-2024-06-24"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.046"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.092"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0092"
      }
     },
     "provider_model_id": "qwen-turbo-2024-11-01"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.087"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.431"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "qwen/qwen-turbo"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "qwen/qwen-turbo"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04348"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08696"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "alibaba/qwen-turbo"
    }
   ],
   "intro": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
   "released_at": "2024-11-01",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "web_search": true
   },
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models",
   "model_type": "text_generation",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen-turbo",
    "qwen-turbo-2024-06-24",
    "qwen-turbo-2024-09-19",
    "qwen-turbo-2024-11-01",
    "qwen-turbo-2025-02-11",
    "qwen-turbo-2025-04-28",
    "qwen-turbo-2025-07-15",
    "qwen/qwen-turbo"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen Turbo 将不再更新，建议替换为 Qwen Flash。超大 Qwen 模型，支持中文、英文等多语言。",
    "zh-TW": "Qwen Turbo 將不再更新，請改用 Qwen Flash。超大型 Qwen 模型，支援中文、英文及其他語言。",
    "ja-JP": "Qwen Turboは今後更新されません。Qwen Flashへの置き換えを推奨します。中国語、英語など多言語に対応した超大規模Qwenモデルです。",
    "ru-RU": "Qwen Turbo больше не обновляется; рекомендуется заменить на Qwen Flash. Ультра-крупная модель Qwen с поддержкой китайского, английского и других языков."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-turbo-latest",
   "model_name": "qwen-turbo-latest",
   "display_name": "qwen-turbo-latest",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.046"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.092"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0092"
      }
     }
    }
   ],
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models",
   "max_input_tokens": 1000000,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "released_at": "2025-08-08",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-v2p5-14b-instruct",
   "model_name": "qwen-v2p5-14b-instruct",
   "display_name": "Qwen2.5 14B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen-v2p5-14b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen-v2p5-14b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 14B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-v2p5-7b",
   "model_name": "qwen-v2p5-7b",
   "display_name": "Qwen2.5 7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen-v2p5-7b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen-v2p5-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 7B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-vl-chat-v1",
   "model_name": "qwen-vl-chat-v1",
   "display_name": "Qwen VL Chat",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen VL 支持灵活交互，包括多图输入、多轮问答与创意任务。",
    "zh-TW": "Qwen VL 支援靈活互動，包括多圖輸入、多輪問答與創意任務。",
    "ja-JP": "Qwen VLは、複数画像入力、マルチターンQA、創造的タスクなど柔軟な対話に対応します。",
    "ru-RU": "Qwen VL поддерживает гибкие взаимодействия, включая ввод нескольких изображений, многотактные вопросы и ответы, а также творческие задачи."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen VL Chat"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-vl-max",
   "model_name": "qwen-vl-max",
   "display_name": "Qwen-VL Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.047059"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      }
     },
     "provider_model_id": "qwen-vl-max-2024-08-09"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.574"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "qwen/qwen-vl-max"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "qwen/qwen-vl-max"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43478"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.30435"
      }
     },
     "provider_model_id": "qwen-vl-max-2025-01-25"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2024-04-08",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen-vl-max-2024-08-09",
    "qwen-vl-max-2024-10-30",
    "qwen-vl-max-2024-11-19",
    "qwen-vl-max-2024-12-30",
    "qwen-vl-max-2025-01-25",
    "qwen-vl-max-2025-04-02",
    "qwen-vl-max-2025-04-08",
    "qwen-vl-max-2025-08-13",
    "qwen/qwen-vl-max"
   ],
   "intro_i18n": {
    "zh-CN": "超大 Qwen 视觉语言模型。相比增强版，进一步提升视觉推理与指令跟随能力，具备更强视觉感知与认知能力。",
    "zh-TW": "超大型 Qwen 視覺語言模型。相較於增強版，進一步提升視覺推理與指令遵循能力，具備更強的視覺感知與認知能力。",
    "ja-JP": "超大規模Qwenビジョン・ランゲージモデル。強化版と比較して、視覚的推論と指示追従能力がさらに向上し、視覚的知覚と認知が強化されています。",
    "ru-RU": "Ультра-крупная мультимодальная модель Qwen. По сравнению с улучшенной версией, она еще больше усиливает визуальное рассуждение и следование инструкциям, обеспечивая более сильное визуальное восприятие и когнитивные способности."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-vl-max-latest",
   "model_name": "qwen-vl-max-latest",
   "display_name": "Qwen VL Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.572"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "image_output": true,
    "pdf_input": true
   },
   "released_at": "2025-08-18",
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "超大 Qwen 视觉语言模型。相比增强版，进一步提升视觉推理与指令跟随能力，具备更强感知与认知能力。",
    "zh-TW": "超大型 Qwen 視覺語言模型。相較於增強版，進一步提升視覺推理與指令遵循能力，具備更強的感知與認知能力。",
    "ja-JP": "超大規模Qwenビジョン・ランゲージモデル。強化版と比較して、視覚的推論と指示追従能力がさらに向上し、知覚と認知が強化されています。",
    "ru-RU": "Ультра-крупная мультимодальная модель Qwen. По сравнению с улучшенной версией, она еще больше усиливает визуальное рассуждение и следование инструкциям, обеспечивая более сильное восприятие и когнитивные способности."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen VL Max"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-vl-ocr",
   "model_name": "qwen-vl-ocr",
   "display_name": "Qwen-VL OCR",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.717"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.717"
      }
     },
     "provider_model_id": "qwen-vl-ocr-2025-11-20"
    }
   ],
   "intro": "OCR model for extracting structured text from documents and screenshots",
   "released_at": "2024-10-28",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 34096,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen-vl-ocr-2025-11-20"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen OCR 是一款用于文档、表格、考试图片和手写文字的文本提取模型，支持中文、英文、法语、日语、韩语、德语、俄语、意大利语、越南语和阿拉伯语。",
    "zh-TW": "Qwen OCR 是一款文字擷取模型，適用於文件、表格、考卷圖片與手寫文字。支援中文、英文、法文、日文、韓文、德文、俄文、義大利文、越南文與阿拉伯文。",
    "ja-JP": "Qwen OCRは、文書、表、試験画像、手書き文字からのテキスト抽出モデルです。中国語、英語、フランス語、日本語、韓国語、ドイツ語、ロシア語、イタリア語、ベトナム語、アラビア語に対応します。",
    "ru-RU": "Qwen OCR — это модель извлечения текста из документов, таблиц, экзаменационных изображений и рукописного текста. Поддерживает китайский, английский, французский, японский, корейский, немецкий, русский, итальянский, вьетнамский и арабский языки."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-vl-plus",
   "model_name": "qwen-vl-plus",
   "display_name": "Qwen-VL Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.63"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.023529"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     },
     "provider_model_id": "qwen-vl-plus-2024-08-09"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.115"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.63"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.042"
      }
     },
     "provider_model_id": "qwen/qwen-vl-plus"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.64"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.63"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0273"
      }
     },
     "provider_model_id": "qwen/qwen-vl-plus"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2024-01-25",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen-vl-plus-2024-08-09",
    "qwen-vl-plus-2025-01-02",
    "qwen-vl-plus-2025-01-25",
    "qwen-vl-plus-2025-05-07",
    "qwen-vl-plus-2025-07-10",
    "qwen-vl-plus-2025-08-15",
    "qwen/qwen-vl-plus"
   ],
   "intro_i18n": {
    "zh-CN": "增强版大规模 Qwen 视觉语言模型，在细节和文本识别方面有显著提升，支持超过百万像素分辨率和任意宽高比。",
    "zh-TW": "增強版大型 Qwen 視覺語言模型，在細節與文字識別方面有重大提升，支援超過百萬像素解析度與任意長寬比。",
    "ja-JP": "詳細とテキスト認識において大幅な性能向上を実現した強化型大規模Qwenビジョン・ランゲージモデル。100万画素以上の解像度と任意のアスペクト比に対応します。",
    "ru-RU": "Улучшенная крупномасштабная мультимодальная модель Qwen с заметным улучшением детализации и распознавания текста, поддерживающая разрешение более одного мегапикселя и произвольные соотношения сторон."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-vl-plus-latest",
   "model_name": "qwen-vl-plus-latest",
   "display_name": "Qwen VL Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "image_output": true,
    "pdf_input": true
   },
   "released_at": "2025-08-18",
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "增强版大规模 Qwen 视觉语言模型，在细节和文本识别方面有显著提升，支持超过百万像素分辨率和任意宽高比。",
    "zh-TW": "增強版大型 Qwen 視覺語言模型，在細節與文字識別方面有重大提升，支援超過百萬像素解析度與任意長寬比。",
    "ja-JP": "詳細とテキスト認識において大幅な性能向上を実現した強化型大規模Qwenビジョン・ランゲージモデル。100万画素以上の解像度と任意のアスペクト比に対応します。",
    "ru-RU": "Улучшенная крупномасштабная мультимодальная модель Qwen с заметным улучшением детализации и распознавания текста, поддерживающая разрешение более одного мегапикселя и произвольные соотношения сторон."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen VL Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qwen-vl-v1",
   "model_name": "qwen-vl-v1",
   "display_name": "Qwen VL",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "基于 Qwen-7B 预训练模型，加入视觉模块，支持 448 分辨率图像输入。",
    "zh-TW": "從 Qwen-7B 預訓練模型初始化，加入視覺模組並支援 448 圖像解析度輸入。",
    "ja-JP": "Qwen-7Bをベースに視覚モジュールを追加し、448解像度の画像入力に対応した事前学習モデルです。",
    "ru-RU": "Предобученная модель, инициализированная от Qwen-7B с добавленным модулем зрения и входом изображения с разрешением 448."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen VL"
    }
   ]
  },
  {
   "slug": "alibaba/qwen/qwen-2.5-72b-instruct",
   "model_name": "qwen/qwen-2.5-72b-instruct",
   "display_name": "Qwen 2.5 72B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.062"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.231"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "qwen-2.5-72b-instruct"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.357"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen-2.5-72b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen-2.5-72b-instruct"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.404412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.423529"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "novita/qwen/qwen-2.5-72b-instruct"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2024-10-15",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 32000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "novita/qwen/qwen-2.5-72b-instruct",
    "qwen-2.5-72b-instruct",
    "qwen-2.5-72b-instruct:free"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5-72B-Instruct 是阿里云最新发布的大语言模型之一。该 72B 模型在编程和数学方面有显著提升，支持超过 29 种语言（包括中英文），在指令理解、结构化数据处理和结构化输出（尤其是 JSON）方面表现优异。",
    "zh-TW": "Qwen2.5-72B-Instruct 是阿里雲最新發布的 LLM 之一。72B 模型在程式設計與數學方面有顯著提升，支援超過 29 種語言（含中英文），並大幅提升指令遵循、結構化資料理解與結構化輸出（特別是 JSON）。",
    "ja-JP": "Qwen2.5-72B-Instructは、Alibaba Cloudの最新LLMの一つです。72Bモデルは、コーディングと数学において顕著な改善をもたらし、中国語と英語を含む29以上の言語に対応。指示追従、構造化データの理解、構造化出力（特にJSON）において大幅に向上しています。",
    "ru-RU": "Qwen2.5-72B-Instruct — одна из новейших LLM-моделей от Alibaba Cloud. Модель с 72 миллиардами параметров демонстрирует значительные улучшения в программировании и математике, поддерживает более 29 языков (включая китайский и английский), а также существенно улучшает следование инструкциям, понимание структурированных данных и генерацию структурированного вывода (особенно в формате JSON)."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 72B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen1.5-0.5B",
   "model_name": "Qwen1.5-0.5B",
   "display_name": "Qwen1.5-0.5B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen/Qwen1.5-0.5B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen1.5-0.5B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen1.5-0.5B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen1.5-1.8B",
   "model_name": "Qwen1.5-1.8B",
   "display_name": "Qwen1.5-1.8B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen/Qwen1.5-1.8B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen1.5-1.8B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen1.5-1.8B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen1.5-14B",
   "model_name": "Qwen1.5-14B",
   "display_name": "Qwen1.5-14B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen/Qwen1.5-14B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen1.5-14B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen1.5-14B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen1.5-4B",
   "model_name": "Qwen1.5-4B",
   "display_name": "Qwen1.5-4B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen/Qwen1.5-4B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen1.5-4B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen1.5-4B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen1.5-72B",
   "model_name": "Qwen1.5-72B",
   "display_name": "Qwen1.5-72B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "Qwen/Qwen1.5-72B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen1.5-72B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen1.5-72B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen1.5-7B",
   "model_name": "Qwen1.5-7B",
   "display_name": "Qwen1.5-7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Qwen/Qwen1.5-7B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen1.5-7B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen1.5-7B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen1p5-72b-chat",
   "model_name": "qwen1p5-72b-chat",
   "display_name": "Qwen1.5 72B Chat",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen1p5-72b-chat"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen1p5-72b-chat"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen1.5 72B Chat"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2-1.5B-Instruct",
   "model_name": "Qwen2-1.5B-Instruct",
   "display_name": "Qwen/Qwen2-1.5B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Qwen/Qwen2-1.5B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "Qwen/Qwen2-1.5B-Instruct"
    }
   ],
   "capabilities": {},
   "released_at": "2024-06-07",
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2-1.5B-Instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen2-1.5B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-14b-instruct",
   "model_name": "qwen2-5-14b-instruct",
   "display_name": "Qwen2.5 14B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "qwen2.5-14b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen2.5-14b-instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.431"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     },
     "provider_model_id": "qwen2.5-14b-instruct"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-14B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-14B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-14B-Instruct"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2024-09",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-14B-Instruct",
    "qwen2.5-14b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5-14B-Instruct 是阿里云最新大语言模型系列的一部分。该 14B 模型在编程和数学方面有显著提升，支持 29 种以上语言，并在指令理解、结构化数据理解和结构化输出（尤其是 JSON）方面表现更优。",
    "zh-TW": "Qwen2.5-14B-Instruct 是阿里雲最新 LLM 系列的一部分。此 14B 模型在程式碼與數學方面有顯著提升，支援超過 29 種語言，並強化指令遵循、結構化資料理解與結構化輸出（特別是 JSON）。",
    "ja-JP": "Qwen2.5-14B-Instruct は、Alibaba Cloud の最新 LLM シリーズの一部です。14B モデルはコーディングと数学において顕著な向上を示し、29 以上の言語をサポートし、命令追従、構造化データの理解、構造化出力（特に JSON）を改善しています。",
    "ru-RU": "Qwen2.5-14B-Instruct — часть последней серии LLM от Alibaba Cloud. Модель с 14 млрд параметров демонстрирует значительный прогресс в программировании и математике, поддерживает более 29 языков и улучшает выполнение инструкций, понимание структурированных данных и генерацию структурированного вывода (особенно JSON)."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-14b-instruct-1m",
   "model_name": "qwen2-5-14b-instruct-1m",
   "display_name": "Qwen2.5 14B 1M",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "qwen2.5-14b-instruct-1m"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    }
   ],
   "released_at": "2025-01-27",
   "max_input_tokens": 1000000,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen2.5-14b-instruct-1m"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5 开源 72B 模型。",
    "zh-TW": "Qwen2.5 開源 72B 模型。",
    "ja-JP": "Qwen2.5のオープンソース72Bモデルです。",
    "ru-RU": "Открытая модель Qwen2.5 с 72 миллиардами параметров."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 14B 1M"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-32b-instruct",
   "model_name": "qwen2-5-32b-instruct",
   "display_name": "Qwen2.5 32B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     },
     "provider_model_id": "qwen2.5-32b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-32B-Instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.514706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      }
     },
     "provider_model_id": "qwen2.5-32b-instruct"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Qwen2.5-32B-Instruct"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.185294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.185294"
      }
     },
     "provider_model_id": "qwen/qwen2.5-32b-instruct"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.185294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.185294"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-32B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-32B-Instruct"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2024-09",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "docs_url": "https://nebius.com/prices-ai-studio",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-32B-Instruct",
    "Qwen2.5-32B-Instruct",
    "qwen/qwen2.5-32b-instruct",
    "qwen2.5-32b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5-32B-Instruct 是阿里云最新大语言模型系列的一部分。该 32B 模型在编程和数学方面有显著提升，支持 29 种以上语言，并在指令理解、结构化数据理解和结构化输出（尤其是 JSON）方面表现更优。",
    "zh-TW": "Qwen2.5-32B-Instruct 是阿里雲最新 LLM 系列的一部分。此 32B 模型在程式碼與數學方面有顯著提升，支援超過 29 種語言，並強化指令遵循、結構化資料理解與結構化輸出（特別是 JSON）。",
    "ja-JP": "Qwen2.5-32B-Instruct は、Alibaba Cloud の最新 LLM シリーズの一部です。32B モデルはコーディングと数学において顕著な向上を示し、29 以上の言語をサポートし、命令追従、構造化データの理解、構造化出力（特に JSON）を改善しています。",
    "ru-RU": "Qwen2.5-32B-Instruct — часть последней серии LLM от Alibaba Cloud. Модель с 32 млрд параметров демонстрирует значительный прогресс в программировании и математике, поддерживает более 29 языков и улучшает выполнение инструкций, понимание структурированных данных и генерацию структурированного вывода (особенно JSON)."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-3b-instruct",
   "model_name": "qwen2-5-3b-instruct",
   "display_name": "qwen2.5-3b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "qwen2.5-3b-instruct"
    }
   ],
   "released_at": "2025-08-06",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen2.5-3b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen2.5-3b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-72b-instruct",
   "model_name": "qwen2-5-72b-instruct",
   "display_name": "Qwen2.5 72B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.6"
      }
     },
     "provider_model_id": "qwen2.5-72b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.72"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.721"
      }
     }
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     },
     "provider_model_id": "Qwen2.5-72B-Instruct"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     },
     "provider_model_id": "qwen2.5-72b-instruct"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen2.5-72B-Instruct"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Qwen2.5-72B-Instruct"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen2.5-72B-Instruct"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "Qwen2.5-72B-Instruct"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.607353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.607353"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen2.5-72B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2024-09",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "model_type": "text_generation",
   "docs_url": "https://nebius.com/prices-ai-studio",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-72B-Instruct",
    "Qwen2.5-72B-Instruct",
    "deepinfra/Qwen/Qwen2.5-72B-Instruct",
    "qwen2.5-72b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5-72B-Instruct 是阿里云最新大语言模型系列的一部分。该 72B 模型在编程和数学方面有显著提升，支持 29 种以上语言，并在指令理解、结构化数据理解和结构化输出（尤其是 JSON）方面表现更优。",
    "zh-TW": "Qwen2.5-72B-Instruct 是阿里雲最新 LLM 系列的一部分。此 72B 模型在程式碼與數學方面有顯著提升，支援超過 29 種語言，並強化指令遵循、結構化資料理解與結構化輸出（特別是 JSON）。",
    "ja-JP": "Qwen2.5-72B-Instruct は、Alibaba Cloud の最新 LLM シリーズの一部です。72B モデルはコーディングと数学において顕著な向上を示し、29 以上の言語をサポートし、命令追従、構造化データの理解、構造化出力（特に JSON）を改善しています。",
    "ru-RU": "Qwen2.5-72B-Instruct — часть последней серии LLM от Alibaba Cloud. Модель с 72 млрд параметров демонстрирует значительный прогресс в программировании и математике, поддерживает более 29 языков и улучшает выполнение инструкций, понимание структурированных данных и генерацию структурированного вывода (особенно JSON)."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "huggingface",
     "charge": "prompt",
     "old": "0.38",
     "new": "0.36"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-7b-instruct",
   "model_name": "qwen2-5-7b-instruct",
   "display_name": "Qwen2.5 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "qwen2.5-7b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.143"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-7B-Instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.144"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen2.5-7B-Instruct"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-7B-Instruct"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "qwen2.5-7b-instruct"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-7B-Instruct"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "qwen/qwen2.5-7b-instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "qwen2.5-7b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "qwen/qwen2.5-7b-instruct"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.051471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.051471"
      }
     },
     "provider_model_id": "Pro/Qwen/Qwen2.5-7B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-7B-Instruct"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-7B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-7B-Instruct"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2024-09",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Pro/Qwen/Qwen2.5-7B-Instruct",
    "Qwen/Qwen2.5-7B-Instruct",
    "Qwen2.5-7B-Instruct",
    "qwen/qwen2.5-7b-instruct",
    "qwen2.5-7b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5-7B-Instruct 是阿里云最新大模型系列的一部分。该 70 亿参数模型在编程和数学方面有显著提升，支持 29+ 种语言，增强了指令理解、结构化数据处理和结构化输出（特别是 JSON）。",
    "zh-TW": "Qwen2.5-7B-Instruct 是阿里雲最新大型語言模型系列的一部分。此 70 億參數模型在程式碼與數學方面有顯著提升，支援超過 29 種語言，並加強了指令遵循、結構化資料理解與結構化輸出（特別是 JSON）能力。",
    "ja-JP": "Qwen2.5-7B-Instructは、Alibaba Cloudの最新LLMシリーズの一部です。7Bモデルは、コーディングと数学で顕著な向上を示し、29以上の言語をサポート。命令追従、構造化データの理解、構造化出力（特にJSON）を改善しています。",
    "ru-RU": "Qwen2.5-7B-Instruct входит в последнюю серию LLM от Alibaba Cloud. Модель на 7B параметров демонстрирует значительный прогресс в программировании и математике, поддерживает более 29 языков и улучшает следование инструкциям, понимание структурированных данных и структурированный вывод (особенно JSON)."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-7b-instruct-1m",
   "model_name": "qwen2-5-7b-instruct-1m",
   "display_name": "qwen2.5-7b-instruct-1m",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.143"
      }
     }
    }
   ],
   "released_at": "2025-12-30",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen2.5-7b-instruct-1m"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-coder-14b-instruct",
   "model_name": "qwen2-5-coder-14b-instruct",
   "display_name": "Qwen2.5 Coder 14B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     },
     "provider_model_id": "qwen2.5-coder-14b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "released_at": "2025-12-30",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen2.5-coder-14b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5-Coder-14B-Instruct 是一款大规模预训练的编程指令模型，具备强大的代码理解与生成能力，能够高效处理多种编程任务，适用于智能编程、自动脚本生成与编程问答。",
    "zh-TW": "Qwen2.5-Coder-14B-Instruct 是一款大型預訓練程式指令模型，具備強大的程式理解與生成能力。能高效處理各類程式任務，適用於智慧編碼、自動腳本生成與程式問答。",
    "ja-JP": "Qwen2.5-Coder-14B-Instructは、大規模な事前学習済みのコーディング指示モデルで、コードの理解と生成に優れています。幅広いプログラミングタスクを効率的に処理でき、スマートコーディング、自動スクリプト生成、プログラミングQ&Aに最適です。",
    "ru-RU": "Qwen2.5-Coder-14B-Instruct — это крупномасштабная предварительно обученная модель для программирования, обладающая высокой способностью к пониманию и генерации кода. Она эффективно справляется с широким спектром задач программирования, идеально подходит для интеллектуального кодирования, автоматической генерации скриптов и вопросов по программированию."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 Coder 14B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-coder-32b-instruct",
   "model_name": "qwen2-5-coder-32b-instruct",
   "display_name": "Qwen2.5-Coder 32B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     },
     "provider_model_id": "qwen2.5-coder-32b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     }
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "@cf/qwen/qwen2.5-coder-32b-instruct"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      }
     },
     "provider_model_id": "qwen/Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen2.5-coder-32b-instruct"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.96"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.96"
      }
     },
     "provider_model_id": "qwen2.5-coder-32b-instruct"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "hf:Qwen/Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-Coder-32B-Instruct"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen2.5-coder-32b-instruct"
    }
   ],
   "released_at": "2024-11",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true
   },
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/qwen/qwen2.5-coder-32b-instruct",
    "Qwen/Qwen2.5-Coder-32B-Instruct",
    "Qwen2.5-Coder-32B-Instruct",
    "deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct",
    "hf:Qwen/Qwen2.5-Coder-32B-Instruct",
    "qwen/Qwen2.5-Coder-32B-Instruct",
    "qwen/qwen2.5-coder-32b-instruct",
    "qwen2.5-coder-32b-instruct",
    "workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5 Coder 32B Instruct 是阿里云最新面向编程的大语言模型。基于 Qwen2.5 构建，并使用 5.5 万亿 tokens 进行训练，在代码生成、推理和修复方面有显著提升，同时保留数学和通用能力，为构建编程智能体提供强大基础。",
    "zh-TW": "Qwen2.5 Coder 32B Instruct 是阿里雲最新專注於程式碼的 LLM。基於 Qwen2.5 並使用 5.5T token 訓練，顯著提升程式碼生成、推理與修復能力，同時保有數學與通用能力，為程式代理提供強大基礎。",
    "ja-JP": "Qwen2.5 Coder 32B Instruct は、Alibaba Cloud による最新のコード特化型 LLM です。Qwen2.5 を基盤とし、5.5T トークンで訓練されており、コード生成、推論、修復を大幅に改善し、数学および一般的な能力も維持しています。コーディングエージェントの強力な基盤を提供します。",
    "ru-RU": "Qwen2.5 Coder 32B Instruct — последняя модель от Alibaba Cloud, ориентированная на программирование. Построена на базе Qwen2.5 и обучена на 5.5 трлн токенов, значительно улучшает генерацию кода, логическое мышление и исправление ошибок, сохраняя при этом сильные стороны в математике и общем понимании, обеспечивая надёжную основу для кодирующих агентов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 32B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-coder-7b",
   "model_name": "qwen2-5-coder-7b",
   "display_name": "Qwen 2.5 Coder 7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "Qwen2.5-Coder-7B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "docs_url": "https://nebius.com/prices-ai-studio",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "family": "Qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen2.5-Coder-7B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 Coder 7B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-coder-7b-instruct",
   "model_name": "qwen2-5-coder-7b-instruct",
   "display_name": "Qwen2.5-Coder 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     },
     "provider_model_id": "qwen2.5-coder-7b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen2.5-coder-7b-instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "qwen2.5-coder-7b-instruct"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-Coder-7B-Instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "qwen/qwen2.5-coder-7b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen/qwen2.5-coder-7b-instruct"
    }
   ],
   "released_at": "2024-11",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "structured_output": true,
    "open_weights": true
   },
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-Coder-7B-Instruct",
    "qwen/qwen2.5-coder-7b-instruct",
    "qwen2.5-coder-7b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "开源 Qwen 编程模型。",
    "zh-TW": "開源 Qwen 程式碼模型。",
    "ja-JP": "オープンソースのQwenコードモデルです。",
    "ru-RU": "Открытая модель кода Qwen."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 7B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-math-1-5b-instruct",
   "model_name": "qwen2-5-math-1-5b-instruct",
   "display_name": "Qwen2.5 Math 1.5B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen2.5-math-1.5b-instruct"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen2.5-math-1.5b-instruct"
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2025-12-31",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen2.5-math-1.5b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen-Math 在数学问题求解方面表现出色。",
    "zh-TW": "Qwen-Math 擅長數學問題解決。",
    "ja-JP": "Qwen-Mathは、数学問題の解決に優れた性能を発揮します。",
    "ru-RU": "Qwen-Math демонстрирует высокую эффективность в решении математических задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 Math 1.5B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-math-72b-instruct",
   "model_name": "qwen2-5-math-72b-instruct",
   "display_name": "Qwen2.5-Math 72B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.721"
      }
     },
     "provider_model_id": "qwen2.5-math-72b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.72"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "qwen2.5-math-72b-instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.721"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     },
     "provider_model_id": "qwen2.5-math-72b-instruct"
    }
   ],
   "released_at": "2024-09",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 4096,
   "max_output_tokens": 3072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen2.5-math-72b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen-Math 在数学问题求解方面表现出色。",
    "zh-TW": "Qwen-Math 擅長數學問題解決。",
    "ja-JP": "Qwen-Mathは、数学問題の解決に優れた性能を発揮します。",
    "ru-RU": "Qwen-Math демонстрирует высокую эффективность в решении математических задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Math 72B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-math-7b-instruct",
   "model_name": "qwen2-5-math-7b-instruct",
   "display_name": "Qwen2.5-Math 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     },
     "provider_model_id": "qwen2.5-math-7b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen2.5-math-7b-instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "qwen2.5-math-7b-instruct"
    }
   ],
   "released_at": "2024-09",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 4096,
   "max_output_tokens": 3072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen2.5-math-7b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen-Math 在数学问题求解方面表现出色。",
    "zh-TW": "Qwen-Math 擅長數學問題解決。",
    "ja-JP": "Qwen-Mathは、数学問題の解決に優れた性能を発揮します。",
    "ru-RU": "Qwen-Math демонстрирует высокую эффективность в решении математических задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Math 7B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-omni-7b",
   "model_name": "qwen2-5-omni-7b",
   "display_name": "Qwen2.5-Omni 7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "6.76"
      }
     },
     "provider_model_id": "qwen2.5-omni-7b"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.9"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.087"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.345"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "5.448"
      }
     }
    }
   ],
   "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
   "released_at": "2024-12",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 32768,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "omni",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen2.5-omni-7b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen-Omni 模型支持多模态输入（视频、音频、图像、文本）并输出音频与文本。",
    "zh-TW": "Qwen-Omni 模型支援多模態輸入（影片、音訊、圖片、文字）並可輸出語音與文字。",
    "ja-JP": "Qwen-Omniモデルは、動画、音声、画像、テキストなどのマルチモーダル入力に対応し、音声およびテキスト出力を生成します。",
    "ru-RU": "Модели Qwen-Omni поддерживают мультимодальные входные данные (видео, аудио, изображения, текст) и вывод в виде аудио и текста."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-vl-32b",
   "model_name": "qwen2-5-vl-32b",
   "display_name": "Qwen 2.5 VL 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "family": "Qwen",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 VL 32B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-vl-32b-instruct",
   "model_name": "qwen2-5-vl-32b-instruct",
   "display_name": "Qwen2.5 VL 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     },
     "provider_model_id": "qwen2.5-vl-32b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-32B-Instruct"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-32B-Instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen2.5-VL-32B-Instruct"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen/qwen2.5-vl-32b-instruct"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-32B-Instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "qwen/qwen2.5-vl-32b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.2"
      }
     }
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-32B-Instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "qwen/qwen2.5-vl-32b-instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-32B-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct"
    }
   ],
   "released_at": "2025-03-24",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "vision": true,
    "image_output": true,
    "video_input": true,
    "pdf_input": true,
    "open_weights": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "knowledge_cutoff": "2024-09",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-VL-32B-Instruct",
    "Qwen2.5-VL-32B-Instruct",
    "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct",
    "qwen/qwen2.5-vl-32b-instruct",
    "qwen2.5-vl-32b-instruct",
    "qwen2.5-vl-32b-instruct:free"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5VL系列模型在数学和主题问答方面接近Qwen2.5VL-72B的性能。响应风格经过调优以符合人类偏好，特别是针对数学、逻辑推理和知识问答等客观查询，输出更清晰、更详细。这是32B版本。",
    "zh-TW": "Qwen2.5VL 系列模型在數學和主題問答方面接近 Qwen2.5VL-72B 的性能。響應風格根據人類偏好進行調整，特別是針對數學、邏輯推理和知識問答等客觀查詢，輸出更清晰和詳細。這是32B版本。",
    "ja-JP": "Qwen2.5VLシリーズモデルで、数学や主題QAにおいてQwen2.5VL-72Bに近い性能を達成しています。応答スタイルは人間の好みに合わせて調整されており、特に数学、論理的推論、知識QAのような客観的なクエリに対して、より明確で詳細な出力を提供します。これは32Bバージョンです。",
    "ru-RU": "Модель серии Qwen2.5VL, достигающая почти уровня производительности Qwen2.5VL-72B в математике и предметных вопросах. Стиль ответов настроен для предпочтений человека, особенно для объективных запросов, таких как математика, логическое рассуждение и вопросы знаний, с более четкими и детализированными выводами. Это версия с 32B параметрами."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 VL 32B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-vl-3b-instruct",
   "model_name": "qwen2-5-vl-3b-instruct",
   "display_name": "qwen2.5-vl-3b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2025-02-21",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen2.5-vl-3b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-vl-72b-instruct",
   "model_name": "qwen2-5-vl-72b-instruct",
   "display_name": "Qwen2.5-VL 72B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.4"
      }
     },
     "provider_model_id": "qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.9"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-72B-Instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.881"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.224"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.671"
      }
     },
     "provider_model_id": "qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.01"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-72B-Instruct"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "qwen/qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "qwen/qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "TEE/qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-72B-Instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "qwen/qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen/qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.01"
      }
     },
     "provider_model_id": "qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.31884"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.95652"
      }
     },
     "provider_model_id": "qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "novita/qwen/qwen2.5-vl-72b-instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-72B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-72B-Instruct"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2024-09",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "docs_url": "https://nebius.com/prices-ai-studio",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-VL-72B-Instruct",
    "Qwen2.5-VL-72B-Instruct",
    "TEE/qwen2.5-vl-72b-instruct",
    "novita/qwen/qwen2.5-vl-72b-instruct",
    "qwen/qwen2.5-vl-72b-instruct",
    "qwen2.5-vl-72b-instruct",
    "qwen2.5-vl-72b-instruct:free"
   ],
   "intro_i18n": {
    "zh-CN": "提升了指令跟随、数学、问题求解与编程能力，具备更强的通用物体识别能力。支持跨格式视觉元素精准定位、最长 10 分钟视频理解（秒级事件定位）、时间顺序与速度理解，以及可解析与定位的操作系统或移动端代理控制。具备强大的关键信息提取与 JSON 输出能力。此为 72B 系列中最强版本。",
    "zh-TW": "強化指令遵循、數學、問題解決與程式能力，具備更強的物體辨識能力。支援跨格式精準視覺元素定位、長影片理解（最長 10 分鐘）、事件時間點與順序理解、速度感知，以及可控制作業系統或行動裝置的代理。具備強大的關鍵資訊擷取與 JSON 輸出能力。此為系列中最強的 72B 版本。",
    "ja-JP": "指示追従、数学、問題解決、コーディングの性能が向上し、一般的な物体認識も強化されています。形式を問わず正確な視覚要素の位置特定、10分までの長時間動画理解、秒単位のイベントタイミング、時間順序や速度の理解、OSやモバイルを操作可能なエージェント機能を備えています。重要情報の抽出やJSON出力にも優れています。これはシリーズ中最強の72Bバージョンです。",
    "ru-RU": "Улучшенное следование инструкциям, решение задач, математика и программирование, а также более точное распознавание объектов. Поддерживает точную локализацию визуальных элементов в различных форматах, понимание длинных видео (до 10 минут) с точной временной разметкой событий, определением порядка и скорости, а также агентов, способных управлять ОС или мобильными устройствами через парсинг и локализацию. Эффективное извлечение ключевой информации и вывод в формате JSON. Это версия 72B — самая мощная в серии."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-5-vl-7b-instruct",
   "model_name": "qwen2-5-vl-7b-instruct",
   "display_name": "Qwen2.5-VL 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.05"
      }
     },
     "provider_model_id": "qwen2.5-vl-7b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.717"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7246400000000001"
      }
     },
     "provider_model_id": "qwen2.5-vl-7b-instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-7B-Instruct"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2024-09",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-VL-7B-Instruct",
    "qwen2.5-vl-7b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "改进了指令遵循、数学、问题解决和编程能力，具有更强的通用对象识别能力。支持跨格式的精确视觉元素定位、长视频理解（最长 10 分钟）以及秒级事件时间、时间顺序和速度理解，并支持通过解析和定位控制操作系统或移动设备的代理。具有强大的关键信息提取和 JSON 输出能力。这是该系列中最强的 720 亿参数版本。",
    "zh-TW": "改進了指令跟隨、數學、問題解決和編程能力，具有更強的通用物體識別能力。支持跨格式的精確視覺元素定位、長視頻理解（最多 10 分鐘），包括秒級事件定時、時間順序和速度理解，以及能通過解析和定位控制操作系統或移動設備的代理。具有強大的關鍵信息提取和 JSON 輸出能力。這是系列中最強的 72B 版本。",
    "ja-JP": "指示追従、数学、問題解決、コーディングが改善され、より強力な一般物体認識を備えています。形式を超えた正確な視覚要素のローカリゼーション、10分間の長時間ビデオ理解、秒単位のイベントタイミング、時間順序および速度理解、OSやモバイルを制御できるエージェントをサポートします。強力な重要情報抽出とJSON出力を提供します。これはシリーズ中で最も強力な72Bバージョンです。",
    "ru-RU": "Улучшенное выполнение инструкций, математика, решение задач и программирование с более сильным общим распознаванием объектов. Поддерживает точное локализованное определение визуальных элементов в различных форматах, понимание длинных видео (до 10 минут) с точным определением событий на уровне секунд, временным упорядочением и пониманием скорости, а также агентов, которые могут управлять ОС или мобильными устройствами через парсинг и локализацию. Сильное извлечение ключевой информации и вывод JSON. Это самая мощная версия в серии с 72 миллиардами параметров."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2-57B-A14B-Instruct",
   "model_name": "Qwen2-57B-A14B-Instruct",
   "display_name": "qwen2-57b-a14b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "qwen2-57b-a14b-instruct"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "Qwen/Qwen2-57B-A14B-Instruct"
    }
   ],
   "released_at": "2025-12-30",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2-57B-A14B-Instruct",
    "qwen2-57b-a14b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen2-57b-a14b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2-72B-Instruct",
   "model_name": "Qwen2-72B-Instruct",
   "display_name": "Qwen2 72B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.72"
      }
     },
     "provider_model_id": "qwen2-72b-instruct"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen2-72B-Instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwen2-72b-instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "Qwen/Qwen2-72B-Instruct"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-08-06",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2-72B-Instruct",
    "accounts/fireworks/models/qwen2-72b-instruct",
    "qwen2-72b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen 2 Instruct（72B）在企业级任务中提供精准的指令执行能力。",
    "zh-TW": "Qwen 2 Instruct（72B）針對企業級工作負載提供精準的指令遵循能力。",
    "ja-JP": "Qwen 2 Instruct（72B）は、企業向けワークロードにおいて高精度な命令追従を実現します。",
    "ru-RU": "Qwen 2 Instruct (72B) обеспечивает точное выполнение инструкций для корпоративных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2 72B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2-7B-Instruct",
   "model_name": "Qwen2-7B-Instruct",
   "display_name": "Qwen2 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "qwen2-7b-instruct"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "Qwen/Qwen2-7B-Instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen2-7b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-08-06",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2-7B-Instruct",
    "accounts/fireworks/models/qwen2-7b-instruct",
    "qwen2-7b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2-7B-Instruct 是 Qwen2 系列中的 7B 指令微调模型，采用 Transformer 架构，结合 SwiGLU、QKV 偏置和分组查询注意力。该模型可处理大规模输入，在理解、生成、多语言、编程、数学和推理等基准测试中表现优异，超越大多数开源模型，并在多项评估中优于 Qwen1.5-7B-Chat。",
    "zh-TW": "Qwen2-7B-Instruct 是 Qwen2 系列中的 7B 指令微調模型，採用 Transformer、SwiGLU、QKV 偏置與分組查詢注意力架構。能處理大規模輸入，在理解、生成、多語言、程式碼、數學與推理基準測試中表現優異，超越多數開源模型，並在多項評估中勝過 Qwen1.5-7B-Chat。",
    "ja-JP": "Qwen2-7B-Instruct は、Qwen2 シリーズの 7B 命令調整モデルであり、Transformer、SwiGLU、QKV バイアス、グループ化クエリアテンションを使用しています。大規模入力に対応し、理解、生成、多言語、コーディング、数学、推論ベンチマークにおいて高い性能を発揮し、多くのオープンモデルを上回り、Qwen1.5-7B-Chat を複数の評価で凌駕しています。",
    "ru-RU": "Qwen2-7B-Instruct — модель с 7 млрд параметров из серии Qwen2, использующая Transformer, SwiGLU, смещение QKV и групповое внимание. Обрабатывает большие входные данные и демонстрирует высокие результаты в понимании, генерации, многоязычии, программировании, математике и логике, превосходя большинство открытых моделей и Qwen1.5-7B-Chat в ряде тестов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2 7B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2-Audio-7B-Instruct",
   "model_name": "Qwen2-Audio-7B-Instruct",
   "display_name": "Qwen2-Audio-7B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "100"
      }
     }
    }
   ],
   "docs_url": "https://cloud.sambanova.ai/plans/pricing",
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2025-06-19",
   "capabilities": {
    "audio_input": true
   },
   "modalities": {
    "input": [
     "audio"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2-Audio-7B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-instruct-72b",
   "model_name": "qwen2-instruct-72b",
   "display_name": "Qwen2 Instruct 72B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2 Instruct 72B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2-vl-2b-instruct",
   "model_name": "qwen2-vl-2b-instruct",
   "display_name": "Qwen2-VL 2B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2-vl-2b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2-vl-2b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2-VL 2B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2-VL-72B-Instruct",
   "model_name": "Qwen2-VL-72B-Instruct",
   "display_name": "Qwen2 VL 72B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.86"
      }
     },
     "provider_model_id": "qwen2-vl-72b-instruct"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.54"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwen2-vl-72b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2-vl-72b-instruct"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Qwen/Qwen2-VL-72B-Instruct"
    }
   ],
   "docs_url": "https://nebius.com/prices-ai-studio",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true,
    "open_weights": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-12-30",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2-VL-72B-Instruct",
    "accounts/fireworks/models/qwen2-vl-72b-instruct",
    "qwen2-vl-72b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "72B Qwen-VL 模型是阿里巴巴最新版本，体现了近一年的创新成果。",
    "zh-TW": "72B Qwen-VL 模型是阿里巴巴最新版本，展現近一年來的創新成果。",
    "ja-JP": "72B Qwen-VLモデルは、Alibabaによる最新のイテレーションであり、約1年にわたる革新の成果を反映しています。",
    "ru-RU": "Модель Qwen-VL с 72 миллиардами параметров — последняя разработка Alibaba, отражающая почти год инноваций."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2 VL 72B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2-VL-7B-Instruct",
   "model_name": "Qwen2-VL-7B-Instruct",
   "display_name": "Qwen2-VL 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen2-vl-7b-instruct"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    }
   ],
   "docs_url": "https://nebius.com/prices-ai-studio",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2-vl-7b-instruct",
    "qwen2-vl-7b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2-VL 7B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2.5-32B-EVA-v0.2",
   "model_name": "Qwen2.5-32B-EVA-v0.2",
   "display_name": "Qwen 2.5 32b EVA",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.493"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.493"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-09-01",
   "max_input_tokens": 24576,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 32b EVA"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2.5-32B-Instruct-abliterated",
   "model_name": "Qwen2.5-32B-Instruct-abliterated",
   "display_name": "Qwen 2.5 32B Abliterated",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "huihui-ai/Qwen2.5-32B-Instruct-abliterated"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-01-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "huihui-ai/Qwen2.5-32B-Instruct-abliterated"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 32B Abliterated"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2.5-72B",
   "model_name": "Qwen2.5-72B",
   "display_name": "Qwen2.5-72B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-72B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-72B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2.5-72B-Instruct-128K",
   "model_name": "Qwen2.5-72B-Instruct-128K",
   "display_name": "Qwen/Qwen2.5-72B-Instruct-128K",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct-128K"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.607353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.607353"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct-128K"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct-128K"
    }
   ],
   "released_at": "2024-09-18",
   "max_input_tokens": 131000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-72B-Instruct-128K"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5-72B-Instruct 是阿里云最新大语言模型系列的一部分。该 72B 模型在编程和数学方面表现更强，支持最多 128K 输入和超过 8K 输出，覆盖 29 种以上语言，并在指令理解和结构化输出（尤其是 JSON）方面有显著提升。",
    "zh-TW": "Qwen2.5-72B-Instruct 是阿里雲最新 LLM 系列的一部分。此 72B 模型提升了程式碼與數學能力，支援最多 128K 輸入與超過 8K 輸出，涵蓋 29+ 種語言，並強化指令遵循與結構化輸出（特別是 JSON）。",
    "ja-JP": "Qwen2.5-72B-Instruct は、Alibaba Cloud の最新 LLM シリーズの一部です。72B モデルはコーディングと数学を改善し、最大 128K の入力と 8K を超える出力をサポートし、29 以上の言語に対応、命令追従と構造化出力（特に JSON）を強化しています。",
    "ru-RU": "Qwen2.5-72B-Instruct — часть последней серии LLM от Alibaba Cloud. Модель с 72 млрд параметров улучшает программирование и математику, поддерживает до 128K входных и более 8K выходных токенов, предлагает поддержку 29+ языков и улучшает выполнение инструкций и структурированный вывод (особенно JSON)."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen2.5-72B-Instruct-128K"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2.5-72B-Instruct-Turbo",
   "model_name": "Qwen2.5-72B-Instruct-Turbo",
   "display_name": "Qwen2.5 72B Instruct Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-72B-Instruct-Turbo"
    }
   ],
   "released_at": "2024-10-11",
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-72B-Instruct-Turbo"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5 是一个专为指令类任务优化的大语言模型系列。",
    "zh-TW": "Qwen2.5 是一個針對指令型任務優化的新 LLM 系列。",
    "ja-JP": "Qwen2.5 は、命令スタイルのタスクに最適化された新しい LLM ファミリーです。",
    "ru-RU": "Qwen2.5 — новое семейство LLM, оптимизированное для задач в стиле инструкций."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 72B Instruct Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2.5-7B-Instruct-Turbo",
   "model_name": "Qwen2.5-7B-Instruct-Turbo",
   "display_name": "Qwen 2.5 7B Instruct Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-7B-Instruct-Turbo"
    }
   ],
   "intro": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
   "released_at": "2024-09-19",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-7B-Instruct-Turbo"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5 是一个专为指令类任务优化的大语言模型系列。",
    "zh-TW": "Qwen2.5 是一個針對指令型任務優化的新 LLM 系列。",
    "ja-JP": "Qwen2.5 は、命令スタイルのタスクに最適化された新しい LLM ファミリーです。",
    "ru-RU": "Qwen2.5 — новое семейство LLM, оптимизированное для задач в стиле инструкций."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 2.5 7B Instruct Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2.5-coder-1.5b-instruct",
   "model_name": "qwen2.5-coder-1.5b-instruct",
   "display_name": "Qwen2.5 Coder 1.5B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "开源 Qwen 编程模型。",
    "zh-TW": "開源 Qwen 程式碼模型。",
    "ja-JP": "オープンソースのQwenコードモデルです。",
    "ru-RU": "Открытая модель кода Qwen."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 Coder 1.5B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2.5-Coder-3B-Instruct",
   "model_name": "Qwen2.5-Coder-3B-Instruct",
   "display_name": "Qwen/Qwen2.5-Coder-3B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-Coder-3B-Instruct"
    }
   ],
   "released_at": "2024-11-06",
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-Coder-3B-Instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen2.5-Coder-3B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2.5-Coder-7B-fast",
   "model_name": "Qwen2.5-Coder-7B-fast",
   "display_name": "Qwen2.5 Coder 7B fast",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "qwen2.5-coder-7b-fast"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-Coder-7B-fast"
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2024-09-15",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 32000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-Coder-7B-fast",
    "qwen2.5-coder-7b-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 Coder 7B fast"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen2.5-VL-72B-Instruct-TEE",
   "model_name": "Qwen2.5-VL-72B-Instruct-TEE",
   "display_name": "Qwen2.5 VL 72B Instruct TEE",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen2.5-VL-72B-Instruct-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen2.5-VL-72B-Instruct-TEE"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 VL 72B Instruct TEE"
    }
   ]
  },
  {
   "slug": "alibaba/qwen25-coder-32b-instruct",
   "model_name": "qwen25-coder-32b-instruct",
   "display_name": "qwen25-coder-32b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen25-coder-32b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen25-vl-72b-instruct",
   "model_name": "qwen25-vl-72b-instruct",
   "display_name": "Qwen25 VL 72b",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.69989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.69989"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-10",
   "max_input_tokens": 32000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen25 VL 72b"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-0p5b-instruct",
   "model_name": "qwen2p5-0p5b-instruct",
   "display_name": "Qwen2.5 0.5B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-0p5b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-0p5b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 0.5B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-14b",
   "model_name": "qwen2p5-14b",
   "display_name": "Qwen2.5 14B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-14b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-14b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 14B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-1p5b-instruct",
   "model_name": "qwen2p5-1p5b-instruct",
   "display_name": "Qwen2.5 1.5B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-1p5b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-1p5b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 1.5B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-32b",
   "model_name": "qwen2p5-32b",
   "display_name": "Qwen2.5 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-32b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-32b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 32B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-32b-instruct",
   "model_name": "qwen2p5-32b-instruct",
   "display_name": "Qwen2.5 32B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-32b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-32b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 32B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-72b",
   "model_name": "qwen2p5-72b",
   "display_name": "Qwen2.5 72B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-72b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-72b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 72B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-72b-instruct",
   "model_name": "qwen2p5-72b-instruct",
   "display_name": "Qwen2.5 72B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-72b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-72b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-72b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5 是由 Qwen 团队与阿里云联合开发的仅解码器大语言模型系列，提供 0.5B、1.5B、3B、7B、14B、32B 和 72B 参数规模，涵盖基础模型与指令微调版本。",
    "zh-TW": "Qwen2.5 是由 Qwen 團隊與阿里雲開發的僅解碼式大型語言模型系列，提供 0.5B、1.5B、3B、7B、14B、32B 與 72B 等多種規模，涵蓋基礎與指令微調版本。",
    "ja-JP": "Qwen2.5は、QwenチームとAlibaba Cloudによって開発されたデコーダ専用のLLMシリーズで、0.5B、1.5B、3B、7B、14B、32B、72Bのサイズがあり、ベースモデルと命令調整済みモデルの両方が提供されています。",
    "ru-RU": "Qwen2.5 — это серия LLM только с декодером, разработанная командой Qwen и Alibaba Cloud, доступная в вариантах 0.5B, 1.5B, 3B, 7B, 14B, 32B и 72B, как в базовой, так и в дообученной на инструкциях версиях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 72B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-7b-instruct",
   "model_name": "qwen2p5-7b-instruct",
   "display_name": "Qwen2.5 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-7b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-7b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5 7B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-0p5b",
   "model_name": "qwen2p5-coder-0p5b",
   "display_name": "Qwen2.5-Coder 0.5B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-0p5b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-0p5b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 0.5B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-0p5b-instruct",
   "model_name": "qwen2p5-coder-0p5b-instruct",
   "display_name": "Qwen2.5-Coder 0.5B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-0p5b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-0p5b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 0.5B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-14b",
   "model_name": "qwen2p5-coder-14b",
   "display_name": "Qwen2.5-Coder 14B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-14b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-14b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 14B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-14b-instruct",
   "model_name": "qwen2p5-coder-14b-instruct",
   "display_name": "Qwen2.5-Coder 14B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-14b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-14b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 14B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-1p5b",
   "model_name": "qwen2p5-coder-1p5b",
   "display_name": "Qwen2.5-Coder 1.5B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-1p5b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-1p5b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 1.5B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-1p5b-instruct",
   "model_name": "qwen2p5-coder-1p5b-instruct",
   "display_name": "Qwen2.5-Coder 1.5B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-1p5b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-1p5b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 1.5B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-32b",
   "model_name": "qwen2p5-coder-32b",
   "display_name": "Qwen2.5-Coder 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-32b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-32b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 32B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-32b-instruct",
   "model_name": "qwen2p5-coder-32b-instruct",
   "display_name": "Qwen2.5-Coder-32B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-32b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-32b-instruct"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-32b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen2.5-Coder 是最新的 Qwen 编码大语言模型（前身为 CodeQwen）。注意：该模型目前作为无服务器模型实验性提供，Fireworks 可能会在短时间内终止部署，生产环境使用请注意。",
    "zh-TW": "Qwen2.5-Coder 是最新的 Qwen 程式語言模型（前身為 CodeQwen）。注意：此模型目前以無伺服器方式實驗性提供，Fireworks 可能會在短時間內終止部署，請注意生產環境使用風險。",
    "ja-JP": "Qwen2.5-Coderは、Qwenの最新のコード向けLLM（旧CodeQwen）です。注：このモデルは現在、サーバーレスモデルとして実験的に提供されています。商用利用を検討する場合、Fireworksが予告なく提供を終了する可能性がある点にご注意ください。",
    "ru-RU": "Qwen2.5-Coder — последняя модель LLM из серии Qwen, предназначенная для программирования (ранее CodeQwen). Примечание: модель предоставляется в экспериментальном режиме как серверлесс-решение. Для использования в продакшене учтите, что Fireworks может прекратить развертывание без предварительного уведомления."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder-32B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-32b-instruct-128k",
   "model_name": "qwen2p5-coder-32b-instruct-128k",
   "display_name": "Qwen2.5-Coder 32B Instruct 128K",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-32b-instruct-128k"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 32B Instruct 128K"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-32b-instruct-32k-rope",
   "model_name": "qwen2p5-coder-32b-instruct-32k-rope",
   "display_name": "Qwen2.5-Coder 32B Instruct 32K RoPE",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-32b-instruct-32k-rope"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 32B Instruct 32K RoPE"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-32b-instruct-64k",
   "model_name": "qwen2p5-coder-32b-instruct-64k",
   "display_name": "Qwen2.5-Coder 32B Instruct 64k",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k"
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-32b-instruct-64k"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 32B Instruct 64k"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-3b",
   "model_name": "qwen2p5-coder-3b",
   "display_name": "Qwen2.5-Coder 3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-3b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-3b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 3B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-3b-instruct",
   "model_name": "qwen2p5-coder-3b-instruct",
   "display_name": "Qwen2.5-Coder 3B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-3b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-3b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 3B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-7b",
   "model_name": "qwen2p5-coder-7b",
   "display_name": "Qwen2.5-Coder 7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-7b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 7B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-coder-7b-instruct",
   "model_name": "qwen2p5-coder-7b-instruct",
   "display_name": "Qwen2.5-Coder 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-coder-7b-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-coder-7b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Coder 7B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-math-72b-instruct",
   "model_name": "qwen2p5-math-72b-instruct",
   "display_name": "Qwen2.5-Math 72B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-math-72b-instruct"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-math-72b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-Math 72B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-vl-32b-instruct",
   "model_name": "qwen2p5-vl-32b-instruct",
   "display_name": "Qwen2.5-VL 32B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-vl-32b-instruct"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-vl-32b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-VL 32B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-vl-3b-instruct",
   "model_name": "qwen2p5-vl-3b-instruct",
   "display_name": "Qwen2.5-VL 3B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-vl-3b-instruct"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-vl-3b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-VL 3B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-vl-72b-instruct",
   "model_name": "qwen2p5-vl-72b-instruct",
   "display_name": "Qwen2.5-VL 72B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-vl-72b-instruct"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "intro": "Latest Qwen's VLM model",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-vl-72b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-VL 72B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen2p5-vl-7b-instruct",
   "model_name": "qwen2p5-vl-7b-instruct",
   "display_name": "Qwen2.5-VL 7B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen2p5-vl-7b-instruct"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen2p5-vl-7b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen2.5-VL 7B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3",
   "model_name": "qwen3",
   "display_name": "qwen3",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "qwen/qwen3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true
   },
   "released_at": "2026-07-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 是阿里巴巴推出的下一代大语言模型，在多种应用场景中表现出色。",
    "zh-TW": "Qwen3 是阿里巴巴新一代大型語言模型，在多種應用場景中展現出強大效能。",
    "ja-JP": "Qwen3は、Alibabaが開発した次世代の大規模言語モデルで、多様なユースケースにおいて高い性能を発揮します。",
    "ru-RU": "Qwen3 — это LLM нового поколения от Alibaba с высокой производительностью в различных сценариях использования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3_5-9B-MLX-4bit",
   "model_name": "Qwen3_5-9B-MLX-4bit",
   "display_name": "Qwen 3.5 9B (MLX 4-bit)",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "atomic-chat",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-03-05",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.5 9B (MLX 4-bit)"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3_5-9B-Q4_K_M",
   "model_name": "Qwen3_5-9B-Q4_K_M",
   "display_name": "Qwen 3.5 9B (Q4_K_M)",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "atomic-chat",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-03-05",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.5 9B (Q4_K_M)"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-0-6b",
   "model_name": "qwen3-0-6b",
   "display_name": "Qwen3 0.6B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "qwen3-0.6b"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.046"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.46"
      }
     },
     "provider_model_id": "qwen3-0.6b"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "qwen3-0.6b"
    }
   ],
   "released_at": "2025-04-28",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen3-0.6b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3是下一代同义Qwen模型，在推理、通用能力、代理能力和多语言性能方面取得了重大进展，并支持切换思维模式。",
    "zh-TW": "Qwen3 是下一代同意 Qwen 模型，在推理、通用能力、代理能力和多語言性能方面取得重大進展，並支持切換思考模式。",
    "ja-JP": "Qwen3は次世代のTongyi Qwenモデルで、推論、汎用能力、エージェント機能、多言語性能において大幅な向上を実現し、思考モードの切り替えをサポートします。",
    "ru-RU": "Qwen3 — это модель следующего поколения Tongyi Qwen с значительными улучшениями в рассуждении, общих способностях, агентных возможностях и многоязычной производительности, поддерживающая переключение режимов мышления."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 0.6B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-0p6b",
   "model_name": "qwen3-0p6b",
   "display_name": "Qwen3 0.6B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-0p6b"
    }
   ],
   "max_input_tokens": 40960,
   "max_output_tokens": 40960,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3-0p6b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 0.6B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-1-7b",
   "model_name": "qwen3-1-7b",
   "display_name": "Qwen3 1.7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "qwen3-1.7b"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.046"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.46"
      }
     },
     "provider_model_id": "qwen3-1.7b"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "qwen3-1.7b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    }
   ],
   "released_at": "2025-04-28",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen3-1.7b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3是下一代同义Qwen模型，在推理、通用能力、代理能力和多语言性能方面取得了重大进展，并支持切换思维模式。",
    "zh-TW": "Qwen3 是下一代同意 Qwen 模型，在推理、通用能力、代理能力和多語言性能方面取得重大進展，並支持切換思考模式。",
    "ja-JP": "Qwen3は次世代のTongyi Qwenモデルで、推論、汎用能力、エージェント機能、多言語性能において大幅な向上を実現し、思考モードの切り替えをサポートします。",
    "ru-RU": "Qwen3 — это модель следующего поколения Tongyi Qwen с значительными улучшениями в рассуждении, общих способностях, агентных возможностях и многоязычной производительности, поддерживающая переключение режимов мышления."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 1.7B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-14b",
   "model_name": "qwen3-14b",
   "display_name": "Qwen3 14B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "4.2"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.43"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-14B"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.434"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      }
     }
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "Qwen/Qwen3-14B"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "Qwen3-14B"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "Qwen/Qwen3-14B"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-14b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-14B"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "qwen/qwen3-14b"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7356566"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7356566"
      }
     },
     "provider_model_id": "Qwen3-14B"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "qwen/qwen3-14b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "Qwen3-14B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "qwen/qwen3-14b"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "Qwen/Qwen3-14B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "Qwen/Qwen3-14B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "Qwen/Qwen3-14B"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-14B"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "qwen/qwen3-14b"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "docs_url": "https://nebius.com/prices-ai-studio",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 10.4,
    "coding_index": 13.8,
    "agentic_index": 1.8
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-14B",
    "Qwen3-14B",
    "accounts/fireworks/models/qwen3-14b",
    "deepinfra/Qwen/Qwen3-14B",
    "qwen/qwen3-14b",
    "qwen3-14b:free"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 是新一代通义千问模型，在推理能力、通用能力、智能体能力和多语言表现方面有重大提升，支持思维模式切换。",
    "zh-TW": "Qwen3 是新一代通義千問模型，在推理、通用能力、代理能力與多語言表現方面取得重大突破，並支援思維模式切換。",
    "ja-JP": "Qwen3は、次世代のTongyi Qwenモデルであり、推論能力、汎用性、エージェント機能、多言語対応において大幅な向上を実現しています。思考モードの切り替えにも対応しています。",
    "ru-RU": "Qwen3 — это модель нового поколения Tongyi Qwen с существенными улучшениями в области рассуждений, общей способности, агентных возможностей и многоязычной производительности. Поддерживает переключение режимов мышления."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.7360084",
     "new": "0.7356566"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.7360084",
     "new": "0.7356566"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.7365197",
     "new": "0.7360084"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.7365197",
     "new": "0.7360084"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.7372961",
     "new": "0.7365197"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.7372961",
     "new": "0.7365197"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.73744665",
     "new": "0.7372961"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.73744665",
     "new": "0.7372961"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.7371856",
     "new": "0.73744665"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.7371856",
     "new": "0.73744665"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.73589475",
     "new": "0.7371856"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.73589475",
     "new": "0.7371856"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.73593535",
     "new": "0.73589475"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.73593535",
     "new": "0.73589475"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-14B-Instruct",
   "model_name": "Qwen3-14B-Instruct",
   "display_name": "Qwen3 14B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "OpenPipe/Qwen3-14B-Instruct"
    }
   ],
   "intro": "An efficient multilingual, dense, instruction-tuned model, optimized by OpenPipe for building agents with finetuning.",
   "released_at": "2025-04-29",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "OpenPipe/Qwen3-14B-Instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenPipe Qwen3 14B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-1p7b",
   "model_name": "qwen3-1p7b",
   "display_name": "Qwen3 1.7B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-1p7b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3-1p7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 1.7B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-1p7b-fp8-draft",
   "model_name": "qwen3-1p7b-fp8-draft",
   "display_name": "qwen3-1p7b-fp8-draft",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-1p7b-fp8-draft"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-1p7b-fp8-draft-131072",
   "model_name": "qwen3-1p7b-fp8-draft-131072",
   "display_name": "qwen3-1p7b-fp8-draft-131072",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-1p7b-fp8-draft-131072"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-1p7b-fp8-draft-40960",
   "model_name": "qwen3-1p7b-fp8-draft-40960",
   "display_name": "qwen3-1p7b-fp8-draft-40960",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 40960,
   "max_output_tokens": 40960,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-1p7b-fp8-draft-40960"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-235B",
   "model_name": "Qwen3-235B",
   "display_name": "Qwen3-235B-A22B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-235b"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2024-12-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen3-235b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-235B-A22B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-235b-2507-cs",
   "model_name": "qwen3-235b-2507-cs",
   "display_name": "qwen3-235b-2507-cs",
   "vendor": "alibaba",
   "pricing": [],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-08-06",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cerebras/qwen3-235b-2507-cs"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-235b-2507-cs"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-235b-a22b",
   "model_name": "qwen3-235b-a22b",
   "display_name": "Qwen3 235B-A22B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "8.4"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.86"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.147"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.868"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.71"
      }
     }
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.54"
      }
     },
     "provider_model_id": "Qwen3-235B-A22B"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.071"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-235b-a22b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "Qwen3-235B-A22B"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.455"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.82"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen3-235B-A22B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.455"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.82"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15942"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-235B-A22B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.42"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B"
    }
   ],
   "intro": "Large open Qwen MoE for multilingual reasoning, coding, and tool use",
   "released_at": "2025-04",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "docs_url": "https://nebius.com/prices-ai-studio",
   "deprecated": true,
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-235B-A22B",
    "Qwen3-235B-A22B",
    "accounts/fireworks/models/qwen3-235b-a22b",
    "deepinfra/Qwen/Qwen3-235B-A22B",
    "qwen/qwen3-235b-a22b",
    "qwen3-235b-a22b:free"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 235B A22B 是 Qwen3 的超大规模模型，提供顶级的 AI 能力。",
    "zh-TW": "Qwen3 235B A22B 是 Qwen3 超大規模模型，提供頂級 AI 能力。",
    "ja-JP": "Qwen3 235B A22Bは、トップクラスのAI能力を提供するQwen3の超大規模モデルです。",
    "ru-RU": "Qwen3 235B A22B — это ультрамасштабная модель Qwen3, обеспечивающая первоклассные возможности ИИ."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-235b-a22b-07-25",
   "model_name": "qwen3-235b-a22b-07-25",
   "display_name": "Qwen3 235B A22B Instruct 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-07-25"
    }
   ],
   "released_at": "2025-04-28",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-235b-a22b-07-25"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 235B A22B Instruct 2507"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-235b-a22b-2507",
   "model_name": "qwen3-235b-a22b-2507",
   "display_name": "Qwen: Qwen3 235B A22B Instruct 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.06"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.04"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2266"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9064"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.91"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.16"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.16"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.37"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2266"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9064"
      }
     },
     "provider_model_id": "qwen.qwen3-235b-a22b-2507"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.071"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-2507"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-2507"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.056"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-2507"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 52429,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-04",
   "family": "qwen",
   "model_type": "text_generation",
   "docs_url": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen.qwen3-235b-a22b-2507",
    "qwen.qwen3-235b-a22b-2507-v1:0",
    "qwen/qwen3-235b-a22b-2507"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-235B-A22B-Instruct-2507 是 Qwen3 系列的 Instruct 版本，兼顾多语言指令使用与长上下文场景。",
    "zh-TW": "Qwen3-235B-A22B-Instruct-2507 是 Qwen3 系列中的 Instruct 變體，兼顧多語指令使用與長上下文場景。",
    "ja-JP": "Qwen3-235B-A22B-Instruct-2507は、Qwen3シリーズのInstructバリアントで、多言語指示対応と長文コンテキスト処理のバランスに優れています。",
    "ru-RU": "Qwen3-235B-A22B-Instruct-2507 — вариант серии Qwen3, оптимизированный для многоязычного использования инструкций и сценариев с длинным контекстом."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen: Qwen3 235B A22B Instruct 2507"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-235b-a22b-fp8",
   "model_name": "qwen3-235b-a22b-fp8",
   "display_name": "Qwen3 235B A22B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-fp8"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-fp8"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-fp8"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "novita/qwen/qwen3-235b-a22b-fp8"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-29",
   "max_input_tokens": 40960,
   "max_output_tokens": 20000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "family": "qwen",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "novita/qwen/qwen3-235b-a22b-fp8",
    "qwen/qwen3-235b-a22b-fp8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 235B A22B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-235B-A22B-fp8-tput",
   "model_name": "Qwen3-235B-A22B-fp8-tput",
   "display_name": "Qwen3-235B-A22B-fp8-tput",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "docs_url": "https://www.together.ai/models/qwen3-235b-a22b-fp8-tput",
   "max_input_tokens": 40000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-235B-A22B-fp8-tput"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-235b-a22b-instruct",
   "model_name": "qwen3-235b-a22b-instruct",
   "display_name": "Qwen3-235B-A22B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-07-01",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 256000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-235B-A22B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-235B-A22B-Instruct-2507",
   "model_name": "Qwen3-235B-A22B-Instruct-2507",
   "display_name": "Qwen3 235B A22B Instruct 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.143"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.92"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.062"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "friendli",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "modelscope",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15942"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.071"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "8.4"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "submodel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "hf:Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.071"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.463"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-instruct-2507"
    }
   ],
   "released_at": "2025-07-22",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true,
    "open_weights": true,
    "prompt_caching": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "intro": "Tool-capable chat model for instruction following and agentic application workflows",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "knowledge_cutoff": "2025-04",
   "deprecated": true,
   "status": "deprecated",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-235B-A22B-Instruct-2507",
    "accounts/fireworks/models/qwen3-235b-a22b-instruct-2507",
    "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507",
    "hf:Qwen/Qwen3-235B-A22B-Instruct-2507",
    "nebius/qwen/qwen3-235b-a22b-instruct-2507",
    "qwen/Qwen3-235B-A22B-Instruct-2507",
    "qwen/qwen3-235b-a22b-instruct-2507",
    "qwen3-235b-a22b-instruct-2507"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 235B A22B Instruct 2507 是一款旗舰级指令模型，适用于广泛的生成与推理任务。",
    "zh-TW": "Qwen3 235B A22B Instruct 2507 是一款旗艦級指令模型，支援多樣生成與推理任務。",
    "ja-JP": "Qwen3 235B A22B Instruct 2507は、幅広い生成および推論タスクに対応するフラッグシップの指示モデルです。",
    "ru-RU": "Qwen3 235B A22B Instruct 2507 — флагманская инструкционная модель для широкого спектра задач генерации и рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4745922",
     "new": "1.4730394"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.36864805",
     "new": "0.36825985"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4748933",
     "new": "1.4745922"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.368723325",
     "new": "0.36864805"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4743712",
     "new": "1.4748933"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.3685928",
     "new": "0.368723325"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4717895",
     "new": "1.4743712"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.367947375",
     "new": "0.3685928"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 235B A22B Instruct 2507"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-235B-A22B-Instruct-2507-FP8",
   "model_name": "Qwen3-235B-A22B-Instruct-2507-FP8",
   "display_name": "Qwen3-235B-A22B-Instruct-2507-FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 235B A22B Instruct 2507 通过 MoE 架构优化推理效率，专为高级推理与指令跟随任务设计。",
    "zh-TW": "Qwen3 235B A22B Instruct 2507 針對高階推理與指令遵循進行最佳化，採用 MoE 架構以在大規模下保持推理效率。",
    "ja-JP": "Qwen3 235B A22B Instruct 2507は、高度な推論と指示追従に最適化されており、MoE（Mixture of Experts）を活用して大規模でも効率的な推論を実現します。",
    "ru-RU": "Qwen3 235B A22B Instruct 2507 оптимизирована для продвинутого логического рассуждения и следования инструкциям, использует архитектуру MoE для эффективного масштабирования рассуждений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-235B-A22B-Instruct-2507-FP8"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-235b-a22b-instruct-2507-maas",
   "model_name": "qwen3-235b-a22b-instruct-2507-maas",
   "display_name": "Qwen3 235B A22B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-instruct-2507-maas",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-instruct-2507-maas",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-instruct-2507-maas",
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-08-13",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-235b-a22b-instruct-2507-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 235B A22B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-235B-A22B-Instruct-2507-TEE",
   "model_name": "Qwen3-235B-A22B-Instruct-2507-TEE",
   "display_name": "Qwen 3 235b A22B 2507 (TEE)",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/Qwen3-235B-A22B-Instruct-2507-TEE"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-07-25",
   "max_input_tokens": 256000,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-235B-A22B-Instruct-2507-TEE",
    "qwen/Qwen3-235B-A22B-Instruct-2507-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3 235b A22B 2507 (TEE)"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-235B-A22B-Instruct-2507-tput",
   "model_name": "Qwen3-235B-A22B-Instruct-2507-tput",
   "display_name": "Qwen3 235B A22B Instruct 2507 FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+litellm+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Instruct-2507-tput"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-07-25",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://www.together.ai/models/qwen3-235b-a22b-instruct-2507-fp8",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-235B-A22B-Instruct-2507-tput"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 235B A22B Instruct 2507 FP8"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-235b-a22b-thinking",
   "model_name": "qwen3-235b-a22b-thinking",
   "display_name": "Qwen3 235B A22B Thinking 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.9000000000000004"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "alibaba/qwen3-235b-a22b-thinking"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-09-23",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "reasoning_config": {
    "budget_min": 1
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen3-235b-a22b-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 235B A22B Thinking 2507"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-235B-A22B-Thinking-2507",
   "model_name": "Qwen3-235B-A22B-Thinking-2507",
   "display_name": "Qwen3 235B A22B Thinking 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.86"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.055"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "modelscope",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1495"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.495"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.89855"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "submodel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "hf:Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.39"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     },
     "provider_model_id": "qwen3-235b-a22b-thinking-2507"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.78"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.056"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "qwen/qwen3-235b-a22b-thinking-2507"
    }
   ],
   "released_at": "2025-07-25",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "open_weights": true,
    "prompt_caching": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "knowledge_cutoff": "2025-04",
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 128
   },
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507",
   "benchmarks": {
    "intelligence_index": 19.6,
    "coding_index": 22.1,
    "agentic_index": 3.8
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-235B-A22B-Thinking-2507",
    "accounts/fireworks/models/qwen3-235b-a22b-thinking-2507",
    "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507",
    "hf:Qwen/Qwen3-235B-A22B-Thinking-2507",
    "qwen/Qwen3-235B-A22B-Thinking-2507",
    "qwen/qwen3-235b-a22b-thinking-2507",
    "qwen3-235b-a22b-thinking-2507"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-235B-A22B-Thinking-2507 是 Qwen3 的思考版本，专为复杂数学与推理任务强化。",
    "zh-TW": "Qwen3-235B-A22B-Thinking-2507 是 Qwen3 的 Thinking 變體，強化數學與複雜推理能力。",
    "ja-JP": "Qwen3-235B-A22B-Thinking-2507は、Qwen3のThinkingバリアントで、複雑な数学や推論タスクに強化されています。",
    "ru-RU": "Qwen3-235B-A22B-Thinking-2507 — вариант модели Qwen3, усиленный для выполнения сложных математических и логических задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 235B A22B Thinking 2507"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-235B-A22B-Thinking-2507-fast",
   "model_name": "Qwen3-235B-A22B-Thinking-2507-fast",
   "display_name": "Qwen3-235B-A22B-Thinking-2507-fast",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507-fast"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-07-25",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 8000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-235B-A22B-Thinking-2507-fast"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-235B-A22B-Thinking-2507-fast"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-235B-A22B-Thinking-2507-TEE",
   "model_name": "Qwen3-235B-A22B-Thinking-2507-TEE",
   "display_name": "Qwen3 235B A22B Thinking 2507 TEE",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1957"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14945"
      }
     },
     "provider_model_id": "Qwen/Qwen3-235B-A22B-Thinking-2507-TEE"
    }
   ],
   "intro": "Qwen reasoning model for deliberate problem solving, math, and coding",
   "released_at": "2025-07",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-235B-A22B-Thinking-2507-TEE"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 235B A22B Thinking 2507 TEE"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-30B-A3B",
   "model_name": "Qwen3-30B-A3B",
   "display_name": "Qwen3 30B A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.102941"
      }
     },
     "provider_model_id": "qwen3-30b-a3b"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.08"
      }
     },
     "provider_model_id": "qwen3-30b-a3b"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.108"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.431"
      }
     },
     "provider_model_id": "qwen3-30b-a3b"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.63"
      }
     },
     "provider_model_id": "qwen3-30b-a3b"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "qwen3-30b-a3b"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "qwen3-30b-a3b"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.323529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.279412"
      }
     },
     "provider_model_id": "qwen3-30b-a3b"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1175"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.136"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0588"
      }
     },
     "provider_model_id": "qwen3-30b-a3b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1087"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43478"
      }
     },
     "provider_model_id": "qwen3-30b-a3b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-30B-A3B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "qwen3-30b-a3b"
    }
   ],
   "released_at": "2025-04-28",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true,
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2025-04",
   "family": "qwen",
   "docs_url": "https://nebius.com/prices-ai-studio",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-30B-A3B",
    "accounts/fireworks/models/qwen3-30b-a3b",
    "deepinfra/Qwen/Qwen3-30B-A3B",
    "qwen/qwen3-30b-a3b",
    "qwen3-30b-a3b",
    "qwen3-30b-a3b:free"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 是最新一代 Qwen 大语言模型，采用稠密与 MoE 架构，擅长推理、多语言支持和高级智能体任务。其独特的“思考模式”与“非思考模式”切换能力，确保在多场景下实现高质量表现。\n\nQwen3 显著超越 QwQ 和 Qwen2.5 等前代模型，在数学、编程、常识推理、创意写作和交互对话方面表现卓越。Qwen3-30B-A3B 版本拥有 30.5B 参数（3.3B 激活），48 层，128 个专家（每任务激活 8 个），支持使用 YaRN 扩展至 131K 上下文，树立开源模型新标杆。",
    "zh-TW": "Qwen3 是最新一代的 Qwen 大型語言模型，採用密集與 MoE 架構，擅長推理、多語言支援與進階代理任務。其獨特的能力可在複雜推理的「思考模式」與高效對話的「非思考模式」間切換，確保多元且高品質的表現。\n\nQwen3 在數學、程式碼、常識推理、創意寫作與互動對話方面，表現遠超前代模型如 QwQ 與 Qwen2.5。Qwen3-30B-A3B 版本擁有 305 億參數（其中 3.3 億為活躍參數）、48 層、128 位專家（每次任務啟用 8 位），並透過 YaRN 支援最高 131K 的上下文長度，為開源模型樹立新標竿。",
    "ja-JP": "Qwen3は、密結合およびMoEアーキテクチャを採用した最新のQwen LLMで、推論、多言語対応、高度なエージェントタスクに優れています。思考モードと非思考モードを切り替える独自機能により、柔軟かつ高品質なパフォーマンスを実現します。\n\nQwen3は、QwQやQwen2.5などの従来モデルを大きく上回り、数学、コーディング、常識推論、創造的な文章生成、対話において優れた性能を発揮します。Qwen3-30B-A3Bバリアントは30.5Bパラメータ（3.3Bアクティブ）、48層、128エキスパート（1タスクあたり8アクティブ）を持ち、YaRNにより最大131Kのコンテキストに対応します。",
    "ru-RU": "Qwen3 — новейшее поколение LLM-моделей Qwen с плотной и MoE-архитектурами, превосходящее в логике, многоязычии и агентных задачах. Уникальная возможность переключения между режимом мышления и обычным режимом общения обеспечивает универсальную и высококачественную работу.\n\nQwen3 значительно превосходит предыдущие модели, такие как QwQ и Qwen2.5, демонстрируя отличные результаты в математике, программировании, логике, креативном письме и интерактивных диалогах. Вариант Qwen3-30B-A3B содержит 30,5 миллиарда параметров (3,3 миллиарда активных), 48 слоев, 128 экспертов (8 активных на задачу) и поддерживает контекст до 131K с помощью YaRN, устанавливая новый стандарт среди открытых моделей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 30B A3B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-30b-a3b-2507",
   "model_name": "qwen3-30b-a3b-2507",
   "display_name": "Qwen3 30B A3B 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "lmstudio",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b-2507"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-07-30",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-30b-a3b-2507"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 30B A3B 2507"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-30b-a3b-fp8",
   "model_name": "qwen3-30b-a3b-fp8",
   "display_name": "Qwen3 30B A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.051"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0509"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.335"
      }
     },
     "provider_model_id": "@cf/qwen/qwen3-30b-a3b-fp8"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b-fp8"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b-fp8"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b-fp8"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-29",
   "max_input_tokens": 40960,
   "max_output_tokens": 20000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "family": "qwen",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/qwen/qwen3-30b-a3b-fp8",
    "qwen/qwen3-30b-a3b-fp8",
    "workers-ai/@cf/qwen/qwen3-30b-a3b-fp8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 30B A3B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-30B-A3B-Instruct-2507",
   "model_name": "Qwen3-30B-A3B-Instruct-2507",
   "display_name": "Qwen3 30B A3B Instruct 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.017647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.070588"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.108"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.431"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507"
    },
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.089"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.268"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102991924"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411967696"
      }
     }
    },
    {
     "provider": "modelscope",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04815"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19305"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1087"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43478"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "alibaba/qwen3-30b-a3b-instruct-2507"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411765"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-instruct-2507"
    }
   ],
   "released_at": "2025-07-29",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true,
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "Tool-capable chat model for instruction following and agentic application workflows",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2025-12",
   "family": "qwen",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-30B-A3B-Instruct-2507",
    "TEE/qwen3-30b-a3b-instruct-2507",
    "accounts/fireworks/models/qwen3-30b-a3b-instruct-2507",
    "alibaba/qwen3-30b-a3b-instruct-2507",
    "nebius/qwen/qwen3-30b-a3b-instruct-2507",
    "qwen/qwen3-30b-a3b-instruct-2507",
    "qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507",
    "qwen3-30b-a3b-instruct-2507"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-30B-A3B-Instruct-2507 是 Qwen3-30B-A3B 的更新版非推理模型。它采用具有 305 亿总参数和 33 亿激活参数的 MoE 架构，在指令遵循、逻辑推理、文本理解、数学、科学、编程和工具使用等方面显著提升，扩展了多语言长尾知识，并在主观开放任务上更好地符合用户偏好。支持 256K 上下文窗口。此模型仅限非推理模式，不会输出 `נקוד` 标签。",
    "zh-TW": "Qwen3-30B-A3B-Instruct-2507 是 Qwen3-30B-A3B 的更新版非思考模型。它是一個具有 305 億總參數和 33 億活躍參數的 MoE 模型。顯著提升了指令跟隨、邏輯推理、文本理解、數學、科學、編程和工具使用能力，擴展了多語言長尾知識，並更好地符合用戶對主觀開放任務的偏好。支持 256K 上下文。此模型僅限非思考模式，不會輸出 `נקוד` 標籤。",
    "ja-JP": "Qwen3-30B-A3B-Instruct-2507はQwen3-30B-A3Bの更新版で、非思考型バージョンです。30.5Bの総パラメータと3.3Bのアクティブパラメータを持つMoEモデルで、指示追従、論理的推論、テキスト理解、数学、科学、コーディング、ツール使用を大幅に改善し、多言語のロングテール知識を拡張し、主観的なオープンタスクでのユーザーの好みにより良く一致します。256Kのコンテキストをサポートします。このモデルは非思考型であり、`נקוד`タグを出力しません。",
    "ru-RU": "Qwen3-30B-A3B-Instruct-2507 — это обновленная версия Qwen3-30B-A3B без способности к самостоятельному мышлению. Это модель MoE с общим количеством параметров 30,5 миллиарда и 3,3 миллиардами активных параметров. Она значительно улучшает выполнение инструкций, логическое мышление, понимание текста, математику, науку, программирование и использование инструментов, расширяет многоязычные знания и лучше соответствует предпочтениям пользователей в субъективных открытых задачах. Поддерживает контекст на 256 тысяч токенов. Эта модель не обладает способностью к самостоятельному мышлению и не будет выводить теги `נקוד`."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412164704",
     "new": "0.411967696"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103041176",
     "new": "0.102991924"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412451032",
     "new": "0.412164704"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103112758",
     "new": "0.103041176"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412885816",
     "new": "0.412451032"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103221454",
     "new": "0.103112758"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412970124",
     "new": "0.412885816"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103242531",
     "new": "0.103221454"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412823936",
     "new": "0.412970124"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103205984",
     "new": "0.103242531"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.41210106",
     "new": "0.412823936"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103025265",
     "new": "0.103205984"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 30B A3B Instruct 2507"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-30B-A3B-Instruct-2507-FP8",
   "model_name": "Qwen3-30B-A3B-Instruct-2507-FP8",
   "display_name": "Qwen3 30B 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "evroc",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.42"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507-FP8"
    }
   ],
   "released_at": "2025-07-30",
   "max_input_tokens": 64000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-30B-A3B-Instruct-2507-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 30B 2507"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-30B-A3B-Instruct-2507-Lora",
   "model_name": "Qwen3-30B-A3B-Instruct-2507-Lora",
   "display_name": "Qwen3-30B-A3B-Instruct-2507-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507-Lora"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-30B-A3B-Instruct-2507-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-30B-A3B-Instruct-2507-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-30B-A3B-Thinking-2507",
   "model_name": "Qwen3-30B-A3B-Thinking-2507",
   "display_name": "Qwen3 30B A3B Thinking 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.102941"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-thinking-2507"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-thinking-2507"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.017647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-thinking-2507"
    },
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-thinking-2507"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.051"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b-thinking-2507"
    },
    {
     "provider": "modelscope",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Thinking-2507"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Thinking-2507"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.56"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "qwen/qwen3-30b-a3b-thinking-2507"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1087"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.0869600000000001"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-thinking-2507"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen/Qwen3-30B-A3B-Thinking-2507"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.102941"
      }
     },
     "provider_model_id": "qwen3-30b-a3b-thinking-2507"
    }
   ],
   "released_at": "2025-07-30",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2025-04",
   "family": "qwen",
   "benchmarks": {
    "intelligence_index": 14.4,
    "coding_index": 12.1,
    "agentic_index": 1.8
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-30B-A3B-Thinking-2507",
    "accounts/fireworks/models/qwen3-30b-a3b-thinking-2507",
    "qwen/qwen3-30b-a3b-thinking-2507",
    "qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507",
    "qwen3-30b-a3b-thinking-2507"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 30B A3B Thinking 2507 是一款中大型思维模型，兼顾准确性与成本。",
    "zh-TW": "Qwen3 30B A3B Thinking 2507 是一款中大型思考模型，在準確性與成本間取得平衡。",
    "ja-JP": "Qwen3 30B A3B Thinking 2507は、精度とコストのバランスを取った中〜大規模の思考モデルです。",
    "ru-RU": "Qwen3 30B A3B Thinking 2507 — модель среднего размера для рассуждений, сочетающая точность и эффективность."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 30B A3B Thinking 2507"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-32b",
   "model_name": "qwen3-32b",
   "display_name": "Qwen3 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "8.4"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.86"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.147"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.868"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.73"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.618"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.93"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.73"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen.qwen3-32b-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.71"
      }
     }
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.618"
      }
     },
     "provider_model_id": "qwen.qwen3-32b"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.099"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+litellm+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "qwen/qwen3-32b"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-32b"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "qwen/qwen3-32b"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B"
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.426471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.705882"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "qwen/qwen3-32b"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "8.4"
      }
     }
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14713132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      }
     },
     "provider_model_id": "Qwen3-32B"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "qwen/qwen3-32b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "qwen/qwen3-32b"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "Qwen3-32B"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15942"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-32B"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen3-32B"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-32B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "intro": "Dense open Qwen model for self-hosted chat, reasoning, and coding",
   "released_at": "2025-04",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "status": "beta",
   "docs_url": "https://nebius.com/prices-ai-studio",
   "deprecated": true,
   "deprecation_date": "2026-04-06",
   "benchmarks": {
    "intelligence_index": 11.5,
    "coding_index": 15.3,
    "agentic_index": 1.8
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-32B",
    "Qwen3-32B",
    "accounts/fireworks/models/qwen3-32b",
    "deepinfra/Qwen/Qwen3-32B",
    "groq/qwen/qwen3-32b",
    "nebius/qwen/qwen3-32b",
    "qwen.qwen3-32b",
    "qwen.qwen3-32b-v1:0",
    "qwen/qwen3-32b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 是新一代通义千问模型，在推理能力、通用能力、智能体能力和多语言表现方面有重大提升，支持思维模式切换。",
    "zh-TW": "Qwen3 是新一代通義千問模型，在推理能力、通用能力、智能體能力與多語言表現方面有重大突破，並支援思考模式切換。",
    "ja-JP": "Qwen3は、次世代のTongyi Qwenモデルであり、推論能力、汎用性、エージェント機能、多言語対応において大幅な向上を実現しています。思考モードの切り替えにも対応しています。",
    "ru-RU": "Qwen3 — это модель нового поколения Tongyi Qwen с существенными улучшениями в области рассуждений, общей способности, агентных возможностей и многоязычной производительности. Поддерживает переключение режимов мышления."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14720168",
     "new": "0.14713132"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14730394",
     "new": "0.14720168"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14745922",
     "new": "0.14730394"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14748933",
     "new": "0.14745922"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14743712",
     "new": "0.14748933"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.1",
     "new": "0.08"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14717895",
     "new": "0.14743712"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58874828",
     "new": "0.5887158"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14718707",
     "new": "0.14717895"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-32b-cs",
   "model_name": "qwen3-32b-cs",
   "display_name": "qwen3-32b-cs",
   "vendor": "alibaba",
   "pricing": [],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-05-15",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cerebras/qwen3-32b-cs"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-32b-cs"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-32B-fast",
   "model_name": "Qwen3-32B-fast",
   "display_name": "Qwen3-32B (Fast)",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B-fast"
    }
   ],
   "released_at": "2026-01-28",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-32B-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-32B (Fast)"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-32b-fp8",
   "model_name": "qwen3-32b-fp8",
   "display_name": "Qwen3 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwen/qwen3-32b-fp8"
    },
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwen/qwen3-32b-fp8"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwen/qwen3-32b-fp8"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-29",
   "max_input_tokens": 40960,
   "max_output_tokens": 20000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "family": "qwen",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-32b-fp8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 32B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-32B-TEE",
   "model_name": "Qwen3-32B-TEE",
   "display_name": "Qwen3 32B TEE",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.104"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.416"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.052"
      }
     },
     "provider_model_id": "Qwen/Qwen3-32B-TEE"
    }
   ],
   "intro": "Dense open Qwen model for self-hosted chat, reasoning, and coding",
   "released_at": "2025-04",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 40960,
   "max_output_tokens": 40960,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-32B-TEE"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 32B TEE"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-4B",
   "model_name": "Qwen3-4B",
   "display_name": "Qwen3 4B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "qwen3-4b"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen3-4b"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.046"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.46"
      }
     },
     "provider_model_id": "qwen3-4b"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "qwen3-4b"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen3-4b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.273"
      }
     },
     "provider_model_id": "qwen/qwen3-4b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen3-4b:free"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "qwen3-4b"
    }
   ],
   "released_at": "2025-04-28",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true,
    "prompt_caching": true
   },
   "docs_url": "https://nebius.com/prices-ai-studio",
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2024-07",
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3-4b",
    "qwen/qwen3-4b",
    "qwen/qwen3-4b:free",
    "qwen3-4b",
    "qwen3-4b:free"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3是下一代同义Qwen模型，在推理、通用能力、代理能力和多语言性能方面取得了重大进展，并支持切换思维模式。",
    "zh-TW": "Qwen3 是下一代同意 Qwen 模型，在推理、通用能力、代理能力和多語言性能方面取得重大進展，並支持切換思考模式。",
    "ja-JP": "Qwen3は次世代のTongyi Qwenモデルで、推論、汎用能力、エージェント機能、多言語性能において大幅な向上を実現し、思考モードの切り替えをサポートします。",
    "ru-RU": "Qwen3 — это модель следующего поколения Tongyi Qwen с значительными улучшениями в рассуждении, общих способностях, агентных возможностях и многоязычной производительности, поддерживающая переключение режимов мышления."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 4B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-4b-fp8",
   "model_name": "qwen3-4b-fp8",
   "display_name": "Qwen3 4B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "qwen/qwen3-4b-fp8"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "qwen/qwen3-4b-fp8"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-29",
   "max_input_tokens": 128000,
   "max_output_tokens": 20000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "family": "qwen",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-4b-fp8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 4B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-4B-Instruct-2507",
   "model_name": "Qwen3-4B-Instruct-2507",
   "display_name": "Qwen 3 4B Instruct 2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen3-4b-instruct-2507"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "Qwen/Qwen3-4B-Instruct-2507"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-4B-Instruct-2507"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-08-05",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-4B-Instruct-2507",
    "accounts/fireworks/models/qwen3-4b-instruct-2507",
    "qwen3-4b-instruct-2507"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3 4B Instruct 2507"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-4B-Thinking-2507",
   "model_name": "Qwen3-4B-Thinking-2507",
   "display_name": "Qwen/Qwen3-4B-Thinking-2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "Qwen/Qwen3-4B-Thinking-2507"
    }
   ],
   "released_at": "2025-08-05",
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-4B-Thinking-2507"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-4B-Thinking-2507"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-5-9b",
   "model_name": "qwen3-5-9b",
   "display_name": "Qwen3.5-9B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "qwen3.5-9b"
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.008"
      }
     },
     "provider_model_id": "qwen3.5-9b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-9B"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-9B"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "qwen/qwen3.5-9b"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "qwen3.5-9b"
    },
    {
     "provider": "mixlayer",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen/qwen3.5-9b"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029426264"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.235410112"
      }
     },
     "provider_model_id": "Qwen3.5-9B"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "qwen/qwen3.5-9b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "qwen/qwen3.5-9b"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "qwen3.5-9b"
    },
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen3.5-9b"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-9B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-9B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.74"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-9B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-9B"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14999999999999997"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen/qwen3.5-9b"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-04",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "model_type": "deep_thinking",
   "benchmarks": {
    "intelligence_index": 21.4,
    "coding_index": 28.7,
    "agentic_index": 7.4
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-9B",
    "Qwen3.5-9B",
    "qwen/qwen3.5-9b",
    "qwen3.5-9b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.5-9B 是 Qwen 团队开发的原生多模态大语言模型，具有 90 亿参数。作为 Qwen3.5 系列中的轻量 Dense 模型，它采用结合门控增量网络和门控注意力的高效混合架构，原生支持 256K 上下文长度，并可扩展至约 100 万个 token。",
    "zh-TW": "Qwen3.5-9B 是 Qwen 團隊開發的原生多模態大型語言模型，擁有 90 億參數。作為 Qwen3.5 系列中的輕量 Dense 模型，它採用高效的混合架構，結合門控增量網絡和門控注意力，原生支持 256K 上下文長度，並可擴展至約 100 萬個標記。",
    "ja-JP": "Qwen3.5-9BはQwenチームによるネイティブなマルチモーダル大規模言語モデルで、総パラメータ数は90億です。Qwen3.5シリーズの軽量Denseモデルとして、効率的なハイブリッドアーキテクチャ（Gated Delta NetworksとGated Attentionの組み合わせ）を採用しています。256Kの文脈長をネイティブにサポートし、約100万トークンまで拡張可能です。",
    "ru-RU": "Qwen3.5-9B — это нативная мультимодальная крупная языковая модель от команды Qwen с 9 миллиардами параметров. Как легкая плотная модель в серии Qwen3.5, она использует эффективную гибридную архитектуру, объединяющую Gated Delta Networks и Gated Attention, нативно поддерживает длину контекста 256K с возможностью расширения до примерно 1 миллиона токенов."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.235522688",
     "new": "0.235410112"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.029440336",
     "new": "0.029426264"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.235686304",
     "new": "0.235522688"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.029460788",
     "new": "0.029440336"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.235934752",
     "new": "0.235686304"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.029491844",
     "new": "0.029460788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.235982928",
     "new": "0.235934752"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.029497866",
     "new": "0.029491844"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.235899392",
     "new": "0.235982928"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.029487424",
     "new": "0.029497866"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.2",
     "new": "0.15"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.04",
     "new": "0.1"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.23548632",
     "new": "0.235899392"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.02943579",
     "new": "0.029487424"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-9B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-6-35b",
   "model_name": "qwen3-6-35b",
   "display_name": "Qwen3.6 35B-A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "llmtr",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "llmtr/qwen3-6-35b"
    },
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0725"
      }
     },
     "provider_model_id": "qwen3.6-35b"
    }
   ],
   "intro": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
   "released_at": "2026-04-17",
   "max_input_tokens": 16384,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llmtr/qwen3-6-35b",
    "qwen3.6-35b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 35B-A3B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-8b",
   "model_name": "qwen3-8b",
   "display_name": "Qwen3 8B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.1"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-8B"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.717"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-8b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "Qwen/Qwen3-8B"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "qwen/qwen3-8b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.47"
      }
     },
     "provider_model_id": "qwen/Qwen3-8B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.455"
      }
     },
     "provider_model_id": "qwen/qwen3-8b"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-8B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "Qwen/Qwen3-8B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "Qwen/Qwen3-8B"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 8.3,
    "coding_index": 9,
    "agentic_index": 1.5
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.6,
     "top_p": 0.95,
     "top_k": 20
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-8B",
    "accounts/fireworks/models/qwen3-8b",
    "qwen/Qwen3-8B",
    "qwen/qwen3-8b",
    "qwen3-8b:free"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 是新一代通义千问模型，在推理能力、通用能力、智能体能力和多语言表现方面有重大提升，支持思维模式切换。",
    "zh-TW": "Qwen3 是新一代通義千問模型，在推理能力、通用能力、智能體能力與多語言表現方面有重大突破，並支援思考模式切換。",
    "ja-JP": "Qwen3は、次世代のTongyi Qwenモデルであり、推論能力、汎用性、エージェント機能、多言語対応において大幅な向上を実現しています。思考モードの切り替えにも対応しています。",
    "ru-RU": "Qwen3 — это модель нового поколения Tongyi Qwen с существенными улучшениями в области рассуждений, общей способности, агентных возможностей и многоязычной производительности. Поддерживает переключение режимов мышления."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-8b-fp8",
   "model_name": "qwen3-8b-fp8",
   "display_name": "Qwen3 8B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.138"
      }
     },
     "provider_model_id": "qwen/qwen3-8b-fp8"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.138"
      }
     },
     "provider_model_id": "qwen/qwen3-8b-fp8"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-29",
   "max_input_tokens": 128000,
   "max_output_tokens": 20000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-8b-fp8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 8B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-8B-Lora",
   "model_name": "Qwen3-8B-Lora",
   "display_name": "Qwen3-8B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-8B-Lora"
    }
   ],
   "max_input_tokens": 40960,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-8B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-8B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-asr-flash",
   "model_name": "qwen3-asr-flash",
   "display_name": "Qwen3-ASR Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.035"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.032"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.032"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.000035"
      }
     },
     "provider_model_id": "qwen/qwen3-asr-flash"
    }
   ],
   "intro": "Speech transcription model for accurate audio-to-text and captioning workflows",
   "released_at": "2025-09-08",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 53248,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-asr-flash"
   ],
   "model_type": "speech_recognition"
  },
  {
   "slug": "alibaba/qwen3-coder",
   "model_name": "qwen3-coder",
   "display_name": "Qwen3 Coder 480B A35B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.13"
      }
     }
    },
    {
     "provider": "canopywave",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      }
     },
     "provider_model_id": "qwen/qwen3-coder"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.099999999"
      }
     },
     "provider_model_id": "qwen/qwen3-coder"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen/qwen3-coder",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "qwen/qwen3-coder"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/qwen3-coder"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "qwen/qwen3-coder"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "alibaba/qwen3-coder",
     "tracks": [
      {
       "label": ">128.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3",
        "completion": "3",
        "cache_read": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128001,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "alibaba/qwen3-coder"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.01"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "qwen/qwen3-coder"
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2025-07-22",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://openrouter.ai/qwen/qwen3-coder",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen3-coder",
    "qwen/qwen3-coder",
    "qwen/qwen3-coder:exacto",
    "qwen/qwen3-coder:free",
    "qwen3-coder:free"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-Coder-480B-A35B-Instruct 是 Qwen 系列中最具智能体能力的代码模型，在智能体编程、浏览器操作等核心编程任务中表现强劲，达到 Claude Sonnet 水平。",
    "zh-TW": "Qwen3-Coder-480B-A35B-Instruct 是 Qwen 最具代理能力的程式模型，在代理式編碼、瀏覽器操作及其他核心編碼任務上表現優異，達到與 Claude Sonnet 同級的成果。",
    "ja-JP": "Qwen3-Coder-480B-A35B-Instructは、Qwenの最もエージェント指向のコードモデルであり、エージェントによるコーディング、ブラウザ操作、その他の主要なコーディングタスクにおいてClaude Sonnetレベルの性能を発揮します。",
    "ru-RU": "Qwen3-Coder-480B-A35B-Instruct — это самая агентно-ориентированная модель для программирования в серии Qwen, демонстрирующая высокие результаты в агентном кодировании, использовании браузера и других ключевых задачах программирования, сопоставимых с уровнем Claude Sonnet."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Coder 480B A35B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-coder-30b",
   "model_name": "qwen3-coder-30b",
   "display_name": "Qwen3 Coder 30B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "lmstudio",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-30b"
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2025-07-23",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-coder-30b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Coder 30B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-coder-30b-a3b",
   "model_name": "qwen3-coder-30b-a3b",
   "display_name": "Qwen 3 Coder 30B A3B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.73"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.618"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.93"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.73"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.29"
      }
     }
    },
    {
     "provider": "privatemode-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "alibaba/qwen3-coder-30b-a3b"
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2025-07-31",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen3-coder-30b-a3b",
    "qwen.qwen3-coder-30b-a3b-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3 Coder 30B A3B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-coder-30b-a3b-instruct",
   "model_name": "qwen3-coder-30b-a3b-instruct",
   "display_name": "Qwen3-Coder 30B-A3B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.330882"
      },
      "prompt_0_128_0_2": {
       "unit": "per_M_tokens",
       "price": "0.551471"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      },
      "completion_0_128_0_2": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.216"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     }
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-30b-a3b-instruct"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.618"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-30b-a3b-instruct"
    },
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11458"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.74812"
      }
     },
     "provider_model_id": "qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.053"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.222"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.013"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-coder-30b-a3b-instruct"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09999999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-30b-a3b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     }
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14713132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      }
     },
     "provider_model_id": "Qwen3-Coder-30B-A3B-Instruct"
    },
    {
     "provider": "modelscope",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-30b-a3b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-30b-a3b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-30b-a3b-instruct"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "Qwen3-Coder-30B-A3B-Instruct"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411765"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct"
    }
   ],
   "intro": "Smaller Qwen coder for efficient local agents and repo-level fixes",
   "released_at": "2025-04",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Coder-30B-A3B-Instruct",
    "Qwen3-Coder-30B-A3B-Instruct",
    "accounts/fireworks/models/qwen3-coder-30b-a3b-instruct",
    "qwen.qwen3-coder-30b-a3b-instruct",
    "qwen/qwen3-coder-30b-a3b-instruct",
    "qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-Coder-30B-A3B-Instruct 是 Qwen 团队推出的 Qwen3 系列代码模型。该模型在保持高性能和高效率的同时，显著增强了代码能力。在智能体编程、自动化浏览器操作和工具使用等开放模型中表现出色。原生支持 256K 上下文，并可扩展至 1M tokens，适用于代码库级理解。支持 Qwen Code 和 CLINE 等平台的智能体编程，采用专用函数调用格式。",
    "zh-TW": "Qwen3-Coder-30B-A3B-Instruct 是 Qwen 團隊推出的 Qwen3 程式模型。此模型在提升程式能力的同時，兼顧高效能與運行效率。其在智能體程式編寫、自動化瀏覽器操作與工具使用方面，在開源模型中表現出色。原生支援 256K 上下文，並可擴展至 1M token，適用於程式庫層級理解。支援 Qwen Code 與 CLINE 等平台上的智能體程式編寫，並採用專用函式呼叫格式。",
    "ja-JP": "Qwen3-Coder-30B-A3B-Instructは、QwenチームによるQwen3コードモデルです。高性能かつ効率的な設計で、コード生成能力を強化しています。エージェント型コーディング、自動ブラウザ操作、ツール使用においてオープンモデルの中でも優れた性能を発揮します。256Kのコンテキストをネイティブにサポートし、最大1Mトークンまで拡張可能で、コードベースレベルの理解に対応します。Qwen CodeやCLINEなどのプラットフォームで、関数呼び出し形式を用いたエージェント型コーディングを実現します。",
    "ru-RU": "Qwen3-Coder-30B-A3B-Instruct — это модель программирования серии Qwen3 от команды Qwen. Оптимизирована для высокой производительности и эффективности при работе с кодом. Демонстрирует сильные стороны в агентном программировании, автоматизации браузера и использовании инструментов среди открытых моделей. Нативно поддерживает контекст до 256K и может быть расширена до 1M токенов для понимания на уровне кодовой базы. Обеспечивает агентное программирование на платформах, таких как Qwen Code и CLINE, с использованием специального формата вызова функций."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14720168",
     "new": "0.14713132"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14730394",
     "new": "0.14720168"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14745922",
     "new": "0.14730394"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14748933",
     "new": "0.14745922"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14743712",
     "new": "0.14748933"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14717895",
     "new": "0.14743712"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58874828",
     "new": "0.5887158"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14718707",
     "new": "0.14717895"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-coder-480b-a35b",
   "model_name": "qwen3-coder-480b-a35b",
   "display_name": "Qwen3 Coder 480B A35B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.022727",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.18"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-v1:0",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.12"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-v1:0",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.87"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-v1:0",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-v1:0",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.79"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-v1:0",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.88"
      }
     }
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2025-09-18",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen.qwen3-coder-480b-a35b-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "Qwen3 Coder 480B A35B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-coder-480b-a35b-instruct",
   "model_name": "qwen3-coder-480b-a35b-instruct",
   "display_name": "Qwen3-Coder 480B-A35B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      },
      "prompt_0_128_0_2": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "5.294118"
      },
      "completion_0_128_0_2": {
       "unit": "per_M_tokens",
       "price": "8.823529"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.43"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Qwen/qwen3-coder-480b-a35b-instruct"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.82"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.29"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.861"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.441"
      }
     }
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.18"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-instruct",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.12"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-instruct",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.87"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-instruct",
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-instruct",
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.79"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-instruct",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-instruct",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-480b-a35b-instruct",
     "region": "us-west-2"
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.53"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.441"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.984"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "Qwen3-Coder-480B-A35B-Instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.225"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-coder-480b-a35b-instruct"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.294118"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-480b-a35b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     }
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-480b-a35b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.55"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-480b-a35b-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-480b-a35b-instruct"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86957"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.47826"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "hf:Qwen/Qwen3-Coder-480B-A35B-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "5.294118"
      }
     }
    }
   ],
   "intro": "Open Qwen coding heavyweight for repository reasoning and agentic engineering",
   "released_at": "2025-04",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Coder-480B-A35B-Instruct",
    "Qwen/qwen3-coder-480b-a35b-instruct",
    "Qwen3-Coder-480B-A35B-Instruct",
    "accounts/fireworks/models/qwen3-coder-480b-a35b-instruct",
    "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct",
    "hf:Qwen/Qwen3-Coder-480B-A35B-Instruct",
    "qwen.qwen3-coder-480b-a35b-instruct",
    "qwen/qwen3-coder-480b-a35b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 Coder 480B A35B Instruct 是一款旗舰级编程模型，支持多语言编程与复杂代码理解。",
    "zh-TW": "Qwen3 Coder 480B A35B Instruct 是一款旗艦級程式碼模型，支援多語言編程與複雜程式理解。",
    "ja-JP": "Qwen3 Coder 480B A35B Instructは、多言語プログラミングと複雑なコード理解に対応するフラッグシップのコードモデルです。",
    "ru-RU": "Qwen3 Coder 480B A35B Instruct — флагманская модель кода для многоязычного программирования и сложного понимания кода."
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.53902128",
     "new": "3.53529456"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.88475532",
     "new": "0.88382364"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.53974392",
     "new": "3.53902128"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.88493598",
     "new": "0.88475532"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.53849088",
     "new": "3.53974392"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.88462272",
     "new": "0.88493598"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.5322948",
     "new": "3.53849088"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.8830737",
     "new": "0.88462272"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35499312",
     "new": "3.5322948"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58874828",
     "new": "0.8830737"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Coder-480B-A35B-Instruct-FP8",
   "model_name": "Qwen3-Coder-480B-A35B-Instruct-FP8",
   "display_name": "Qwen3 Coder 480B A35B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "submodel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+litellm+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2025-08-23",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-04",
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Coder 480B A35B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Coder-480B-A35B-Instruct-FP8-TEE",
   "model_name": "Qwen3-Coder-480B-A35B-Instruct-FP8-TEE",
   "display_name": "Qwen3 Coder 480B A35B Instruct FP8 TEE",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Coder 480B A35B Instruct FP8 TEE"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar",
   "model_name": "Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar",
   "display_name": "Qwen 3 Coder 480B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     },
     "provider_model_id": "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar"
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2025-01-15",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 106000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3 Coder 480B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-coder-480b-a35b-instruct-maas",
   "model_name": "qwen3-coder-480b-a35b-instruct-maas",
   "display_name": "qwen3-coder-480b-a35b-instruct-maas",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-480b-a35b-instruct-maas",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-480b-a35b-instruct-maas",
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "text",
     "code"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-coder-480b-a35b-instruct-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-coder-480b-a35b-instruct-maas"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Coder-480B-A35B-Instruct-Turbo",
   "model_name": "Qwen3-Coder-480B-A35B-Instruct-Turbo",
   "display_name": "Qwen 3 Coder 480B Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+deepinfra+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "qwen3-coder-480b-a35b-instruct-turbo"
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2026-01-27",
   "max_input_tokens": 256000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-04",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo",
    "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo",
    "qwen3-coder-480b-a35b-instruct-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3 Coder 480B Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-coder-480b-instruct-bf16",
   "model_name": "qwen3-coder-480b-instruct-bf16",
   "display_name": "Qwen3 Coder 480B Instruct BF16",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-coder-480b-instruct-bf16"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3-coder-480b-instruct-bf16"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Coder 480B Instruct BF16"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-coder-flash",
   "model_name": "qwen3-coder-flash",
   "display_name": "Qwen3 Coder Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "cache_read_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "cache_read_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "cache_read_0_256_1": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      },
      "prompt_0_256_1": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion_0_256_1": {
       "unit": "per_M_tokens",
       "price": "3.676471"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      }
     },
     "provider_model_id": "qwen3-coder-flash-2025-07-28"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.136"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.544"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "qwen3-coder-flash-2025-07-28"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.195"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.975"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-flash"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-flash"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.195"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.975"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.039"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.24375"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-flash"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "alibaba/qwen3-coder-flash"
    }
   ],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2025-07-28",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen3-coder-flash",
    "qwen/qwen3-coder-flash",
    "qwen3-coder-flash-2025-07-28"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen 编程模型。最新的 Qwen3-Coder 系列基于 Qwen3，具备强大的编程代理能力、工具使用与环境交互能力，编程表现优异，通用能力扎实。",
    "zh-TW": "Qwen 程式碼模型。最新的 Qwen3-Coder 系列基於 Qwen3，具備強大的程式代理能力、工具使用與環境互動能力，支援自主編程，程式碼表現優異，通用能力穩健。",
    "ja-JP": "Qwenコードモデル。最新のQwen3-Coderシリーズは、Qwen3をベースにしており、自律的なプログラミングのための強力なコードエージェント機能、ツール使用、環境との対話を提供します。優れたコード性能と堅実な汎用能力を備えています。",
    "ru-RU": "Модель кода Qwen. Новейшая серия Qwen3-Coder основана на Qwen3 и обладает мощными возможностями кодирующего агента, использования инструментов и взаимодействия со средой для автономного программирования, с отличной производительностью кода и общей функциональностью."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Coder-Next",
   "model_name": "Qwen3-Coder-Next",
   "display_name": "Qwen3 Coder Next",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     },
     "provider_model_id": "qwen3-coder-next"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "qwen3-coder-next"
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-coder-next"
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-coder-next"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.515"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.236"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.78"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.515"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.236"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.78"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-coder-next",
     "region": "us-west-2"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-Next"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.158"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.84"
      }
     },
     "provider_model_id": "qwen3-coder-next"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-Next"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-next"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-next"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.108"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.675"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "qwen3-coder-next"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-next"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-next"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-next"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-next"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.202"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5152"
      }
     },
     "provider_model_id": "qwen3-coder-next"
    },
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen3-coder-next"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-next"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "alibaba/qwen3-coder-next"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2026-03-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "knowledge_cutoff": "2025-04",
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "benchmarks": {
    "intelligence_index": 21.1,
    "coding_index": 36.2,
    "agentic_index": 8.8
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Coder-Next",
    "alibaba/qwen3-coder-next",
    "qwen.qwen3-coder-next",
    "qwen/qwen3-coder-next",
    "qwen3-coder-next"
   ],
   "intro_i18n": {
    "zh-CN": "下一代Qwen编码器，优化用于复杂多文件代码生成、调试和高吞吐代理工作流。设计用于强大的工具集成和改进的推理性能。",
    "zh-TW": "下一代 Qwen 編碼器，針對複雜的多文件代碼生成、調試和高吞吐量代理工作流進行了優化。設計上強調工具集成和推理性能的提升。",
    "ja-JP": "次世代Qwenコーダーは、複雑なマルチファイルコード生成、デバッグ、高スループットエージェントワークフローに最適化されています。強力なツール統合と推論性能の向上を目指して設計されています。",
    "ru-RU": "Следующее поколение Qwen coder, оптимизированное для сложной генерации кода из нескольких файлов, отладки и высокопроизводительных рабочих процессов агентов. Разработано для сильной интеграции инструментов и улучшенной производительности рассуждений."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Coder Next"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Coder-Next-FP8",
   "model_name": "Qwen3-Coder-Next-FP8",
   "display_name": "Qwen3 Coder Next FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Coder-Next-FP8"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2026-02-03",
   "knowledge_cutoff": "2026-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Coder-Next-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Coder Next FP8"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-coder-plus",
   "model_name": "qwen3-coder-plus",
   "display_name": "Qwen3 Coder Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "cache_read_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "cache_read_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "cache_read_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "prompt_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "5.882353"
      },
      "completion_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "29.411765"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     },
     "provider_model_id": "qwen3-coder-plus-2025-07-22"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.108"
      }
     },
     "provider_model_id": "qwen3-coder-plus-2025-07-22"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.058"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.718"
      }
     },
     "provider_model_id": "qwen3-coder-plus-2025-07-22"
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-plus"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-plus"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.8125"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-plus"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "alibaba/qwen3-coder-plus"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "alibaba/qwen3-coder-plus",
     "tracks": [
      {
       "label": ">256.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "6",
        "completion": "12",
        "cache_read": "6"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256001,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">128.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3",
        "completion": "3",
        "cache_read": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128001,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "qwen/qwen3-coder-plus",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "12"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "6"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "3.6"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Hosted Qwen coder for software agents, repo edits, and long-context code",
   "released_at": "2025-07-23",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "docs_url": "https://openrouter.ai/qwen/qwen3-coder-plus",
   "parameters": {
    "supported": [
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen3-coder-plus",
    "qwen/qwen3-coder-plus",
    "qwen3-coder-plus-2025-07-22",
    "qwen3-coder-plus-2025-09-23"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-Coder-Plus 是 Qwen 系列的代码智能体模型，优化了复杂工具使用和长时间会话能力。",
    "zh-TW": "Qwen3-Coder-Plus 是 Qwen 系列中的程式代理模型，針對更複雜的工具使用與長時間工作流程進行最佳化。",
    "ja-JP": "Qwen3-Coder-Plusは、より複雑なツール利用と長時間セッションに最適化されたQwenシリーズのコーディングエージェントモデルです。",
    "ru-RU": "Qwen3-Coder-Plus — модель-агент для программирования из серии Qwen, оптимизированная для сложного использования инструментов и длительных сессий."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-coder:480b",
   "model_name": "qwen3-coder:480b",
   "display_name": "qwen3-coder:480b",
   "vendor": "alibaba",
   "pricing": [],
   "intro": "Qwen coding model for software agents, repository edits, and code reasoning",
   "released_at": "2025-07-22",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "阿里巴巴高性能长上下文模型，适用于代理与编程任务。",
    "zh-TW": "阿里巴巴推出的高效能長上下文模型，適用於代理與程式任務。",
    "ja-JP": "エージェントおよびコーディングタスク向けのAlibabaの高性能長文コンテキストモデルです。",
    "ru-RU": "Высокопроизводительная модель от Alibaba с длинным контекстом для задач агентов и программирования."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-coder:480b"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Embedding-0.6B",
   "model_name": "Qwen3-Embedding-0.6B",
   "display_name": "Qwen3 Embedding 0.6B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     },
     "provider_model_id": "qwen3-embedding-0.6b"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.012"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/qwen/qwen3-embedding-0.6b"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.012"
      }
     },
     "provider_model_id": "@cf/qwen/qwen3-embedding-0.6b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-0.6B"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-embedding-0.6b"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-0.6B"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-embedding-0.6b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Embedding-0.6B"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "alibaba/qwen3-embedding-0.6b"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2025-11-14",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "status": "beta",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/qwen/qwen3-embedding-0.6b",
    "Qwen/Qwen3-Embedding-0.6B",
    "alibaba/qwen3-embedding-0.6b",
    "deepinfra/Qwen/Qwen3-Embedding-0.6B",
    "qwen3-embedding-0.6b",
    "workers-ai/@cf/qwen/qwen3-embedding-0.6b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Embedding 0.6B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Embedding-0.6B-batch",
   "model_name": "Qwen3-Embedding-0.6B-batch",
   "display_name": "deepinfra/Qwen/Qwen3-Embedding-0.6B-batch",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-0.6B-batch"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Embedding-0.6B-batch"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true
   },
   "released_at": "2025-11-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Embedding-0.6B-batch",
    "deepinfra/Qwen/Qwen3-Embedding-0.6B-batch"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra/Qwen/Qwen3-Embedding-0.6B-batch"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-embedding-0p6b",
   "model_name": "qwen3-embedding-0p6b",
   "display_name": "Qwen3 Embedding 0.6B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-embedding-0p6b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_embedding",
   "capabilities": {
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3-embedding-0p6b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Embedding 0.6B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Embedding-4B",
   "model_name": "Qwen3-Embedding-4B",
   "display_name": "Qwen3 Embedding 4B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     },
     "provider_model_id": "qwen3-embedding-4b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-4B"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-embedding-4b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-4B"
    },
    {
     "provider": "inference",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen3-embedding-4b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "qwen/qwen3-embedding-4b"
    },
    {
     "provider": "privatemode-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-embedding-4b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Embedding-4B"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "alibaba/qwen3-embedding-4b"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2025-06-05",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-12",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Embedding-4B",
    "accounts/fireworks/models/qwen3-embedding-4b",
    "alibaba/qwen3-embedding-4b",
    "deepinfra/Qwen/Qwen3-Embedding-4B",
    "qwen/qwen3-embedding-4b",
    "qwen3-embedding-4b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Embedding 4B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Embedding-4B-batch",
   "model_name": "Qwen3-Embedding-4B-batch",
   "display_name": "deepinfra/Qwen/Qwen3-Embedding-4B-batch",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-4B-batch"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Embedding-4B-batch"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true
   },
   "released_at": "2025-11-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Embedding-4B-batch",
    "deepinfra/Qwen/Qwen3-Embedding-4B-batch"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra/Qwen/Qwen3-Embedding-4B-batch"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Embedding-8B",
   "model_name": "Qwen3-Embedding-8B",
   "display_name": "Qwen3-Embedding-8B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     },
     "provider_model_id": "qwen3-embedding-8b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-8B"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.115"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.115"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-8B"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-embedding-8b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-8B"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-8B"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-embedding-8b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "qwen/qwen3-embedding-8b"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    },
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen3-embedding-8b"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-embedding-8b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Embedding-8B"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "alibaba/qwen3-embedding-8b"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2026-02-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-12",
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Embedding-8B",
    "accounts/fireworks/models/qwen3-embedding-8b",
    "alibaba/qwen3-embedding-8b",
    "deepinfra/Qwen/Qwen3-Embedding-8B",
    "qwen/qwen3-embedding-8b",
    "qwen3-embedding-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-Embedding-8B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Embedding-8B-batch",
   "model_name": "Qwen3-Embedding-8B-batch",
   "display_name": "deepinfra/Qwen/Qwen3-Embedding-8B-batch",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Embedding-8B-batch"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Embedding-8B-batch"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true
   },
   "released_at": "2025-11-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Embedding-8B-batch",
    "deepinfra/Qwen/Qwen3-Embedding-8B-batch"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra/Qwen/Qwen3-Embedding-8B-batch"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-livetranslate-flash-realtime",
   "model_name": "qwen3-livetranslate-flash-realtime",
   "display_name": "Qwen3-LiveTranslate Flash Realtime",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "38"
      }
     }
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-09-22",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 53248,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "realtime_speech_translation"
  },
  {
   "slug": "alibaba/qwen3-max",
   "model_name": "qwen3-max",
   "display_name": "Qwen3 Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank+pricetoken",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "cache_read_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "cache_read_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.205882"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "prompt_0_128_0_252": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "completion_0_128_0_252": {
       "unit": "per_M_tokens",
       "price": "4.117647"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.43"
      }
     },
     "provider_model_id": "qwen3-max-2025-09-23"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.37"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09016"
      }
     },
     "provider_model_id": "qwen3-max-2026-01-23"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.861"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.441"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.036"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.448"
      }
     },
     "provider_model_id": "qwen3-max-2025-09-23"
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-max-2026-01-23"
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-max-2026-01-23"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.13"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Max",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-max"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.845"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.08018"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4009"
      }
     },
     "provider_model_id": "qwen/qwen3-max"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.45"
      }
     },
     "provider_model_id": "qwen/qwen3-max"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.45"
      }
     },
     "provider_model_id": "qwen/qwen3-max"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.78"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.156"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.975"
      }
     },
     "provider_model_id": "qwen/qwen3-max"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.359"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.434"
      }
     },
     "provider_model_id": "qwen/qwen3-max"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.0909"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5758"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86957"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.47826"
      }
     },
     "provider_model_id": "qwen3-max-2026-01-23"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.861"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.441"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "alibaba/qwen3-max"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "alibaba/qwen3-max",
     "tracks": [
      {
       "label": ">128.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128001,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "qwen/qwen3-max"
    }
   ],
   "intro": "Flagship Qwen3 model for coding agents, complex reasoning, and tool use",
   "released_at": "2025-09-23",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 1
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Max",
    "alibaba/qwen3-max",
    "deepinfra/Qwen/Qwen3-Max",
    "qwen/qwen3-max",
    "qwen3-max-2025-09-23",
    "qwen3-max-2026-01-23"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 Max 是 Qwen3 系列的高端推理模型，专注于多语言推理与工具集成。",
    "zh-TW": "Qwen3 Max 是 Qwen3 系列中高階推理模型，支援多語言推理與工具整合。",
    "ja-JP": "Qwen3 Maxは、Qwen3シリーズの最上位推論モデルで、多言語推論とツール統合に対応します。",
    "ru-RU": "Qwen3 Max — флагманская модель логического вывода в серии Qwen3, предназначенная для многоязычного логического анализа и интеграции инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "302ai",
     "charge": "completion",
     "old": "1.83",
     "new": "3.43"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "302ai",
     "charge": "prompt",
     "old": "0.46",
     "new": "0.86"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "aihubmix",
     "charge": "completion",
     "old": "1.8032",
     "new": "1.37"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "aihubmix",
     "charge": "prompt",
     "old": "0.4508",
     "new": "0.34"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-max-n",
   "model_name": "qwen3-max-n",
   "display_name": "Qwen3-Max-N",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.1313"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5354"
      }
     }
    }
   ],
   "released_at": "2025-11-05",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-Max-N"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-max-preview",
   "model_name": "qwen3-max-preview",
   "display_name": "Qwen3 Max Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "cache_read_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "cache_read_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "5.882353"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "8.823529"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.43"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.846"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.384"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.861"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.441"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.173"
      }
     }
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.861"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.441"
      }
     },
     "provider_model_id": "qwen/qwen3-max-preview"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.0909"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.8485"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86957"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.47826"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "alibaba/qwen3-max-preview",
     "tracks": [
      {
       "label": ">128.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128001,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "qwen/qwen3-max-preview"
    }
   ],
   "released_at": "2025-10-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2025-04",
   "family": "qwen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen3-max-preview",
    "qwen/qwen3-max-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 Max（预览版）是面向高级推理与工具集成的 Max 版本。",
    "zh-TW": "Qwen3 Max（預覽版）是 Max 變體，專為進階推理與工具整合設計。",
    "ja-JP": "Qwen3 Max（プレビュー）は、高度な推論とツール統合に対応するMaxバリアントです。",
    "ru-RU": "Qwen3 Max (предпросмотр) — вариант Max для продвинутого логического вывода и интеграции инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Max Preview"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Max-Thinking",
   "model_name": "Qwen3-Max-Thinking",
   "display_name": "Qwen 3 Max Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Max-Thinking"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.78"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9"
      }
     },
     "provider_model_id": "qwen/qwen3-max-thinking"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.78"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9"
      }
     },
     "provider_model_id": "qwen/qwen3-max-thinking"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.0909"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5758"
      }
     },
     "provider_model_id": "qwen3-max-thinking"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "alibaba/qwen3-max-thinking",
     "tracks": [
      {
       "label": ">128.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128001,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Qwen reasoning model for deliberate problem solving, math, and coding",
   "released_at": "2026-01-23",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 256000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Max-Thinking",
    "alibaba/qwen3-max-thinking",
    "qwen/qwen3-max-thinking",
    "qwen3-max-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3 Max Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-next",
   "model_name": "qwen3-next",
   "display_name": "qwen3-next",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen/qwen3-next"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "text",
     "code"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-next"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-next"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-next-80b",
   "model_name": "qwen3-next-80b",
   "display_name": "Qwen 3 Next 80b",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1515"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5152"
      }
     }
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     }
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-04-29",
   "max_input_tokens": 256000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-07",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3 Next 80b"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-next-80b-a3b",
   "model_name": "qwen3-next-80b-a3b",
   "display_name": "Qwen/Qwen3-Next-80B-A3B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.45"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.236"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.45"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b",
     "region": "us-west-2"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     }
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1175"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.136"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0588"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-09-18",
   "max_input_tokens": 262000,
   "max_output_tokens": 262000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen.qwen3-next-80b-a3b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-Next-80B-A3B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-next-80b-a3b-instruct",
   "model_name": "qwen3-next-80b-a3b-instruct",
   "display_name": "Qwen3-Next 80B-A3B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5715"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.138"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.552"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.574"
      }
     }
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-instruct"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.45"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b-instruct",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b-instruct",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.236"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b-instruct",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b-instruct",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b-instruct",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b-instruct",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.45"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b-instruct",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b-instruct",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b-instruct",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen.qwen3-next-80b-a3b-instruct",
     "region": "us-west-2"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Next-80B-A3B-Instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Next-80B-A3B-Instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-next-80b-a3b-instruct"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Next-80B-A3B-Instruct"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Next-80B-A3B-Instruct"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-instruct"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14713132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      }
     },
     "provider_model_id": "Qwen3-Next-80B-A3B-Instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "provider_model_id": "qwen/Qwen3-Next-80B-A3B-Instruct"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-instruct"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14493"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      }
     }
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Next-80B-A3B-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen3-Next-80B-A3B-Instruct"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "alibaba/qwen3-next-80b-a3b-instruct"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-09",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Next-80B-A3B-Instruct",
    "Qwen3-Next-80B-A3B-Instruct",
    "accounts/fireworks/models/qwen3-next-80b-a3b-instruct",
    "alibaba/qwen3-next-80b-a3b-instruct",
    "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct",
    "qwen.qwen3-next-80b-a3b-instruct",
    "qwen/Qwen3-Next-80B-A3B-Instruct",
    "qwen/qwen3-next-80b-a3b-instruct",
    "qwen/qwen3-next-80b-a3b-instruct:free"
   ],
   "intro_i18n": {
    "zh-CN": "下一代 Qwen3 非推理开源模型。相比上一版本（Qwen3-235B-A22B-Instruct-2507），在中文理解、逻辑推理和文本生成方面均有显著提升。",
    "zh-TW": "下一代 Qwen3 非思考開源模型。相較前代（Qwen3-235B-A22B-Instruct-2507），具備更佳中文理解、更強邏輯推理與更優文本生成能力。",
    "ja-JP": "次世代のQwen3非思考型オープンソースモデル。前バージョン（Qwen3-235B-A22B-Instruct-2507）と比較して、中国語理解、論理的推論、テキスト生成が向上しています。",
    "ru-RU": "Модель следующего поколения Qwen3 без рассуждений с открытым исходным кодом. По сравнению с предыдущей версией (Qwen3-235B-A22B-Instruct-2507), улучшено понимание китайского языка, логическое мышление и генерация текста."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14720168",
     "new": "0.14713132"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14730394",
     "new": "0.14720168"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14745922",
     "new": "0.14730394"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14748933",
     "new": "0.14745922"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14743712",
     "new": "0.14748933"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "1.4",
     "new": "1.1"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.14",
     "new": "0.09"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14717895",
     "new": "0.14743712"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58874828",
     "new": "0.5887158"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14718707",
     "new": "0.14717895"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Next-80B-A3B-Instruct-FP8",
   "model_name": "Qwen3-Next-80B-A3B-Instruct-FP8",
   "display_name": "Qwen3-Next-80B-A3B-Instruct-FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Next-80B-A3B-Instruct-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-Next-80B-A3B-Instruct-FP8"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-next-80b-a3b-instruct-maas",
   "model_name": "qwen3-next-80b-a3b-instruct-maas",
   "display_name": "qwen3-next-80b-a3b-instruct-maas",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-instruct-maas",
     "region": "global"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "text",
     "code"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-next-80b-a3b-instruct-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-next-80b-a3b-instruct-maas"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-next-80b-a3b-thinking",
   "model_name": "qwen3-next-80b-a3b-thinking",
   "display_name": "Qwen3-Next 80B-A3B (Thinking)",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.142"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.42"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.434"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.164"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.311"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "Qwen3-Next-80B-A3B-Thinking"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-next-80b-a3b-thinking"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Next-80B-A3B-Thinking"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-thinking"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0975"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-thinking"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-thinking"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-thinking"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Next-80B-A3B-Thinking"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-thinking"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-thinking"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0975"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-thinking"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14493"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4492800000000001"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "nebius/qwen/qwen3-next-80b-a3b-thinking"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Next-80B-A3B-Thinking"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen3-Next-80B-A3B-Thinking"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "alibaba/qwen3-next-80b-a3b-thinking"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     }
    }
   ],
   "intro": "Efficient Qwen thinking model for local reasoning, math, and coding agents",
   "released_at": "2025-09",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 1
   },
   "benchmarks": {
    "intelligence_index": 16.7,
    "coding_index": 17.4,
    "agentic_index": 2.1
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Next-80B-A3B-Thinking",
    "Qwen3-Next-80B-A3B-Thinking",
    "accounts/fireworks/models/qwen3-next-80b-a3b-thinking",
    "alibaba/qwen3-next-80b-a3b-thinking",
    "nebius/qwen/qwen3-next-80b-a3b-thinking",
    "qwen/qwen3-next-80b-a3b-thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 Next 80B A3B Thinking 是面向复杂任务的旗舰推理模型版本。",
    "zh-TW": "Qwen3 Next 80B A3B Thinking 是一款旗艦級推理模型，適用於複雜任務。",
    "ja-JP": "Qwen3 Next 80B A3B Thinkingは、複雑なタスクに対応するフラッグシップの推論モデルです。",
    "ru-RU": "Qwen3 Next 80B A3B Thinking — флагманская версия модели рассуждений для сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Next-80B-A3B-Thinking-fast",
   "model_name": "Qwen3-Next-80B-A3B-Thinking-fast",
   "display_name": "Qwen3-Next-80B-A3B-Thinking-fast",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1875"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Next-80B-A3B-Thinking-fast"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-07-25",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 8000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Next-80B-A3B-Thinking-fast"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-Next-80B-A3B-Thinking-fast"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-next-80b-a3b-thinking-maas",
   "model_name": "qwen3-next-80b-a3b-thinking-maas",
   "display_name": "qwen3-next-80b-a3b-thinking-maas",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen/qwen3-next-80b-a3b-thinking-maas",
     "region": "global"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "text",
     "code"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-next-80b-a3b-thinking-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-next-80b-a3b-thinking-maas"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-next-80b-think",
   "model_name": "qwen3-next-80b-think",
   "display_name": "Qwen3-Next-80B-Think",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1515"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5152"
      }
     }
    }
   ],
   "released_at": "2025-09-11",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-Next-80B-Think"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-next:80b",
   "model_name": "qwen3-next:80b",
   "display_name": "qwen3-next:80b",
   "vendor": "alibaba",
   "pricing": [],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-09-15",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-next:80b"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Omni-30B-A3B-Captioner",
   "model_name": "Qwen3-Omni-30B-A3B-Captioner",
   "display_name": "Qwen/Qwen3-Omni-30B-A3B-Captioner",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411765"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Omni-30B-A3B-Captioner"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Omni-30B-A3B-Captioner"
    }
   ],
   "released_at": "2025-10-04",
   "max_input_tokens": 66000,
   "max_output_tokens": 66000,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "omni",
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "stream": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Omni-30B-A3B-Captioner"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-Omni-30B-A3B-Captioner 是 Qwen3 系列的视觉语言模型（VLM），专为生成高质量、细致且准确的图像描述而设计。该模型采用 300 亿参数的 MoE 架构，具备深度图像理解能力，能够流畅生成描述，擅长捕捉细节、理解场景、识别物体及进行关系推理。",
    "zh-TW": "Qwen3-Omni-30B-A3B-Captioner 是 Qwen3 系列的視覺語言模型（VLM），專為高品質、細緻且準確的圖像描述而設計。採用 30B 參數的 MoE 架構，能深入理解圖像並生成流暢描述，擅長細節捕捉、場景理解、物體辨識與關係推理。",
    "ja-JP": "Qwen3-Omni-30B-A3B-Captionerは、Qwen3シリーズのVLMで、高品質かつ詳細で正確な画像キャプション生成に特化しています。30BパラメータのMoEアーキテクチャを採用し、画像を深く理解し、流暢な説明を生成します。細部の把握、シーン理解、物体認識、関係推論に優れています。",
    "ru-RU": "Qwen3-Omni-30B-A3B-Captioner — это модель VLM из серии Qwen3, созданная для высококачественных, детализированных и точных описаний изображений. Использует архитектуру MoE с 30B параметров для глубокого понимания изображений и генерации беглых описаний, превосходя в захвате деталей, понимании сцен, распознавании объектов и логических связях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-Omni-30B-A3B-Captioner"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Omni-30B-A3B-Instruct",
   "model_name": "Qwen3-Omni-30B-A3B-Instruct",
   "display_name": "Qwen3 Omni 30B A3B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-omni-30b-a3b-instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      }
     },
     "provider_model_id": "qwen3-omni-30b-a3b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.788"
      }
     },
     "provider_model_id": "qwen/qwen3-omni-30b-a3b-instruct"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411765"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Omni-30B-A3B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Omni-30B-A3B-Instruct"
    }
   ],
   "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
   "released_at": "2025-09-24",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 65536,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "video",
     "audio",
     "image"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "omni",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Omni-30B-A3B-Instruct",
    "accounts/fireworks/models/qwen3-omni-30b-a3b-instruct",
    "qwen/qwen3-omni-30b-a3b-instruct",
    "qwen3-omni-30b-a3b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-Omni-30B-A3B-Instruct 是 Qwen3 系列的 MoE 模型，拥有 300 亿总参数和 30 亿激活参数，在保持强大性能的同时降低推理成本。该模型基于高质量多源多语种数据训练，支持全模态输入（文本、图像、音频、视频）及跨模态理解与生成。",
    "zh-TW": "Qwen3-Omni-30B-A3B-Instruct 是 Qwen3 系列的 MoE 模型，總參數為 30B，啟用參數為 3B，具備高效能與低推理成本。訓練於高品質多來源多語言資料，支援全模態輸入（文字、圖像、音訊、影片）與跨模態理解與生成。",
    "ja-JP": "Qwen3-Omni-30B-A3B-Instructは、Qwen3シリーズのMoEモデルで、総パラメータ数30B、アクティブパラメータ数3Bを備え、低コストで高性能を実現します。高品質なマルチソース多言語データでトレーニングされており、テキスト、画像、音声、動画といったフルモーダル入力に対応し、クロスモーダルな理解と生成を可能にします。",
    "ru-RU": "Qwen3-Omni-30B-A3B-Instruct — это модель MoE из серии Qwen3 с 30B общих и 3B активных параметров, обеспечивающая высокую производительность при низкой стоимости вывода. Обучена на высококачественных многоязычных данных из различных источников, поддерживает полные мультимодальные входы (текст, изображения, аудио, видео) и кросс-модальное понимание и генерацию."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Omni 30B A3B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Omni-30B-A3B-Thinking",
   "model_name": "Qwen3-Omni-30B-A3B-Thinking",
   "display_name": "Qwen3 Omni 30B A3B Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      }
     },
     "provider_model_id": "qwen3-omni-30b-a3b-thinking"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.788"
      }
     },
     "provider_model_id": "qwen/qwen3-omni-30b-a3b-thinking"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411765"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Omni-30B-A3B-Thinking"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Omni-30B-A3B-Thinking"
    }
   ],
   "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
   "released_at": "2025-09-24",
   "max_input_tokens": 65536,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "audio",
     "video",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "omni",
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Omni-30B-A3B-Thinking",
    "qwen/qwen3-omni-30b-a3b-thinking",
    "qwen3-omni-30b-a3b-thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-Omni-30B-A3B-Thinking 是 Qwen3-Omni 的核心“思考者”组件，能够处理多模态输入（文本、音频、图像、视频），并执行复杂的思维链推理。它将多模态信息统一为共享表示，实现深度跨模态理解。该模型采用 MoE 架构，拥有 300 亿总参数和 30 亿激活参数，在推理能力与计算效率之间实现良好平衡。",
    "zh-TW": "Qwen3-Omni-30B-A3B-Thinking 是 Qwen3-Omni 的核心「思考者」組件。可處理多模態輸入（文字、音訊、圖像、影片），並執行複雜的思考鏈推理，將輸入統一為共享表示以實現深度跨模態理解。採用 MoE 架構，總參數為 30B，啟用參數為 3B，兼顧強大推理能力與運算效率。",
    "ja-JP": "Qwen3-Omni-30B-A3B-Thinkingは、Qwen3-Omniの中核となる「思考」コンポーネントです。テキスト、音声、画像、動画といったマルチモーダル入力を処理し、複雑な思考の連鎖による推論を行います。入力を統一された表現に変換し、深いクロスモーダル理解を実現します。MoEアーキテクチャを採用し、総パラメータ数30B、アクティブパラメータ数3Bで、強力な推論能力と計算効率のバランスを取っています。",
    "ru-RU": "Qwen3-Omni-30B-A3B-Thinking — это основной компонент \"Thinker\" в Qwen3-Omni. Обрабатывает мультимодальные входы (текст, аудио, изображения, видео) и выполняет сложные цепочки рассуждений, объединяя входные данные в общее представление для глубокого кросс-модального понимания. Это модель MoE с 30B общих и 3B активных параметров, обеспечивающая баланс между мощными рассуждениями и вычислительной эффективностью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Omni 30B A3B Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-omni-flash",
   "model_name": "qwen3-omni-flash",
   "display_name": "Qwen3-Omni Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.66"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3.81"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "15.11"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.485294"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3.584"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "7.168"
      }
     }
    }
   ],
   "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
   "released_at": "2025-09-15",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 65536,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "stream": true
   },
   "model_type": "omni",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen3-Omni-Flash 是基于 Thinker–Talker 专家混合（MoE）架构构建的多模态大型模型。支持文本、图像、音频和视频的高效理解，以及语音生成能力。该模型支持 119 种语言的文本交互和 20 种语言的语音交互，能够生成类人语音，实现精准的跨语言交流。具备强大的指令跟随能力，并支持可定制的系统提示，灵活适应不同的对话风格和角色设置。广泛适用于文本创作、语音助手和多媒体分析等场景，提供自然流畅的多模态交互体验。",
    "zh-TW": "Qwen3-Omni-Flash 是基於 Thinker–Talker 專家混合架構（MoE）構建的多模態大型模型。支持文本、圖像、音頻和視頻的高效理解，以及語音生成能力。該模型支持 119 種語言的文本交互和 20 種語言的語音交互，生成類人語音以實現精確的跨語言溝通。具備強大的指令跟隨能力，支持可定制的系統提示，靈活適應不同的對話風格和角色設置。廣泛應用於文本創作、語音助手和多媒體分析等場景，提供自然流暢的多模態交互體驗。",
    "ja-JP": "Qwen3-Omni-Flashは、Thinker–Talker Mixture-of-Experts（MoE）アーキテクチャに基づくマルチモーダル大規模モデルです。テキスト、画像、音声、動画の効率的な理解をサポートし、音声生成機能も備えています。このモデルは、119言語でのテキストベースの対話と20言語での音声対話を可能にし、正確なクロスリンガルコミュニケーションのために人間らしい音声を生成します。強力な指示追従能力を持ち、カスタマイズ可能なシステムプロンプトをサポートすることで、さまざまな会話スタイルや役割設定に柔軟に適応できます。テキスト作成、音声アシスタント、マルチメディア分析などのシナリオで広く活用され、自然でシームレスなマルチモーダルインタラクション体験を提供します。",
    "ru-RU": "Qwen3-Omni-Flash — это мультимодальная крупная модель, построенная на архитектуре Thinker–Talker Mixture-of-Experts (MoE). Она поддерживает эффективное понимание текста, изображений, аудио и видео, а также возможности генерации речи. Модель обеспечивает текстовое взаимодействие на 119 языках и голосовое взаимодействие на 20 языках, создавая речь, близкую к человеческой, для точной межъязыковой коммуникации. Она обладает сильными способностями следовать инструкциям и поддерживает настраиваемые системные подсказки, позволяя гибко адаптироваться к различным стилям общения и ролевым настройкам. Широко применима в таких сценариях, как создание текста, голосовые помощники и мультимедийный анализ, обеспечивая естественное и бесшовное мультимодальное взаимодействие."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-omni-flash-realtime",
   "model_name": "qwen3-omni-flash-realtime",
   "display_name": "Qwen3-Omni Flash Realtime",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.52"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.99"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "4.57"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "18.13"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.918"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3.584"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "7.168"
      }
     }
    }
   ],
   "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
   "released_at": "2025-09-15",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 65536,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "stream": true
   },
   "model_type": "realtime_omni",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Reranker-0.6B",
   "model_name": "Qwen3-Reranker-0.6B",
   "display_name": "Qwen3 Reranker 0.6B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "qwen3-reranker-0.6b"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Reranker-0.6B"
    }
   ],
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2025-06-03",
   "max_input_tokens": 40960,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Reranker-0.6B",
    "qwen3-reranker-0.6b"
   ],
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Reranker 0.6B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-Reranker-4B",
   "model_name": "Qwen3-Reranker-4B",
   "display_name": "Qwen3-Reranker-4B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "qwen3-reranker-4b"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0575"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3-Reranker-4B"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-reranker-4b"
    },
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "qwen3-reranker-4b"
    }
   ],
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2026-02-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-Reranker-4B",
    "accounts/fireworks/models/qwen3-reranker-4b",
    "qwen3-reranker-4b"
   ],
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-Reranker-4B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-reranker-8b",
   "model_name": "qwen3-reranker-8b",
   "display_name": "Qwen3 Reranker 8B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-reranker-8b"
    }
   ],
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "max_input_tokens": 40960,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3-reranker-8b"
   ],
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 Reranker 8B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-TTS",
   "model_name": "Qwen3-TTS",
   "display_name": "Qwen3-TTS",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "20"
      }
     },
     "provider_model_id": "Qwen/Qwen3-TTS"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_input": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-TTS"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-TTS"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-TTS-VoiceDesign",
   "model_name": "Qwen3-TTS-VoiceDesign",
   "display_name": "Qwen3 TTS VoiceDesign",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "20"
      }
     },
     "provider_model_id": "Qwen/Qwen3-TTS-VoiceDesign"
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2026-04-21",
   "max_input_tokens": 32768,
   "max_output_tokens": 1,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "qwen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "audio_output": true,
    "open_weights": true
   },
   "model_type": "speech_synthesis",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-TTS-VoiceDesign",
    "qwen3-tts-voicedesign"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 TTS VoiceDesign"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl",
   "model_name": "qwen3-vl",
   "display_name": "qwen3-vl",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.13"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "qwen3-vl"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-235b-a22b",
   "model_name": "qwen3-vl-235b-a22b",
   "display_name": "Qwen3-VL 235B-A22B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "8.4"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286705"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14682"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.867051"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.866667",
        "completion": "0.886667"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.22"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.13"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5459"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.7398"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.13"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.13"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.82"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.12"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.22"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.66"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.66"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.66"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b",
     "region": "us-west-2"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.71"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.186"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.686"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.047"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     }
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-04",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen.qwen3-vl-235b-a22b",
    "qwen.qwen3-vl-235b-a22b-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "completion",
     "old": "1.5",
     "new": "1.9"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "prompt",
     "old": "0.25",
     "new": "0.21"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-235b-a22b-i",
   "model_name": "qwen3-vl-235b-a22b-i",
   "display_name": "Qwen3-VL-235B-A22B-I",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.303"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5152"
      }
     }
    }
   ],
   "released_at": "2025-09-24",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL-235B-A22B-I"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-235b-a22b-instruct",
   "model_name": "qwen3-vl-235b-a22b-instruct",
   "display_name": "qwen3-vl-235b-a22b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.143"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.274"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.096"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.147"
      }
     }
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.22"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b-instruct",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.13"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b-instruct",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5459"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.7398"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b-instruct",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.13"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b-instruct",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.13"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b-instruct",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.82"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.12"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b-instruct",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.22"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b-instruct",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.66"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b-instruct",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.66"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b-instruct",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.66"
      }
     },
     "provider_model_id": "qwen.qwen3-vl-235b-a22b-instruct",
     "region": "us-west-2"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-vl-235b-a22b-instruct"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Instruct"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-235b-a22b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwen/Qwen3-VL-235B-A22B-Instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-235b-a22b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-235b-a22b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-235b-a22b-instruct"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-235b-a22b-instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Instruct"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "alibaba/qwen3-vl-235b-a22b-instruct"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "open_weights": true,
    "stream": true,
    "image_output": true
   },
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-09-23",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "knowledge_cutoff": "2025-09",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.7,
     "top_p": 0.8
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-VL-235B-A22B-Instruct",
    "accounts/fireworks/models/qwen3-vl-235b-a22b-instruct",
    "alibaba/qwen3-vl-235b-a22b-instruct",
    "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct",
    "qwen.qwen3-vl-235b-a22b-instruct",
    "qwen/Qwen3-VL-235B-A22B-Instruct",
    "qwen/qwen3-vl-235b-a22b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 VL 235B A22B Instruct 是面向高要求理解与创作任务的旗舰多模态模型。",
    "zh-TW": "Qwen3 VL 235B A22B Instruct 是一款旗艦級多模態模型，適用於高要求的理解與創作任務。",
    "ja-JP": "Qwen3 VL 235B A22B Instructは、高度な理解と創造に対応するフラッグシップのマルチモーダルモデルです。",
    "ru-RU": "Qwen3 VL 235B A22B Instruct — флагманская мультимодальная модель для сложного понимания и генерации."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-VL-235B-A22B-Instruct-FP8",
   "model_name": "Qwen3-VL-235B-A22B-Instruct-FP8",
   "display_name": "Qwen3-VL 235B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "stackit",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.76"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.05"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Instruct-FP8"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2024-11-01",
   "max_input_tokens": 218000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-VL-235B-A22B-Instruct-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "limit",
     "old": "8192",
     "new": "16384",
     "note": "max_output_tokens"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "stackit",
     "charge": "completion",
     "old": "1.91",
     "new": "2.05"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "stackit",
     "charge": "prompt",
     "old": "1.64",
     "new": "1.76"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL 235B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-235b-a22b-instruct-original",
   "model_name": "qwen3-vl-235b-a22b-instruct-original",
   "display_name": "Qwen3 VL 235B A22B Instruct Original",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-09-25",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 VL 235B A22B Instruct Original"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-235b-a22b-t",
   "model_name": "qwen3-vl-235b-a22b-t",
   "display_name": "Qwen3-VL-235B-A22B-T",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9899"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9899"
      }
     }
    }
   ],
   "released_at": "2025-09-24",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL-235B-A22B-T"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-235b-a22b-thinking",
   "model_name": "qwen3-vl-235b-a22b-thinking",
   "display_name": "qwen3-vl-235b-a22b-thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.86"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.274"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.74"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-vl-235b-a22b-thinking"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.98"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.95"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Thinking"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-235b-a22b-thinking"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.98"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.95"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.98"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.95"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-235b-a22b-thinking"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.98"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.95"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-235b-a22b-thinking"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-235b-a22b-thinking"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-235b-a22b-thinking"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Thinking"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-235B-A22B-Thinking"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    }
   ],
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "open_weights": true,
    "stream": true,
    "image_output": true
   },
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-09-24",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "knowledge_cutoff": "2025-03",
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 1024
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.8,
     "top_p": 0.95,
     "top_k": 20,
     "repetition_penalty": 1
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-VL-235B-A22B-Thinking",
    "accounts/fireworks/models/qwen3-vl-235b-a22b-thinking",
    "qwen/qwen3-vl-235b-a22b-thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 VL 235B A22B Thinking 是面向复杂多模态推理与规划的旗舰推理版本。",
    "zh-TW": "Qwen3 VL 235B A22B Thinking 是旗艦級的深度思考版本，專為複雜的多模態推理與規劃任務設計。",
    "ja-JP": "Qwen3 VL 235B A22B Thinkingは、複雑なマルチモーダル推論と計画に対応するフラッグシップの思考モデルです。",
    "ru-RU": "Qwen3 VL 235B A22B Thinking — флагманская версия для сложного мультимодального рассуждения и планирования."
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "llmgateway",
     "charge": "completion",
     "old": "2",
     "new": "3.95"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "llmgateway",
     "charge": "prompt",
     "old": "0.5",
     "new": "0.98"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-30b-a3b",
   "model_name": "qwen3-vl-30b-a3b",
   "display_name": "Qwen3-VL 30B-A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.108"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.431"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.076"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.63"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1862"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2031"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0931"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2898"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7387"
      }
     }
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-04",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-VL-30B-A3B-Instruct",
   "model_name": "Qwen3-VL-30B-A3B-Instruct",
   "display_name": "Qwen3 VL 30B A3B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1028"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4112"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.108"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.431"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-30B-A3B-Instruct"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.92"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-30B-A3B-Instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-30B-A3B-Instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102991924"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411967696"
      }
     }
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-30B-A3B-Instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1087"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43478"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-instruct"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411765"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-30B-A3B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-30B-A3B-Instruct"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-30B-A3B-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-instruct"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "vision": true,
    "image_output": true,
    "video_input": true,
    "pdf_input": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true,
    "prompt_caching": true
   },
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-10-11",
   "modalities": {
    "input": [
     "text",
     "video",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "knowledge_cutoff": "2025-03",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.7,
     "top_p": 0.8,
     "top_k": 20,
     "repetition_penalty": 1
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-VL-30B-A3B-Instruct",
    "accounts/fireworks/models/qwen3-vl-30b-a3b-instruct",
    "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct",
    "qwen/qwen3-vl-30b-a3b-instruct",
    "qwen3-vl-30b-a3b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-VL-30B-A3B-Instruct 是一款经过指令微调的 Qwen3-VL 模型，具备强大的视觉语言理解与生成能力。原生支持 256K 上下文长度，适用于多模态对话与图像条件生成任务。",
    "zh-TW": "Qwen3-VL-30B-A3B-Instruct 是指令微調的 Qwen3-VL 模型，具備強大的視覺語言理解與生成能力。原生支援 256K 上下文，適用於多模態對話與圖像條件生成。",
    "ja-JP": "Qwen3-VL-30B-A3B-Instructは、視覚と言語の理解と生成に優れた指示調整済みQwen3-VLモデルです。256Kのコンテキストをネイティブにサポートし、マルチモーダルチャットや画像条件付き生成に対応します。",
    "ru-RU": "Qwen3-VL-30B-A3B-Instruct — это модель Qwen3-VL, настроенная на выполнение инструкций, с сильным пониманием и генерацией в связке зрение-язык. Нативно поддерживает контекст до 256K для мультимодального чата и генерации, основанной на изображениях."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412164704",
     "new": "0.411967696"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103041176",
     "new": "0.102991924"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412451032",
     "new": "0.412164704"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103112758",
     "new": "0.103041176"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412885816",
     "new": "0.412451032"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103221454",
     "new": "0.103112758"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412970124",
     "new": "0.412885816"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103242531",
     "new": "0.103221454"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412823936",
     "new": "0.412970124"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103205984",
     "new": "0.103242531"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.41210106",
     "new": "0.412823936"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103025265",
     "new": "0.103205984"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 VL 30B A3B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-VL-30B-A3B-Thinking",
   "model_name": "Qwen3-VL-30B-A3B-Thinking",
   "display_name": "Qwen3 VL 30B A3B Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.102941"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-thinking"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-thinking"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1028"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.028"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-thinking"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-thinking"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.56"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-30b-a3b-thinking"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-thinking"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-thinking"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-30b-a3b-thinking"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.56"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-30b-a3b-thinking"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1087"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.0869600000000001"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-thinking"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411765"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-30B-A3B-Thinking"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-30B-A3B-Thinking"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-30B-A3B-Thinking"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.102941"
      }
     },
     "provider_model_id": "qwen3-vl-30b-a3b-thinking"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "vision": true,
    "image_output": true,
    "video_input": true,
    "pdf_input": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true,
    "prompt_caching": true
   },
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2026-02-09",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "knowledge_cutoff": "2025-03",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.8,
     "top_p": 0.95,
     "top_k": 20,
     "repetition_penalty": 1
    }
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-VL-30B-A3B-Thinking",
    "accounts/fireworks/models/qwen3-vl-30b-a3b-thinking",
    "qwen/qwen3-vl-30b-a3b-thinking",
    "qwen3-vl-30b-a3b-thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-VL-30B-A3B-Thinking 是 Qwen3-VL 的推理增强版本，专为多模态推理、图像转代码及复杂视觉理解任务优化。支持 256K 上下文，具备更强的思维链能力。",
    "zh-TW": "Qwen3-VL-30B-A3B-Thinking 是 Qwen3-VL 的推理增強版本，針對多模態推理、圖像轉程式碼與複雜視覺理解進行優化。支援 256K 上下文，具備更強的思考鏈能力。",
    "ja-JP": "Qwen3-VL-30B-A3B-Thinkingは、Qwen3-VLの推論強化バージョンで、マルチモーダル推論、画像からコードへの変換、複雑な視覚理解に最適化されています。256Kのコンテキストをサポートし、強力な思考の連鎖能力を備えています。",
    "ru-RU": "Qwen3-VL-30B-A3B-Thinking — версия Qwen3-VL с усиленными возможностями рассуждения, оптимизированная для мультимодальных рассуждений, преобразования изображений в код и сложного визуального понимания. Поддерживает контекст до 256K с улучшенной способностью к цепочкам рассуждений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 VL 30B A3B Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-32b",
   "model_name": "qwen3-vl-32b",
   "display_name": "qwen3-vl-32b",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.71"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "qwen3-vl-32b"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-32b-instruct",
   "model_name": "qwen3-vl-32b-instruct",
   "display_name": "qwen3-vl-32b-instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.64"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.143"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.64"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3-vl-32b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.104"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.416"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-32b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.104"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.416"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-32b-instruct"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-32B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-32B-Instruct"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-32B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-32B-Instruct"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "open_weights": true,
    "stream": true,
    "image_output": true
   },
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-10-21",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "parameters": {
    "supported": [
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.7,
     "top_p": 0.8,
     "top_k": 20,
     "repetition_penalty": 1
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-VL-32B-Instruct",
    "accounts/fireworks/models/qwen3-vl-32b-instruct",
    "qwen/qwen3-vl-32b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-VL-32B-Instruct 是 Qwen 团队推出的视觉语言模型，在多个 VL 基准测试中取得领先 SOTA 成绩。支持百万像素分辨率图像，具备强大的视觉理解、多语种 OCR、细粒度视觉定位与视觉对话能力，能够处理复杂多模态任务，并支持工具调用与前缀补全。",
    "zh-TW": "Qwen3-VL-32B-Instruct 是 Qwen 團隊推出的視覺語言模型，在多項 VL 基準測試中取得領先成績。支援百萬像素解析度圖像，具備強大的視覺理解、多語言 OCR、細粒度視覺定位與視覺對話能力。可處理複雜多模態任務，並支援工具呼叫與前綴補全。",
    "ja-JP": "Qwen3-VL-32B-Instructは、Qwenチームによる視覚と言語のモデルで、複数のVLベンチマークで最先端の結果を達成しています。メガピクセル解像度の画像をサポートし、強力な視覚理解、多言語OCR、精緻な視覚的グラウンディング、視覚対話に対応します。複雑なマルチモーダルタスクを処理し、ツール呼び出しやプレフィックス補完も可能です。",
    "ru-RU": "Qwen3-VL-32B-Instruct — это модель зрение-язык от команды Qwen с передовыми результатами на нескольких VL-бенчмарках. Поддерживает изображения с мегапиксельным разрешением и обеспечивает сильное визуальное понимание, многоязычное OCR, точную визуальную привязку и визуальный диалог. Обрабатывает сложные мультимодальные задачи и поддерживает вызов инструментов и автозавершение по префиксу."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-32b-thinking",
   "model_name": "qwen3-vl-32b-thinking",
   "display_name": "qwen3-vl-32b-thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.87"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.86"
      }
     }
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-32B-Thinking"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-32B-Thinking"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-32B-Thinking"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    }
   ],
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true,
    "image_output": true
   },
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-10-21",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-VL-32B-Thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-VL-32B-Thinking 针对复杂视觉推理任务进行了优化，内置“思考模式”，在生成答案前输出中间推理步骤，提升多步骤逻辑、规划与复杂推理能力。支持百万像素图像，具备强大的视觉理解、多语种 OCR、细粒度定位、视觉对话、工具调用与前缀补全能力。",
    "zh-TW": "Qwen3-VL-32B-Thinking 專為複雜視覺推理優化。內建思考模式，在回答前生成中間推理步驟，提升多步邏輯、規劃與複雜推理能力。支援百萬像素圖像、強視覺理解、多語言 OCR、細粒度定位、視覺對話、工具呼叫與前綴補全。",
    "ja-JP": "Qwen3-VL-32B-Thinkingは、複雑な視覚的推論に最適化されたモデルです。内蔵の思考モードにより、回答前に中間的な推論ステップを生成し、マルチステップの論理、計画、複雑な推論を強化します。メガピクセル画像、強力な視覚理解、多言語OCR、精緻なグラウンディング、視覚対話、ツール呼び出し、プレフィックス補完に対応します。",
    "ru-RU": "Qwen3-VL-32B-Thinking оптимизирована для сложных визуальных рассуждений. Включает встроенный режим мышления, который генерирует промежуточные шаги рассуждений перед ответами, улучшая многошаговую логику, планирование и сложные рассуждения. Поддерживает изображения с мегапиксельным разрешением, сильное визуальное понимание, многоязычное OCR, точную привязку, визуальный диалог, вызов инструментов и автозавершение по префиксу."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-VL-4B-Instruct",
   "model_name": "Qwen3-VL-4B-Instruct",
   "display_name": "Qwen3-VL-4B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025747981"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.102991924"
      }
     }
    }
   ],
   "released_at": "2025-10-15",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.103041176",
     "new": "0.102991924"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.025760294",
     "new": "0.025747981"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.103112758",
     "new": "0.103041176"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0257781895",
     "new": "0.025760294"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.103221454",
     "new": "0.103112758"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0258053635",
     "new": "0.0257781895"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.103242531",
     "new": "0.103221454"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.02581063275",
     "new": "0.0258053635"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.103205984",
     "new": "0.103242531"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.025801496",
     "new": "0.02581063275"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.103025265",
     "new": "0.103205984"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.02575631625",
     "new": "0.025801496"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL-4B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-8b",
   "model_name": "qwen3-vl-8b",
   "display_name": "qwen3-vl-8b",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "qwen3-vl-8b"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-VL-8B-Instruct",
   "model_name": "Qwen3-VL-8B-Instruct",
   "display_name": "Qwen3 VL 8B Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "qwen3-vl-8b-instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     },
     "provider_model_id": "qwen3-vl-8b-instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen3-vl-8b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-8b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen3-vl-8b-instruct"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.051495962"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.205983848"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen3-vl-8b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-8b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.455"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-8b-instruct"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-8b-instruct"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-8B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-8B-Instruct"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-8B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-8B-Instruct"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "qwen3-vl-8b-instruct"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true,
    "prompt_caching": true
   },
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-10-17",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.7,
     "top_p": 0.8
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-VL-8B-Instruct",
    "accounts/fireworks/models/qwen3-vl-8b-instruct",
    "qwen/qwen3-vl-8b-instruct",
    "qwen3-vl-8b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-VL-8B-Instruct 是基于 Qwen3-8B-Instruct 构建的视觉语言模型，训练于大规模图文数据，擅长通用视觉理解、以视觉为中心的对话及图像中的多语种文本识别，适用于视觉问答、图像描述、多模态指令跟随与工具使用等任务。",
    "zh-TW": "Qwen3-VL-8B-Instruct 是基於 Qwen3-8B-Instruct 的視覺語言模型，訓練於大量圖文資料。擅長通用視覺理解、以視覺為中心的對話與圖像中的多語言文字辨識，適用於視覺問答、圖說、多模態指令遵循與工具使用。",
    "ja-JP": "Qwen3-VL-8B-Instructは、Qwen3-8B-Instructをベースに構築された視覚と言語のモデルで、大規模な画像とテキストデータでトレーニングされています。一般的な視覚理解、視覚中心の対話、画像内の多言語テキスト認識に優れ、視覚QA、キャプション生成、マルチモーダル指示追従、ツール使用に適しています。",
    "ru-RU": "Qwen3-VL-8B-Instruct — это модель зрение-язык из серии Qwen3, построенная на базе Qwen3-8B-Instruct и обученная на больших объемах данных изображение-текст. Отличается общим визуальным пониманием, диалогом с упором на визуальные элементы и многоязычным распознаванием текста на изображениях. Подходит для визуального QA, создания подписей, мультимодального следования инструкциям и использования инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206082352",
     "new": "0.205983848"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051520588",
     "new": "0.051495962"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206225516",
     "new": "0.206082352"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051556379",
     "new": "0.051520588"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206442908",
     "new": "0.206225516"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051610727",
     "new": "0.051556379"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206485062",
     "new": "0.206442908"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0516212655",
     "new": "0.051610727"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206411968",
     "new": "0.206485062"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051602992",
     "new": "0.0516212655"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.20605053",
     "new": "0.206411968"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0515126325",
     "new": "0.051602992"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 VL 8B Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-VL-8B-Thinking",
   "model_name": "Qwen3-VL-8B-Thinking",
   "display_name": "Qwen3 VL 8B Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     },
     "provider_model_id": "qwen3-vl-8b-thinking"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.365"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-8b-thinking"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.365"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-8b-thinking"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.1"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-8b-thinking"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-8B-Thinking"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-8B-Thinking"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     },
     "provider_model_id": "qwen3-vl-8b-thinking"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-10-15",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-VL-8B-Thinking",
    "qwen/qwen3-vl-8b-thinking",
    "qwen3-vl-8b-thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3-VL-8B-Thinking 是 Qwen3 的视觉思考版本，专为复杂多步骤推理任务优化。在生成答案前输出思维链，提升准确性，适用于深度视觉问答与图像细节分析。",
    "zh-TW": "Qwen3-VL-8B-Thinking 是 Qwen3 的視覺思考版本，針對複雜多步推理進行優化。在回答前生成思考鏈以提升準確性，適用於深度視覺問答與細緻圖像分析。",
    "ja-JP": "Qwen3-VL-8B-Thinkingは、Qwen3の視覚的思考バージョンで、複雑なマルチステップ推論に最適化されています。回答前に思考の連鎖を生成し、精度を向上させます。深い視覚QAや詳細な画像分析に最適です。",
    "ru-RU": "Qwen3-VL-8B-Thinking — визуальная версия мышления в серии Qwen3, оптимизированная для сложных многошаговых рассуждений. Генерирует цепочку мышления перед ответами для повышения точности, идеально подходит для глубокого визуального QA и детального анализа изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 VL 8B Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-embedding",
   "model_name": "qwen3-vl-embedding",
   "display_name": "Qwen3 VL Embedding",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-embedding"
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 8192,
   "capabilities": {},
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-vl-embedding"
   ],
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 VL Embedding"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-VL-Embedding-2B",
   "model_name": "Qwen3-VL-Embedding-2B",
   "display_name": "Qwen3-VL-Embedding-2B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0132418188"
      }
     }
    }
   ],
   "released_at": "2026-01-26",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "multimodal_embedding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132481512",
     "new": "0.0132418188"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132573546",
     "new": "0.0132481512"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132713298",
     "new": "0.0132573546"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132740397",
     "new": "0.0132713298"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132693408",
     "new": "0.0132740397"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132461055",
     "new": "0.0132693408"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL-Embedding-2B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-VL-Embedding-8B",
   "model_name": "Qwen3-VL-Embedding-8B",
   "display_name": "Qwen3-VL Embedding 8B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.051495962"
      }
     }
    },
    {
     "provider": "stackit",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "Qwen/Qwen3-VL-Embedding-8B"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2026-02-05",
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3-VL-Embedding-8B"
   ],
   "model_type": "multimodal_embedding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051520588",
     "new": "0.051495962"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051556379",
     "new": "0.051520588"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051610727",
     "new": "0.051556379"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0516212655",
     "new": "0.051610727"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051602992",
     "new": "0.0516212655"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0515126325",
     "new": "0.051602992"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL Embedding 8B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-flash",
   "model_name": "qwen3-vl-flash",
   "display_name": "Qwen3 VL Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.022059"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.022"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "qwen3-vl-flash-2025-10-15"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0206"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.206"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.00412"
      }
     },
     "provider_model_id": "qwen3-vl-flash-2026-01-22"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.022"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.215"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0022"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0275"
      }
     },
     "provider_model_id": "qwen3-vl-flash-2025-10-15"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "vision": true,
    "image_output": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-10-09",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen3-vl-flash-2025-10-15",
    "qwen3-vl-flash-2026-01-22"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 VL Flash：轻量级、高速推理版本，适用于对延迟敏感或高并发请求。",
    "zh-TW": "Qwen3 VL Flash：輕量高速推理版本，適用於對延遲敏感或高頻請求場景。",
    "ja-JP": "Qwen3 VL Flash：遅延に敏感または高トラフィックなリクエスト向けの軽量・高速推論モデルです。",
    "ru-RU": "Qwen3 VL Flash: легковесная, высокоскоростная версия рассуждений для задач с низкой задержкой или высоким объемом запросов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 VL Flash"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-flash-2025-10-15-us",
   "model_name": "qwen3-vl-flash-2025-10-15-us",
   "display_name": "Qwen3-VL-Flash-2025-10-15-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-10-15",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "structured_output": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL-Flash-2025-10-15-US"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-flash-2026-01-22-us",
   "model_name": "qwen3-vl-flash-2026-01-22-us",
   "display_name": "Qwen3-VL-Flash-2026-01-22-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2026-03-13",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL-Flash-2026-01-22-US"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-flash-us",
   "model_name": "qwen3-vl-flash-us",
   "display_name": "Qwen3-VL-Flash-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    }
   ],
   "released_at": "2025-10-15",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL-Flash-US"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-instruct",
   "model_name": "qwen3-vl-instruct",
   "display_name": "Qwen3 VL Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "alibaba/qwen3-vl-instruct"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-09-23",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 129024,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen3-vl-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 VL Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-plus",
   "model_name": "qwen3-vl-plus",
   "display_name": "Qwen3-VL Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "4.8"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "4.411765"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.43"
      }
     },
     "provider_model_id": "qwen3-vl-plus-2025-09-23"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.137"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.37"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0274"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.433525"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "4.300576"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "qwen3-vl-plus-2025-09-23"
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "4.8"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen/qwen3-vl-plus"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-09-23",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3-vl-plus",
    "qwen3-vl-plus-2025-09-23",
    "qwen3-vl-plus-2025-12-19"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3 VL-Plus 是 Qwen3 的视觉增强版本，具备更强的多模态推理与视频处理能力。",
    "zh-TW": "Qwen3 VL-Plus 是強化視覺能力的 Qwen3 變體，具備更佳的多模態推理與影片處理能力。",
    "ja-JP": "Qwen3 VL-Plusは、視覚機能を強化したQwen3のバリアントで、マルチモーダル推論と動画処理に優れています。",
    "ru-RU": "Qwen3 VL-Plus — визуально-усиленный вариант Qwen3 с улучшенным мультимодальным логическим выводом и обработкой видео."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-VL-Reranker-2B",
   "model_name": "Qwen3-VL-Reranker-2B",
   "display_name": "Qwen3-VL-Reranker-2B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0132418188"
      }
     }
    }
   ],
   "released_at": "2026-01-26",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132481512",
     "new": "0.0132418188"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132573546",
     "new": "0.0132481512"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132713298",
     "new": "0.0132573546"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132740397",
     "new": "0.0132713298"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132693408",
     "new": "0.0132740397"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0132461055",
     "new": "0.0132693408"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL-Reranker-2B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3-VL-Reranker-8B",
   "model_name": "Qwen3-VL-Reranker-8B",
   "display_name": "Qwen3-VL-Reranker-8B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.051495962"
      }
     }
    }
   ],
   "released_at": "2026-01-20",
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051520588",
     "new": "0.051495962"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051556379",
     "new": "0.051520588"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051610727",
     "new": "0.051556379"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0516212655",
     "new": "0.051610727"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051602992",
     "new": "0.0516212655"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0515126325",
     "new": "0.051602992"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3-VL-Reranker-8B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl-thinking",
   "model_name": "qwen3-vl-thinking",
   "display_name": "Qwen3 VL Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "alibaba/qwen3-vl-thinking"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2025-09-23",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "reasoning_config": {
    "budget_min": 1
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/qwen3-vl-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3 VL Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl:235b",
   "model_name": "qwen3-vl:235b",
   "display_name": "qwen3-vl:235b",
   "vendor": "alibaba",
   "pricing": [],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-09-22",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-vl:235b"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3-vl:235b-instruct",
   "model_name": "qwen3-vl:235b-instruct",
   "display_name": "qwen3-vl:235b-instruct",
   "vendor": "alibaba",
   "pricing": [],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-09-22",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3-vl:235b-instruct"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5",
   "model_name": "qwen3.5",
   "display_name": "qwen3.5",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.02"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "qwen3.5"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-0.8B",
   "model_name": "Qwen3.5-0.8B",
   "display_name": "Qwen3.5-0.8B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-0.8B"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-0.8B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-0.8B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-0.8B-Lora",
   "model_name": "Qwen3.5-0.8B-Lora",
   "display_name": "Qwen3.5-0.8B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-0.8B-Lora"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-0.8B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-0.8B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-122b",
   "model_name": "qwen3.5-122b",
   "display_name": "Qwen3.5-122B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     }
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-122B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-122b-a10b",
   "model_name": "qwen3.5-122b-a10b",
   "display_name": "Qwen3.5 122B-A10B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.941176"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.92"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1126"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9008"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.115"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.917"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.444"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.106"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.111"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-122B-A10B"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-122B-A10B"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "qwen/qwen3.5-122b-a10b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.08"
      }
     },
     "provider_model_id": "qwen/qwen3.5-122b-a10b"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "qwen/qwen3.5-122b-a10b"
    },
    {
     "provider": "mixlayer",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "qwen/qwen3.5-122b-a10b"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.205983848"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4713132"
      }
     },
     "provider_model_id": "Qwen3.5-122B-A10B"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.88"
      }
     },
     "provider_model_id": "qwen3.5-122b-a10b:thinking"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-122B-A10B"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "qwen/qwen3.5-122b-a10b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "qwen/qwen3.5-122b-a10b"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen3.5-122b-a10b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.08"
      }
     },
     "provider_model_id": "qwen/qwen3.5-122b-a10b"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.115"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.917"
      }
     },
     "provider_model_id": "qwen/qwen3.5-122b-a10b"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.941176"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-122B-A10B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.08"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-122B-A10B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.32"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-122B-A10B"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.08"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "qwen/qwen3.5-122b-a10b"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-23",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2026-01",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "docs_url": "https://openrouter.ai/qwen/qwen3.5-122b-a10b",
   "benchmarks": {
    "intelligence_index": 32.3,
    "coding_index": 45.7,
    "agentic_index": 20.7
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.6,
     "top_p": 0.95,
     "top_k": 20
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-122B-A10B",
    "Qwen3.5-122B-A10B",
    "TEE/qwen3.5-122b-a10b",
    "qwen/qwen3.5-122b-a10b",
    "qwen3-5-122b-a10b",
    "qwen3.5-122b-a10b:thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.5-122B-A10B 是 Qwen 团队开发的原生多模态大语言模型，具有 1220 亿总参数，仅 100 亿激活参数。它采用结合门控增量网络和稀疏专家混合（MoE）的高效混合架构，原生支持 256K 上下文长度，并可扩展至约 100 万个 token。",
    "zh-TW": "Qwen3.5-122B-A10B 是 Qwen 團隊開發的原生多模態大型語言模型，擁有 1220 億總參數，僅 100 億激活參數。它採用高效的混合架構，結合門控增量網絡和稀疏專家混合（MoE），原生支持 256K 上下文長度，並可擴展至約 100 萬個標記。",
    "ja-JP": "Qwen3.5-122B-A10BはQwenチームによるネイティブなマルチモーダル大規模言語モデルで、総パラメータ数は1220億、アクティブパラメータ数は10億です。効率的なハイブリッドアーキテクチャ（Gated Delta NetworksとSparse Mixture-of-Experts（MoE）の組み合わせ）を採用し、256Kの文脈長をネイティブにサポートし、約100万トークンまで拡張可能です。",
    "ru-RU": "Qwen3.5-122B-A10B — это нативная мультимодальная крупная языковая модель от команды Qwen с общим количеством параметров 122 миллиарда и только 10 миллиардами активных параметров. Она использует эффективную гибридную архитектуру, объединяющую Gated Delta Networks и Sparse Mixture-of-Experts (MoE), нативно поддерживает длину контекста 256K с возможностью расширения до примерно 1 миллиона токенов."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4720168",
     "new": "1.4713132"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206082352",
     "new": "0.205983848"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4730394",
     "new": "1.4720168"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206225516",
     "new": "0.206082352"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4745922",
     "new": "1.4730394"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206442908",
     "new": "0.206225516"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4748933",
     "new": "1.4745922"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206485062",
     "new": "0.206442908"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4743712",
     "new": "1.4748933"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206411968",
     "new": "0.206485062"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4717895",
     "new": "1.4743712"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.20605053",
     "new": "0.206411968"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.4718707",
     "new": "1.4717895"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206061898",
     "new": "0.20605053"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-122B-A10B-FP8",
   "model_name": "Qwen3.5-122B-A10B-FP8",
   "display_name": "Qwen3.5-122B-A10B-FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-122B-A10B-FP8"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-122B-A10B-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-122B-A10B-FP8"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-122B-A10B-Lora",
   "model_name": "Qwen3.5-122B-A10B-Lora",
   "display_name": "Qwen3.5-122B-A10B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-122B-A10B-Lora"
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-122B-A10B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-122B-A10B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-27b",
   "model_name": "qwen3.5-27b",
   "display_name": "Qwen3.5 27B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.705882"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "2.117647"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.69"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0846"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6768"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.086"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.688"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-27B"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-27B"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "qwen/qwen3.5-27b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.195"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.56"
      }
     },
     "provider_model_id": "qwen/qwen3.5-27b"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "qwen/qwen3.5-27b"
    },
    {
     "provider": "mixlayer",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "qwen/qwen3.5-27b"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088278792"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.706230336"
      }
     },
     "provider_model_id": "Qwen3.5-27B"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.16"
      }
     },
     "provider_model_id": "qwen3.5-27b:thinking"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "qwen/qwen3.5-27b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "qwen/qwen3.5-27b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.195"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.56"
      }
     },
     "provider_model_id": "qwen/qwen3.5-27b"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.086"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.688"
      }
     },
     "provider_model_id": "qwen/qwen3.5-27b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3.5-27B"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.705882"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "2.117647"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-27B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-27B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.09"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-27B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-27B"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-27B"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-23",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2025-04",
   "deprecated": true,
   "status": "deprecated",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "docs_url": "https://openrouter.ai/qwen/qwen3.5-27b",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.6,
     "top_p": 0.95,
     "top_k": 20
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-27B",
    "Qwen3.5-27B",
    "TEE/qwen3.5-27b",
    "deepinfra/Qwen/Qwen3.5-27B",
    "qwen/qwen3.5-27b",
    "qwen3-5-27b",
    "qwen3.5-27b:thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.5-27B 是 Qwen 团队开发的原生多模态大语言模型，具有 270 亿参数。它采用结合门控增量网络和门控注意力的高效混合架构，原生支持 256K 上下文长度，并可扩展至约 100 万个 token。",
    "zh-TW": "Qwen3.5-27B 是 Qwen 團隊開發的原生多模態大型語言模型，擁有 270 億參數。它採用高效的混合架構，結合門控增量網絡和門控注意力，原生支持 256K 上下文長度，並可擴展至約 100 萬個標記。",
    "ja-JP": "Qwen3.5-27BはQwenチームによるネイティブなマルチモーダル大規模言語モデルで、総パラメータ数は270億です。効率的なハイブリッドアーキテクチャ（Gated Delta NetworksとGated Attentionの組み合わせ）を採用し、256Kの文脈長をネイティブにサポートし、約100万トークンまで拡張可能です。",
    "ru-RU": "Qwen3.5-27B — это нативная мультимодальная крупная языковая модель от команды Qwen с 27 миллиардами параметров. Она использует эффективную гибридную архитектуру, объединяющую Gated Delta Networks и Gated Attention, нативно поддерживает длину контекста 256K с возможностью расширения до примерно 1 миллиона токенов."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.706568064",
     "new": "0.706230336"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088321008",
     "new": "0.088278792"
    },
    {
     "date": "2026-07-08",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707058912",
     "new": "0.706568064"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088382364",
     "new": "0.088321008"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707804256",
     "new": "0.707058912"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088475532",
     "new": "0.088382364"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707948784",
     "new": "0.707804256"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088493598",
     "new": "0.088475532"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707698176",
     "new": "0.707948784"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088462272",
     "new": "0.088493598"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.70645896",
     "new": "0.707698176"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.08830737",
     "new": "0.088462272"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.706497936",
     "new": "0.70645896"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088312242",
     "new": "0.08830737"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Anko",
   "model_name": "Qwen3.5-27B-Anko",
   "display_name": "Qwen3.5 27B Anko",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Anko"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-BlueStar-Derestricted",
   "model_name": "Qwen3.5-27B-BlueStar-Derestricted",
   "display_name": "Qwen3.5 27B BlueStar Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-06",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B BlueStar Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-BlueStar-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-BlueStar-Derestricted-Lite",
   "display_name": "Qwen3.5 27B BlueStar Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-06",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B BlueStar Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-BlueStar-v2-Derestricted",
   "model_name": "Qwen3.5-27B-BlueStar-v2-Derestricted",
   "display_name": "Qwen3.5 27B BlueStar v2 Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-06",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B BlueStar v2 Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-BlueStar-v2-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-BlueStar-v2-Derestricted-Lite",
   "display_name": "Qwen3.5 27B BlueStar v2 Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-06",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B BlueStar v2 Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-BlueStar-v3-Derestricted",
   "model_name": "Qwen3.5-27B-BlueStar-v3-Derestricted",
   "display_name": "Qwen3.5 27B BlueStar v3 Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B BlueStar v3 Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-BlueStar-v3-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-BlueStar-v3-Derestricted-Lite",
   "display_name": "Qwen3.5 27B BlueStar v3 Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B BlueStar v3 Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled",
   "model_name": "Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled",
   "display_name": "Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088278792"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.706230336"
      }
     }
    }
   ],
   "released_at": "2026-04-02",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.706568064",
     "new": "0.706230336"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088321008",
     "new": "0.088278792"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707058912",
     "new": "0.706568064"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088382364",
     "new": "0.088321008"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707804256",
     "new": "0.707058912"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088475532",
     "new": "0.088382364"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707948784",
     "new": "0.707804256"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088493598",
     "new": "0.088475532"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707698176",
     "new": "0.707948784"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088462272",
     "new": "0.088493598"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.70645896",
     "new": "0.707698176"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.08830737",
     "new": "0.088462272"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Derestricted",
   "model_name": "Qwen3.5-27B-Derestricted",
   "display_name": "Qwen3.5 27B Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-03-17",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-earica-Derestricted",
   "model_name": "Qwen3.5-27B-earica-Derestricted",
   "display_name": "Qwen3.5 27B earica Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B earica Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-earica-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-earica-Derestricted-Lite",
   "display_name": "Qwen3.5 27B earica Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B earica Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Infracelestial",
   "model_name": "Qwen3.5-27B-Infracelestial",
   "display_name": "Qwen3.5 27B Infracelestial",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Infracelestial"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Lora",
   "model_name": "Qwen3.5-27B-Lora",
   "display_name": "Qwen3.5-27B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-27B-Lora"
    }
   ],
   "max_input_tokens": 262144,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-27B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-27B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Marvin-DPO-V2-Derestricted",
   "model_name": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted",
   "display_name": "Qwen3.5 27B Marvin DPO V2 Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Marvin DPO V2 Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Marvin-DPO-V2-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-Marvin-DPO-V2-Derestricted-Lite",
   "display_name": "Qwen3.5 27B Marvin DPO V2 Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Marvin DPO V2 Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Marvin-V2-Derestricted",
   "model_name": "Qwen3.5-27B-Marvin-V2-Derestricted",
   "display_name": "Qwen3.5 27B Marvin V2 Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Marvin V2 Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Marvin-V2-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-Marvin-V2-Derestricted-Lite",
   "display_name": "Qwen3.5 27B Marvin V2 Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Marvin V2 Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Musica-v1",
   "model_name": "Qwen3.5-27B-Musica-v1",
   "display_name": "Qwen3.5 27B Musica v1",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-03-27",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "music_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Musica v1"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-NaNovel-Derestricted",
   "model_name": "Qwen3.5-27B-NaNovel-Derestricted",
   "display_name": "Qwen3.5 27B NaNovel Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B NaNovel Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-NaNovel-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-NaNovel-Derestricted-Lite",
   "display_name": "Qwen3.5 27B NaNovel Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B NaNovel Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted",
   "model_name": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted",
   "display_name": "Qwen3.5 27B Omega Evolution v2.0 Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-06",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Omega Evolution v2.0 Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-Omega-Evolution-v2.0-Derestricted-Lite",
   "display_name": "Qwen3.5 27B Omega Evolution v2.0 Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-06",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Omega Evolution v2.0 Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted",
   "model_name": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted",
   "display_name": "Qwen3.5 27B Omega Evolution v2.2 Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Omega Evolution v2.2 Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-Omega-Evolution-v2.2-Derestricted-Lite",
   "display_name": "Qwen3.5 27B Omega Evolution v2.2 Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Omega Evolution v2.2 Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Queen-Derestricted",
   "model_name": "Qwen3.5-27B-Queen-Derestricted",
   "display_name": "Qwen3.5 27B Queen Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Queen Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Queen-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-Queen-Derestricted-Lite",
   "display_name": "Qwen3.5 27B Queen Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Queen Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-RpRMax-v1",
   "model_name": "Qwen3.5-27B-RpRMax-v1",
   "display_name": "Qwen3.5 27B RpRMax v1",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B RpRMax v1"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Vivid-Durian",
   "model_name": "Qwen3.5-27B-Vivid-Durian",
   "display_name": "Qwen3.5 27B Vivid Durian",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-03-18",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Vivid Durian"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Writer-Derestricted",
   "model_name": "Qwen3.5-27B-Writer-Derestricted",
   "display_name": "Qwen3.5 27B Writer Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-06",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Writer Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Writer-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-Writer-Derestricted-Lite",
   "display_name": "Qwen3.5 27B Writer Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-06",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Writer Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Writer-V2-Derestricted",
   "model_name": "Qwen3.5-27B-Writer-V2-Derestricted",
   "display_name": "Qwen3.5 27B Writer V2 Derestricted",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-06",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Writer V2 Derestricted"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-27B-Writer-V2-Derestricted-Lite",
   "model_name": "Qwen3.5-27B-Writer-V2-Derestricted-Lite",
   "display_name": "Qwen3.5 27B Writer V2 Derestricted Lite",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-06",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 27B Writer V2 Derestricted Lite"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-2B",
   "model_name": "Qwen3.5-2B",
   "display_name": "deepinfra/Qwen/Qwen3.5-2B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-2B"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3.5-2B"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 81920,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "released_at": "2026-05-27",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-2B",
    "deepinfra/Qwen/Qwen3.5-2B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra/Qwen/Qwen3.5-2B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-2B-Lora",
   "model_name": "Qwen3.5-2B-Lora",
   "display_name": "Qwen3.5-2B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-2B-Lora"
    }
   ],
   "max_input_tokens": 262144,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-2B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-2B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-35b-a3b",
   "model_name": "qwen3.5-35b-a3b",
   "display_name": "Qwen3.5 35B-A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.235294"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "1.882353"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.46"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0564"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4512"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.057"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.459"
      }
     }
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "qwen/qwen3.5-35b-a3b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-35B-A3B"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-35B-A3B"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "qwen/qwen3.5-35b-a3b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "qwen/qwen3.5-35b-a3b"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "qwen/qwen3.5-35b-a3b"
    },
    {
     "provider": "mixlayer",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "qwen/qwen3.5-35b-a3b"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058852528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.470820224"
      }
     },
     "provider_model_id": "Qwen3.5-35B-A3B"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.225"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "qwen3.5-35b-a3b:thinking"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "qwen/qwen3.5-35b-a3b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "qwen/qwen3.5-35b-a3b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "qwen/qwen3.5-35b-a3b"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.057"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.459"
      }
     },
     "provider_model_id": "qwen/qwen3.5-35b-a3b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3.5-35B-A3B"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.235294"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "1.882353"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-35B-A3B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-35B-A3B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-35B-A3B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-35B-A3B"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1625"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1625"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.1625"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.1625"
      }
     },
     "provider_model_id": "qwen/qwen3.5-35b-a3b"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15625"
      }
     },
     "provider_model_id": "qwen3-5-35b-a3b"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-35B-A3B"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-23",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2025-04",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "docs_url": "https://openrouter.ai/qwen/qwen3.5-35b-a3b",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95,
     "top_k": 20
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-35B-A3B",
    "Qwen3.5-35B-A3B",
    "deepinfra/Qwen/Qwen3.5-35B-A3B",
    "qwen/qwen3.5-35b-a3b",
    "qwen3-5-35b-a3b",
    "qwen3.5-35b-a3b:thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.5-35B-A3B 是 Qwen 团队开发的原生多模态大语言模型，具有 350 亿总参数，仅 30 亿激活参数。它采用结合门控增量网络和稀疏专家混合（MoE）的高效混合架构，原生支持 256K 上下文长度，并可扩展至约 100 万个 token。",
    "zh-TW": "Qwen3.5-35B-A3B 是 Qwen 團隊開發的原生多模態大型語言模型，擁有 350 億總參數，僅 30 億激活參數。它採用高效的混合架構，結合門控增量網絡和稀疏專家混合（MoE），原生支持 256K 上下文長度，並可擴展至約 100 萬個標記。",
    "ja-JP": "Qwen3.5-35B-A3BはQwenチームによるネイティブなマルチモーダル大規模言語モデルで、総パラメータ数は350億、アクティブパラメータ数は30億です。効率的なハイブリッドアーキテクチャ（Gated Delta NetworksとSparse Mixture-of-Experts（MoE）の組み合わせ）を採用し、256Kの文脈長をネイティブにサポートし、約100万トークンまで拡張可能です。",
    "ru-RU": "Qwen3.5-35B-A3B — это нативная мультимодальная крупная языковая модель от команды Qwen с общим количеством параметров 35 миллиардов и только 3 миллиардами активных параметров. Она использует эффективную гибридную архитектуру, объединяющую Gated Delta Networks и Sparse Mixture-of-Experts (MoE), нативно поддерживает длину контекста 256K с возможностью расширения до примерно 1 миллиона токенов."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471045376",
     "new": "0.470820224"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058880672",
     "new": "0.058852528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471372608",
     "new": "0.471045376"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058921576",
     "new": "0.058880672"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471869504",
     "new": "0.471372608"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058983688",
     "new": "0.058921576"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471965856",
     "new": "0.471869504"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058995732",
     "new": "0.058983688"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471798784",
     "new": "0.471965856"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058974848",
     "new": "0.058995732"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.47097264",
     "new": "0.471798784"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.05887158",
     "new": "0.058974848"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.470998624",
     "new": "0.47097264"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058874828",
     "new": "0.05887158"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-35B-A3B-Base-Lora",
   "model_name": "Qwen3.5-35B-A3B-Base-Lora",
   "display_name": "Qwen3.5-35B-A3B-Base-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-35B-A3B-Base-Lora"
    }
   ],
   "max_input_tokens": 262144,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-35B-A3B-Base-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-35B-A3B-Base-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-35B-A3B-Lora",
   "model_name": "Qwen3.5-35B-A3B-Lora",
   "display_name": "Qwen3.5-35B-A3B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-35B-A3B-Lora"
    }
   ],
   "max_input_tokens": 262144,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-35B-A3B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-35B-A3B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-397b",
   "model_name": "qwen3.5-397b",
   "display_name": "Qwen3.5 397B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.69"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1725"
      }
     }
    }
   ],
   "max_input_tokens": 262128,
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 397B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-397b-a17b",
   "model_name": "qwen3.5-397b-a17b",
   "display_name": "Qwen3.5 397B-A17B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "1.058824"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.171"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.03"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1644"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9864"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.58"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.58"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.53"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.34"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b"
    },
    {
     "provider": "mixlayer",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.385"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.45"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.111"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.172"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.032"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.25"
      }
     },
     "provider_model_id": "Qwen3.5-397B-A17B"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6061"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6364"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17390999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.04348"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "deepinfra/Qwen/Qwen3.5-397B-A17B"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "qwen3-5-397b-a17b"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.705882"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.34"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.74"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+litellm+truefoundry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3399999999999994"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "qwen3-5-397b-a17b"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B"
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      }
     },
     "provider_model_id": "Qwen3.5-397B-A17B"
    },
    {
     "provider": "wafer-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "Qwen3.5-397B-A17B"
    },
    {
     "provider": "wafer.ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen3.5-397B-A17B"
    }
   ],
   "intro": "Large open Qwen multimodal MoE for visual agents and long technical tasks",
   "released_at": "2026-02-15",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "knowledge_cutoff": "2025-04",
   "model_type": "deep_thinking",
   "docs_url": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B",
   "benchmarks": {
    "intelligence_index": 33.7,
    "coding_index": 48.2,
    "agentic_index": 19.8
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.6,
     "top_p": 0.95,
     "top_k": 20
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-397B-A17B",
    "Qwen3.5-397B-A17B",
    "TEE/qwen3.5-397b-a17b",
    "deepinfra/Qwen/Qwen3.5-397B-A17B",
    "nebius/qwen/qwen3.5-397b-a17b",
    "novita/qwen/qwen3.5-397b-a17b",
    "qwen/qwen3.5-397b-a17b",
    "qwen3-5-397b-a17b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.5-397B-A17B 是 Qwen3.5 系列中最新的视觉语言模型，采用专家混合（MoE）架构，具有 3970 亿总参数和 170 亿激活参数。它原生支持 256K 上下文长度，并可扩展至约 100 万个 token，支持 201 种语言，提供统一的视觉语言理解、工具调用和推理能力。",
    "zh-TW": "Qwen3.5-397B-A17B 是 Qwen3.5 系列中最新的視覺語言模型，採用專家混合（MoE）架構，擁有 3970 億總參數和 170 億激活參數。它原生支持 256K 上下文長度，並可擴展至約 100 萬個標記，支持 201 種語言，提供統一的視覺語言理解、工具調用和推理能力。",
    "ja-JP": "Qwen3.5-397B-A17BはQwen3.5シリーズの最新のビジョンと言語モデルで、Mixture-of-Experts（MoE）アーキテクチャを採用し、総パラメータ数は3970億、アクティブパラメータ数は170億です。256Kの文脈長をネイティブにサポートし、約100万トークンまで拡張可能で、201言語をサポートし、統一されたビジョンと言語の理解、ツール呼び出し、推論能力を提供します。",
    "ru-RU": "Qwen3.5-397B-A17B — это последняя модель в серии Qwen3.5 для понимания языка и изображений, использующая архитектуру Mixture-of-Experts (MoE) с общим количеством параметров 397 миллиардов и 17 миллиардами активных параметров. Она нативно поддерживает длину контекста 256K с возможностью расширения до примерно 1 миллиона токенов, поддерживает 201 язык и предоставляет унифицированные возможности понимания языка и изображений, вызова инструментов и рассуждений."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "openrouter",
     "charge": "cache_read",
     "old": "0.195",
     "new": "0.111"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-397B-A17B-fast",
   "model_name": "Qwen3.5-397B-A17B-fast",
   "display_name": "Qwen3.5-397B-A17B-fast",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B-fast"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-07-15",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 8000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-397B-A17B-fast"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-397B-A17B-fast"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-397B-A17B-FP4",
   "model_name": "Qwen3.5-397B-A17B-FP4",
   "display_name": "Qwen3.5-397B-A17B-FP4",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B-FP4"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-397B-A17B-FP4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-397B-A17B-FP4"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-397B-A17B-FP8",
   "model_name": "Qwen3.5-397B-A17B-FP8",
   "display_name": "Qwen3.5 397B A17B FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.69"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1725"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B-FP8"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B-FP8"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2026-02-01",
   "max_input_tokens": 262128,
   "max_output_tokens": 262128,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-397B-A17B-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 397B A17B FP8"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-397B-A17B-Lora",
   "model_name": "Qwen3.5-397B-A17B-Lora",
   "display_name": "Qwen3.5-397B-A17B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B-Lora"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-397B-A17B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-397B-A17B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-397B-A17B-TEE",
   "model_name": "Qwen3.5-397B-A17B-TEE",
   "display_name": "Qwen3.5 397B A17B TEE",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.225"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-397B-A17B-TEE"
    }
   ],
   "intro": "Large open Qwen multimodal MoE for visual agents and long technical tasks",
   "released_at": "2026-02-15",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-397B-A17B-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 397B A17B TEE"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-397b-a17b-thinking",
   "model_name": "qwen3.5-397b-a17b-thinking",
   "display_name": "Qwen3.5 397B A17B Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "qwen/qwen3.5-397b-a17b-thinking"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-16",
   "max_input_tokens": 258048,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3.5-397b-a17b-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 397B A17B Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-397b-fast",
   "model_name": "qwen3.5-397b-fast",
   "display_name": "Qwen3.5 397B Fast",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.69"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1725"
      }
     }
    }
   ],
   "intro": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
   "released_at": "2026-02-01",
   "max_input_tokens": 262128,
   "max_output_tokens": 262128,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 397B Fast"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-4B",
   "model_name": "Qwen3.5-4B",
   "display_name": "Qwen/Qwen3.5-4B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-4B"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-4B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-4B"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-03-03",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "open_weights": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-4B"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.5-4B 是 Qwen 团队开发的原生多模态大语言模型，具有 40 亿参数，是 Qwen3.5 系列中最轻量的 Dense 模型。它采用结合门控增量网络和门控注意力的高效混合架构，原生支持 256K 上下文长度，并可扩展至约 100 万个 token。",
    "zh-TW": "Qwen3.5-4B 是 Qwen 團隊開發的原生多模態大型語言模型，擁有 40 億參數，是 Qwen3.5 系列中最輕量的 Dense 模型。它採用高效的混合架構，結合門控增量網絡和門控注意力，原生支持 256K 上下文長度，並可擴展至約 100 萬個標記。",
    "ja-JP": "Qwen3.5-4BはQwenチームによるネイティブなマルチモーダル大規模言語モデルで、総パラメータ数は40億です。Qwen3.5シリーズで最も軽量なDenseモデルであり、効率的なハイブリッドアーキテクチャ（Gated Delta NetworksとGated Attentionの組み合わせ）を採用しています。256Kの文脈長をネイティブにサポートし、約100万トークンまで拡張可能です。",
    "ru-RU": "Qwen3.5-4B — это нативная мультимодальная крупная языковая модель от команды Qwen с 4 миллиардами параметров, являющаяся самой легкой плотной моделью в серии Qwen3.5. Она использует эффективную гибридную архитектуру, объединяющую Gated Delta Networks и Gated Attention, нативно поддерживает длину контекста 256K с возможностью расширения до примерно 1 миллиона токенов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3.5-4B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-4b-el",
   "model_name": "qwen3.5-4b-el",
   "display_name": "Qwen3.5-4B-EL",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0404"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0707"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0202"
      }
     }
    }
   ],
   "released_at": "2026-05-17",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-4B-EL"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-4B-Lora",
   "model_name": "Qwen3.5-4B-Lora",
   "display_name": "Qwen3.5-4B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-4B-Lora"
    }
   ],
   "max_input_tokens": 262144,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-4B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-4B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-9b-el",
   "model_name": "qwen3.5-9b-el",
   "display_name": "Qwen3.5-9B-EL",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0909"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1313"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0455"
      }
     }
    }
   ],
   "released_at": "2026-05-17",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-9B-EL"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-9B-FP8",
   "model_name": "Qwen3.5-9B-FP8",
   "display_name": "Qwen3.5-9B-FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-9B-FP8"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 81920,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-9B-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-9B-FP8"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.5-9B-Lora",
   "model_name": "Qwen3.5-9B-Lora",
   "display_name": "Qwen3.5-9B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-9B-Lora"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-9B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5-9B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-flash-02-23",
   "model_name": "qwen3.5-flash-02-23",
   "display_name": "Qwen: Qwen3.5-Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen/qwen3.5-flash-02-23"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.065"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0813"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0065"
      }
     },
     "provider_model_id": "qwen/qwen3.5-flash-02-23"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-26",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "family": "qwen",
   "docs_url": "https://openrouter.ai/qwen/qwen3.5-flash-02-23",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3.5-flash-02-23"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen: Qwen3.5-Flash"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-flash:thinking",
   "model_name": "qwen3.5-flash:thinking",
   "display_name": "Qwen3.5 Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.172"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.72"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005882"
      }
     },
     "provider_model_id": "qwen3.5-flash",
     "tracks": [
      {
       "label": ">256000000K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "6.976744",
        "completion": "6.976744",
        "cache_read": "6"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">128000000K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.651163",
        "completion": "4.651163",
        "cache_read": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "qwen3.5-flash"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0282"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.282"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.00282"
      }
     },
     "provider_model_id": "qwen3.5-flash"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.172"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.72"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.72"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.036"
      }
     },
     "provider_model_id": "qwen3.5-flash"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "qwen/qwen3.5-flash"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029426264"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29426264"
      }
     },
     "provider_model_id": "Qwen3.5-Flash"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "qwen3.5-flash"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen/qwen3.5-flash"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0909"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3717"
      }
     },
     "provider_model_id": "qwen3.5-flash"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1048"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4194"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1048"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1048"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.1048"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.1048"
      }
     },
     "provider_model_id": "qwen/qwen3.5-flash"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.001"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "alibaba/qwen3.5-flash"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "qwen/qwen3.5-flash"
    }
   ],
   "released_at": "2026-02-23",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "structured_output": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true,
    "web_search": true
   },
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "reasoning_config": {
    "budget_min": 1
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen3.5-Flash",
    "alibaba/qwen3.5-flash",
    "qwen/qwen3.5-flash",
    "qwen/qwen3.5-flash-2026-02-23",
    "qwen3.5-flash",
    "qwen3.5-flash-2026-02-23"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.5 原生视觉语言 Flash 模型基于线性注意力机制与稀疏 Mixture-of-Experts（MoE）混合架构构建，推理效率更高。相较于 3 系列，无论在纯文本任务还是多模态任务上均有大幅性能提升，同时具备更快响应速度，在推理速度与整体能力之间实现良好平衡。",
    "zh-TW": "Qwen3.5 原生視覺語言 Flash 模型採用結合線性注意力機制與稀疏 Mixture-of-Experts（MoE）設計的混合架構，在推理效率上更具優勢。相較於 3 系列，在純文字與多模態表現上均有大幅提升，同時具備快速回應能力，兼顧推理速度與整體效能。",
    "ja-JP": "Qwen3.5 ネイティブ視覚言語 Flash モデルは、線形アテンション機構とスパース MoE を組み合わせたハイブリッド構造により、高い推論効率を実現しています。3 シリーズと比べてテキスト・マルチモーダル性能が大幅に向上し、高速応答と性能のバランスを両立しています。",
    "ru-RU": "Нативная модель Qwen3.5 Flash для работы с визуально-языковыми данными построена на гибридной архитектуре, сочетающей механизм линейного внимания и разреженный Mixture-of-Experts (MoE), что обеспечивает более высокую эффективность вывода. По сравнению с серией 3 модель значительно улучшает качество работы как в текстовых, так и в мультимодальных задачах. Она также отличается быстрым временем отклика, сочетая скорость вывода и общую мощность."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.29440336",
     "new": "0.29426264"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.029440336",
     "new": "0.029426264"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.29460788",
     "new": "0.29440336"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.029460788",
     "new": "0.029440336"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.29491844",
     "new": "0.29460788"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.029491844",
     "new": "0.029460788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.29497866",
     "new": "0.29491844"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.029497866",
     "new": "0.029491844"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.29487424",
     "new": "0.29497866"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.029487424",
     "new": "0.029497866"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.2943579",
     "new": "0.29487424"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.02943579",
     "new": "0.029487424"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 Flash"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-omni-flash",
   "model_name": "qwen3.5-omni-flash",
   "display_name": "Qwen3.5 Omni Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.323529"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.323529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.955882"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10.588235"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2026-03-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "model_type": "omni",
   "capabilities": {
    "web_search": true,
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true
   },
   "intro": "Omni-modal model for text, vision, audio, and multimodal agent tasks",
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen3.5 Omni Flash 是一款快速、经济高效的全模态 Qwen 模型，支持文本、图像和视频输入。",
    "zh-TW": "Qwen3.5 Omni Flash 是一款快速、成本效益高的全模態 Qwen 模型，支持文本、圖像和視頻輸入。",
    "ja-JP": "Qwen3.5 Omni Flashは、テキスト、画像、動画入力をサポートする高速かつコスト効率の高いフルモーダルQwenモデルです。",
    "ru-RU": "Qwen3.5 Omni Flash — это быстрая, экономичная полноформатная модель Qwen, поддерживающая ввод текста, изображений и видео."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 Omni Flash"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-omni-plus",
   "model_name": "qwen3.5-omni-plus",
   "display_name": "Qwen3.5 Omni Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "7.794118"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.882353"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "31.323529"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.7143"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "7.5714"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "4.018886863724014"
      }
     }
    }
   ],
   "released_at": "2026-03-30",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "model_type": "omni",
   "capabilities": {
    "web_search": true,
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "intro": "Omni-modal model for text, vision, audio, and multimodal agent tasks",
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen3.5 Omni Plus 支持文本、图像和视频输入，是最新的高质量多模态理解与生成的全模态 Qwen 模型。",
    "zh-TW": "Qwen3.5 Omni Plus 支持文本、圖像和視頻輸入，是最新的高品質多模態理解與生成的全模態 Qwen 模型。",
    "ja-JP": "Qwen3.5 Omni Plusは、テキスト、画像、動画入力をサポートします。高品質なマルチモーダル理解と生成のための最新のフルモーダルQwenモデルです。",
    "ru-RU": "Qwen3.5 Omni Plus поддерживает ввод текста, изображений и видео. Это новейшая полноформатная модель Qwen для высококачественного мультимодального понимания и генерации."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 Omni Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-plus",
   "model_name": "qwen3.5-plus",
   "display_name": "Qwen3.5 Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.011765"
      },
      "cache_read_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "cache_read_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "cache_write_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "cache_write_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      },
      "cache_write_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.705882"
      },
      "completion_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     },
     "provider_model_id": "qwen3.5-plus-2026-04-20"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.69"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01096"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.573"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.44"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3.44"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.012"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.143"
      }
     },
     "provider_model_id": "qwen3.5-plus-2026-02-15"
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "qwen/qwen3.5-plus-20260420"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "Qwen/Qwen3.5-Plus"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "qwen/qwen3.5-plus"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "qwen/qwen3.5-plus-20260420"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.115"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.688"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "qwen/qwen3.5-plus"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3636"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2303"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11594"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.69565"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02319"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.14493"
      }
     },
     "provider_model_id": "qwen/qwen3.5-plus"
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.705882"
      },
      "completion_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion_0_256_infinity": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     },
     "provider_model_id": "Qwen3.5-Plus"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "alibaba/qwen3.5-plus",
     "tracks": [
      {
       "label": ">256.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3",
        "completion": "3",
        "cache_read": "3",
        "cache_write": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "qwen/qwen3.5-plus"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-16",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "deprecated": true,
   "status": "deprecated",
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.5-Plus",
    "Qwen3.5-Plus",
    "alibaba/qwen3.5-plus",
    "qwen/qwen3.5-plus",
    "qwen/qwen3.5-plus-2026-02-15",
    "qwen/qwen3.5-plus-20260420",
    "qwen3.5-plus-2026-02-15",
    "qwen3.5-plus-2026-04-20"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.5 Plus 支持文本、图像与视频输入，在纯文本任务上的表现可比肩 Qwen3 Max，且成本更低。其多模态能力相较 Qwen3 VL 系列有显著提升。",
    "zh-TW": "Qwen3.5 Plus 支援文字、影像與影片輸入，在純文字任務上的效能接近 Qwen3 Max，但成本更低、表現更佳；多模態能力也較 Qwen3 VL 系列大幅提升。",
    "ja-JP": "Qwen3.5 Plus はテキスト、画像、動画入力に対応します。テキストタスクの性能は Qwen3 Max と同等で、より高性能かつ低コストです。マルチモーダル能力は Qwen3 VL シリーズより大幅に向上しています。",
    "ru-RU": "Qwen3.5 Plus поддерживает ввод текста, изображений и видео. Производительность в текстовых задачах сопоставима с Qwen3 Max, но модель быстрее и дешевле. Мультимодальные возможности значительно улучшены по сравнению с серией Qwen3 VL."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-plus-02-15",
   "model_name": "qwen3.5-plus-02-15",
   "display_name": "Qwen: Qwen3.5 Plus 2026-02-15",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.56"
      }
     },
     "provider_model_id": "qwen/qwen3.5-plus-02-15"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.56"
      }
     },
     "provider_model_id": "qwen/qwen3.5-plus-02-15",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.923077",
        "completion": "1.923077"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.56"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "qwen/qwen3.5-plus-02-15"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-15",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-04",
   "family": "qwen",
   "docs_url": "https://openrouter.ai/qwen/qwen3.5-plus-02-15",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3.5-plus-02-15"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen: Qwen3.5 Plus 2026-02-15"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5-plus-thinking",
   "model_name": "qwen3.5-plus-thinking",
   "display_name": "Qwen3.5 Plus Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "qwen/qwen3.5-plus-thinking"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-16",
   "max_input_tokens": 983616,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3.5-plus-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 Plus Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.5:397b",
   "model_name": "qwen3.5:397b",
   "display_name": "qwen3.5:397b",
   "vendor": "alibaba",
   "pricing": [],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-15",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Qwen3.5 是一款统一的视觉-语言基础模型，采用混合架构（专家混合 + 线性注意力），在 256K 上下文窗口内提供强大的多模态推理、编码和长上下文能力。",
    "zh-TW": "Qwen3.5 是一款統一的視覺-語言基礎模型，採用混合架構（專家混合 + 線性注意力），提供強大的多模態推理、編程及長上下文能力，支持 256K 上下文窗口。",
    "ja-JP": "Qwen3.5は、ハイブリッドアーキテクチャ（Mixture-of-Experts + 線形注意）を備えた統一的なビジョン・言語基盤モデルで、強力なマルチモーダル推論、コーディング、長文コンテキスト能力を提供し、256Kのコンテキストウィンドウをサポートします。",
    "ru-RU": "Qwen3.5 — это унифицированная модель для работы с текстом и изображениями с гибридной архитектурой (Mixture-of-Experts + линейное внимание), предлагающая сильные мультимодальные возможности рассуждения, программирования и работы с длинным контекстом с окном 256K."
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3.5:397b"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-27b",
   "model_name": "qwen3.6-27b",
   "display_name": "Qwen3.6 27B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.422"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.532"
      }
     }
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "qwen/qwen3.6-27b"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.7"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "qwen/qwen3.6-27b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.19"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.403"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.09"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2015"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.325"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.25"
      }
     },
     "provider_model_id": "qwen/qwen3.6-27b"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088278792"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.706230336"
      }
     },
     "provider_model_id": "Qwen3.6-27B"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.203"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.24"
      }
     },
     "provider_model_id": "alibaba/qwen3.6-27b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "qwen/qwen3.6-27b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.285"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "qwen/qwen3.6-27b"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.19"
      }
     },
     "provider_model_id": "Qwen3.6-27B"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33391"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.33913"
      }
     },
     "provider_model_id": "qwen/qwen3.6-27b"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     },
     "provider_model_id": "route/qwen3.6-27b"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.705882"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "2.117647"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B"
    },
    {
     "provider": "stackit",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.76"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "hf:Qwen/Qwen3.6-27B"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.325"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.25"
      }
     },
     "provider_model_id": "qwen3-6-27b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "alibaba/qwen3.6-27b"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-04-22",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "benchmarks": {
    "intelligence_index": 37.1,
    "coding_index": 53.7,
    "agentic_index": 27
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.6-27B",
    "Qwen3.6-27B",
    "TEE/qwen3.6-27b",
    "alibaba/qwen3.6-27b",
    "alibaba/qwen3.6-27b:thinking",
    "hf:Qwen/Qwen3.6-27B",
    "qwen/qwen3.6-27b",
    "qwen3-6-27b",
    "route/qwen3.6-27b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.6-27B 是 Qwen3.6 系列中首个开源中型密集模型，在代码生成、代理工作流和真实开发场景中具有关键增强功能。与 Qwen3.5-27B 相比，该模型在前端开发、代码库级推理、工具调用和复杂问题解决方面表现显著提升，并新增了历史推理能力优化。",
    "zh-TW": "Qwen3.6-27B 是 Qwen3.6 系列中首個開源中型密集模型，針對代碼生成、代理工作流程和真實世界開發場景進行了關鍵增強。與 Qwen3.5-27B 相比，此模型在前端開發、倉庫級推理、工具調用和複雜問題解決方面顯著提升，並新增了歷史推理能力優化。",
    "ja-JP": "Qwen3.6-27BはQwen3.6シリーズの最初のオープンソース中型密集モデルで、コード生成、エージェントワークフロー、実世界の開発シナリオ向けに重要な強化が施されています。Qwen3.5-27Bと比較して、このモデルはフロントエンド開発、リポジトリレベルの推論、ツール呼び出し、複雑な問題解決において大幅な改善を示し、新たに履歴推論能力の最適化が追加されています。",
    "ru-RU": "Qwen3.6-27B — это первая открытая средняя плотная модель в серии Qwen3.6 с ключевыми улучшениями для генерации кода, рабочих процессов агентов и реальных сценариев разработки. По сравнению с Qwen3.5-27B, эта модель демонстрирует значительные улучшения в разработке интерфейсов, рассуждениях на уровне репозиториев, вызове инструментов и решении сложных задач, с новыми оптимизациями для исторического мышления."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.1984",
     "new": "0.2015"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "3.03",
     "new": "3.09"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.3968",
     "new": "0.403"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.706568064",
     "new": "0.706230336"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088321008",
     "new": "0.088278792"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707058912",
     "new": "0.706568064"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088382364",
     "new": "0.088321008"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.1995",
     "new": "0.1984"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "3.19",
     "new": "3.03"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.399",
     "new": "0.3968"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707804256",
     "new": "0.707058912"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088475532",
     "new": "0.088382364"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.1845",
     "new": "0.1995"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.95",
     "new": "3.19"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.369",
     "new": "0.399"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.707948784",
     "new": "0.707804256"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.088493598",
     "new": "0.088475532"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.1854",
     "new": "0.1845"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "3.03",
     "new": "2.95"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.3708",
     "new": "0.369"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-27b-202k",
   "model_name": "qwen3.6-27b-202k",
   "display_name": "Qwen3.6 27B 202K",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     },
     "provider_model_id": "route/qwen3.6-27b-202k"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-04-22",
   "max_input_tokens": 202000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "route/qwen3.6-27b-202k"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 27B 202K"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.6-27B-FP8",
   "model_name": "Qwen3.6-27B-FP8",
   "display_name": "Qwen 3.6 27B FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nearai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.325"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B-FP8"
    }
   ],
   "released_at": "2026-06-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.6-27B-FP8"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.6 27B FP8"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.6-27B-Lora",
   "model_name": "Qwen3.6-27B-Lora",
   "display_name": "Qwen3.6-27B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B-Lora"
    }
   ],
   "max_input_tokens": 262144,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.6-27B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6-27B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.6-27B-TEE",
   "model_name": "Qwen3.6-27B-TEE",
   "display_name": "Qwen3.6 27B TEE",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-27B-TEE"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-04-22",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.6-27B-TEE"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 27B TEE"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-35b-a3b",
   "model_name": "qwen3.6-35b-a3b",
   "display_name": "Qwen3.6 35B-A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.248"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.485"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.55"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.254"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.524"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.248"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.485"
      }
     }
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "qwen/qwen3.6-35b-a3b"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.31"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18024"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.16305"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09012"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1802"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1631"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0901"
      }
     },
     "provider_model_id": "qwen3-6-35b-a3b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1612"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.96525"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1612"
      }
     },
     "provider_model_id": "qwen/qwen3.6-35b-a3b"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.248"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.485"
      }
     }
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058852528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.470820224"
      }
     },
     "provider_model_id": "Qwen3.6-35B-A3B"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.112"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "qwen/Qwen3.6-35B-A3B"
    },
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0725"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.248"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.485"
      }
     },
     "provider_model_id": "qwen/qwen3.6-35b-a3b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1612"
      }
     },
     "provider_model_id": "qwen/qwen3.6-35b-a3b"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.248"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.485"
      }
     },
     "provider_model_id": "qwen/qwen3.6-35b-a3b"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen3-6-35b-a3b"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.235294"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "1.882353"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B"
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Qwen3.6-35B-A3B"
    },
    {
     "provider": "wafer-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "Qwen3.6-35B-A3B"
    },
    {
     "provider": "wafer.ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen3.6-35B-A3B"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B"
    },
    {
     "provider": "zenifra",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "provider_model_id": "alibaba/qwen3.6-35b-a3b"
    }
   ],
   "intro": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
   "released_at": "2026-04-17",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2025-04",
   "status": "beta",
   "benchmarks": {
    "intelligence_index": 31.6,
    "coding_index": 41.9,
    "agentic_index": 21.4
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95,
     "top_k": 20
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.6-35B-A3B",
    "Qwen/Qwen3.6-35B-A3B:thinking",
    "Qwen3.6-35B-A3B",
    "TEE/qwen3.6-35b-a3b",
    "alibaba/qwen3.6-35b-a3b",
    "qwen/Qwen3.6-35B-A3B",
    "qwen/Qwen3.6-35B-A3B:thinking",
    "qwen/qwen3.6-35b-a3b",
    "qwen3-6-35b-a3b"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.6-35B-A3B 是 Qwen 团队在 Qwen3.6 系列中推出的大语言模型，采用 Mixture-of-Experts（MoE）架构，总参数量为 350 亿，激活参数量为 30 亿。在高效推理与卓越性能之间实现了良好平衡，支持思考模式与非思考模式，可在快速响应与深度推理之间灵活切换。",
    "zh-TW": "Qwen3.6-35B-A3B 是 Qwen 團隊在 Qwen3.6 系列中推出的大型語言模型，採用 Mixture-of-Experts（MoE）架構，具備 350 億總參數與 30 億啟用參數。其兼具高效推理與卓越效能，並支援思考模式與非思考模式，可在快速回應與深度推理間靈活切換。",
    "ja-JP": "Qwen3.6-35B-A3B は、Qwen チームによる Qwen3.6 シリーズの大規模言語モデルで、35B の総パラメータと 3B のアクティブパラメータを備えた Mixture-of-Experts (MoE) アーキテクチャを採用しています。高速推論と優れた性能の両立を図り、思考モードと非思考モードの双方をサポートし、迅速な応答と深い推論を柔軟に切り替えることができます。",
    "ru-RU": "Qwen3.6-35B-A3B — это крупная языковая модель команды Qwen из серии Qwen3.6, использующая архитектуру Mixture-of-Experts (MoE) с общим числом параметров 35B и 3B активных параметров. Она сочетает эффективный вывод с высокой производительностью и поддерживает как режимы с размышлением, так и без него, позволяя гибко переключаться между быстрым ответом и глубоким рассуждением."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471045376",
     "new": "0.470820224"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058880672",
     "new": "0.058852528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471372608",
     "new": "0.471045376"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058921576",
     "new": "0.058880672"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.0814",
     "new": "0.09012"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "1.141313",
     "new": "1.16305"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.1628",
     "new": "0.18024"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.0814",
     "new": "0.0901"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "1.1413",
     "new": "1.1631"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.1628",
     "new": "0.1802"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471869504",
     "new": "0.471372608"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058983688",
     "new": "0.058921576"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471965856",
     "new": "0.471869504"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058995732",
     "new": "0.058983688"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471798784",
     "new": "0.471965856"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058974848",
     "new": "0.058995732"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.47097264",
     "new": "0.471798784"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.05887158",
     "new": "0.058974848"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.470998624",
     "new": "0.47097264"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.058874828",
     "new": "0.05887158"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.6-35B-A3B-FP8",
   "model_name": "Qwen3.6-35B-A3B-FP8",
   "display_name": "Qwen 3.6 35B A3B FP8",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.345"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.38"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B-FP8"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.056"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B-FP8"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B-FP8"
    }
   ],
   "intro": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
   "released_at": "2026-04-17",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.6-35B-A3B-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.6 35B A3B FP8"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.6-35B-A3B-Lora",
   "model_name": "Qwen3.6-35B-A3B-Lora",
   "display_name": "Qwen3.6-35B-A3B-Lora",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-35B-A3B-Lora"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.6-35B-A3B-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6-35B-A3B-Lora"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-35b-a3b-uncensored",
   "model_name": "qwen3.6-35b-a3b-uncensored",
   "display_name": "Qwen3.6 35B A3B Uncensored TEE",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "TEE/qwen3.6-35b-a3b-uncensored"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-05-23",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TEE/qwen3.6-35b-a3b-uncensored"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 35B A3B Uncensored TEE"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-35b-fast",
   "model_name": "qwen3.6-35b-fast",
   "display_name": "Qwen3.6 35B Fast",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0725"
      }
     }
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2026-04-01",
   "max_input_tokens": 131056,
   "max_output_tokens": 131056,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen3.6",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 35B Fast"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-flash",
   "model_name": "qwen3.6-flash",
   "display_name": "Qwen3.6 Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.234375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035294"
      }
     },
     "tracks": [
      {
       "label": ">256000000K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "25.6",
        "completion": "25.6",
        "cache_read": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.03"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.01"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0169"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.21125"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "4.019802",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "4.019802",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.234375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.017"
      }
     },
     "provider_model_id": "qwen3.6-flash-2026-04-16"
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.234375"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.234375"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3125"
      }
     },
     "provider_model_id": "qwen/qwen3.6-flash"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3.6-flash"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.176557584"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.059345504"
      }
     },
     "provider_model_id": "Qwen3.6-Flash"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.16"
      }
     },
     "provider_model_id": "alibaba/qwen3.6-flash"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.234375"
      }
     },
     "provider_model_id": "qwen/qwen3.6-flash"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "qwen/qwen3.6-flash"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.171"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.0289999999999997"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.016999999999999998"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.21399999999999997"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.171"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.171"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.808302"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0134717"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.16839625"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.134717"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5.38868"
      }
     },
     "provider_model_id": "qwen/qwen3.6-flash"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-04-27",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen3.6",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "knowledge_cutoff": "2025-04",
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen3.6-Flash",
    "alibaba/qwen3.6-flash",
    "qwen/qwen3.6-flash",
    "qwen/qwen3.6-flash-2026-04-16",
    "qwen3.6-flash-2026-04-16"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.6 原生视觉语言 Flash 模型相比 3.5-Flash 具备显著性能提升。该模型重点增强了智能体编码能力（在多项代码智能体基准中大幅领先前代），并进一步提升数学推理与代码推理表现。在视觉方面，空间智能显著增强，尤其在物体定位与目标检测任务上表现突出。",
    "zh-TW": "Qwen3.6 原生視覺語言 Flash 模型的性能相較 3.5-Flash 版本有明顯提升。本模型著重強化代理式程式碼能力（在多項程式代理基準上大幅領先前代），並提升數學推理與程式碼推理能力。在視覺方面，其空間智能獲得顯著增強，尤其在物件定位與目標檢測任務上有卓越表現。",
    "ja-JP": "Qwen3.6 ネイティブ視覚言語 Flash モデルは、3.5-Flash と比べて大幅に性能が向上しています。とくにエージェント型コーディング能力（複数のコードエージェントベンチマークで前世代を大幅に上回る）、数理推論・コード推論が強化されています。視覚面では空間認識能力が向上し、物体位置特定やターゲット検出で顕著な改善が見られます。",
    "ru-RU": "Нативная модель Qwen3.6 Flash для визуально-языковых задач демонстрирует значительно улучшенную производительность по сравнению с версией 3.5-Flash. Она фокусируется на усилении возможностей агентного программирования (существенно превосходя предыдущую версию по множеству бенчмарков), а также улучшает способности к математическим рассуждениям и анализу кода. В области компьютерного зрения модель демонстрирует заметный рост пространственного интеллекта, особенно в задачах локализации объектов и обнаружения целей."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.059852096",
     "new": "1.059345504"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.176642016",
     "new": "0.176557584"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.060588368",
     "new": "1.059852096"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.176764728",
     "new": "0.176642016"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.061706384",
     "new": "1.060588368"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.176951064",
     "new": "0.176764728"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.061923176",
     "new": "1.061706384"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.176987196",
     "new": "0.176951064"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.061547264",
     "new": "1.061923176"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.176924544",
     "new": "0.176987196"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.05968844",
     "new": "1.061547264"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.17661474",
     "new": "0.176924544"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.059746904",
     "new": "1.05968844"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.176624484",
     "new": "0.17661474"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-flash-us",
   "model_name": "qwen3.6-flash-us",
   "display_name": "Qwen3.6-Flash-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3125"
      }
     }
    }
   ],
   "released_at": "2026-07-03",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "Qwen3.6-Flash-US"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3.6-Max",
   "model_name": "Qwen3.6-Max",
   "display_name": "Qwen3.6-Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.32418188"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.94509128"
      }
     }
    }
   ],
   "released_at": "2026-04-22",
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.94889072",
     "new": "7.94509128"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.32481512",
     "new": "1.32418188"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.95441276",
     "new": "7.94889072"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.32573546",
     "new": "1.32481512"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.96279788",
     "new": "7.95441276"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.32713298",
     "new": "1.32573546"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.96442382",
     "new": "7.96279788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.32740397",
     "new": "1.32713298"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.96160448",
     "new": "7.96442382"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.32693408",
     "new": "1.32740397"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.9476633",
     "new": "7.96160448"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.32461055",
     "new": "1.32693408"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6-Max"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-max-preview",
   "model_name": "qwen3.6-max-preview",
   "display_name": "Qwen3.6 Max Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.625"
      },
      "cache_read_0_0_128": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      },
      "cache_read_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt_0_0_128": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion_0_0_128": {
       "unit": "per_M_tokens",
       "price": "7.941176"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "13.235294"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.61"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1268"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.585"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.661417",
        "completion": "1.664915",
        "cache_read": "1.665615",
        "cache_write": "1.665615"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.132"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "qwen/qwen3.6-max-preview"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.625"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.8"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "qwen/qwen3.6-max-preview"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3131"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.8788"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.625"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "qwen/qwen3.6-max-preview",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "1.538462",
        "cache_write": "1.538462"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Flagship Qwen model for complex reasoning, coding, and agentic workflows",
   "released_at": "2026-04-20",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3.6-max-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.6 系列中规模最大的闭源模型。具备更强的世界知识、指令理解能力与智能体编码性能，可处理复杂任务。该模型为纯文本模型，默认支持思考模式、显式缓存与函数调用。",
    "zh-TW": "Qwen3.6 系列中最大的封閉源模型，具備更強的世界知識、指令跟隨能力與代理式程式碼性能，適用於複雜任務。該模型為純文字模式，預設支援思考模式、顯式快取與函式呼叫。",
    "ja-JP": "Qwen3.6 シリーズで最大規模のクローズドソースモデルです。世界知識、指示理解、エージェント型コーディングなど複雑なタスクに対して高い性能を発揮します。テキスト専用で、思考モードがデフォルト有効、明示的なキャッシング、関数呼び出しに対応しています。",
    "ru-RU": "Крупнейшая закрытая модель серии Qwen3.6. Она обеспечивает улучшенные знания о мире, лучшее следование инструкциям и высокую производительность в агентном программировании для сложных задач. Это текстовая модель, по умолчанию поддерживает режим размышления, явное кэширование и вызов функций."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-plus",
   "model_name": "qwen3.6-plus",
   "display_name": "Qwen3.6 Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+lobehub-modelbank+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "prompt_0_0_256": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_256_1": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_0_256": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion_0_256_1": {
       "unit": "per_M_tokens",
       "price": "7.058824"
      },
      "cache_read_0_0_256": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "cache_read_0_256_1": {
       "unit": "per_M_tokens",
       "price": "0.235294"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.69"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0282"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3525"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.035714",
        "completion": "4.005917",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.035714",
        "completion": "4.005917",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "qwen3.6-plus-2026-04-02",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.325"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0325"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.40625"
      }
     },
     "provider_model_id": "qwen/qwen3.6-plus"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "alibaba/qwen3.6-plus"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.17705056"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.06230336"
      }
     },
     "provider_model_id": "Qwen3.6-Plus"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "qwen3.6-plus-free"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     }
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.325"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.95"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.40625"
      }
     },
     "provider_model_id": "qwen/qwen3.6-plus"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "qwen/qwen3.6-plus",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5051"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.0303"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.73913"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05797"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.36232000000000003"
      }
     },
     "provider_model_id": "qwen/qwen3.6-plus"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "alibaba/qwen3.6-plus"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "Qwen/Qwen3.6-Plus"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.21"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.54"
      }
     },
     "provider_model_id": "qwen/qwen3.6-plus"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "alibaba/qwen3.6-plus",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "2",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "qwen/qwen3.6-plus",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
   "released_at": "2026-04-02",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://openrouter.ai/qwen/qwen3.6-plus",
   "benchmarks": {
    "intelligence_index": 39.6,
    "coding_index": 54.5,
    "agentic_index": 27.6
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.6-Plus",
    "Qwen3.6-Plus",
    "alibaba/qwen3.6-plus",
    "fireworks/qwen3.6-plus",
    "qwen/qwen3.6-plus",
    "qwen/qwen3.6-plus-2026-04-02",
    "qwen/qwen3.6-plus:free",
    "qwen3.6-plus-2026-04-02",
    "qwen3.6-plus-free",
    "stealth/qwen3.6-plus"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.6 Plus支持文本、图像和视频输入，在质量、速度和成本之间实现了平衡性能。与Qwen3 VL系列相比，其多模态能力显著提升。",
    "zh-TW": "Qwen3.6 Plus 支持文本、影像和視頻輸入。在質量、速度和成本方面提供平衡的性能。與 Qwen3 VL 系列相比，其多模態能力顯著提升。",
    "ja-JP": "Qwen3.6 Plusはテキスト、画像、動画入力をサポートします。品質、速度、コストのバランスが取れた性能を提供し、Qwen3 VLシリーズと比較してマルチモーダル機能が大幅に向上しています。",
    "ru-RU": "Qwen3.6 Plus поддерживает ввод текста, изображений и видео. Она обеспечивает сбалансированную производительность по качеству, скорости и стоимости. Её мультимодальные возможности значительно улучшены по сравнению с серией Qwen3 VL."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.06568064",
     "new": "7.06230336"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17761344",
     "new": "1.17705056"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.07058912",
     "new": "7.06568064"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17843152",
     "new": "1.17761344"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.07804256",
     "new": "7.07058912"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17967376",
     "new": "1.17843152"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.07948784",
     "new": "7.07804256"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17991464",
     "new": "1.17967376"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.07698176",
     "new": "7.07948784"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17949696",
     "new": "1.17991464"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.0645896",
     "new": "7.07698176"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.1774316",
     "new": "1.17949696"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "7.06497936",
     "new": "7.0645896"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17749656",
     "new": "1.1774316"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-plus-256k",
   "model_name": "qwen3.6-plus-256k",
   "display_name": "Qwen3.6 Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.6-plus-preview:free",
   "model_name": "qwen3.6-plus-preview:free",
   "display_name": "qwen3.6-plus-preview:free",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen/qwen3.6-plus-preview:free"
    }
   ],
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwen/qwen3.6-plus-preview:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwen3.6-plus-preview:free"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.7",
   "model_name": "qwen3.7",
   "display_name": "qwen3.7",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.71"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "qwen3.7"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.7-max",
   "model_name": "qwen3.7-max",
   "display_name": "Qwen3.7 Max",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.69"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.07"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.169"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.1125"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      }
     },
     "provider_model_id": "qwen3.7-max-2026-05-20"
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "Qwen/Qwen3.7-Max",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2.5",
        "completion": "2.466667",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      }
     },
     "provider_model_id": "Qwen/Qwen3.7-Max"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.875"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1625"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.03125"
      }
     },
     "provider_model_id": "qwen/qwen3.7-max"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "qwen/qwen3.7-max"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      }
     },
     "provider_model_id": "alibaba/qwen3.7-max"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.76557584"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.29672752"
      }
     },
     "provider_model_id": "Qwen3.7-Max"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "qwen3.7-max:thinking"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "qwen/qwen3.7-max"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "qwen/qwen3.7-max"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.5625"
      }
     },
     "provider_model_id": "qwen/qwen3.7-max"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      }
     }
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.5625"
      }
     },
     "provider_model_id": "qwen/qwen3.7-max"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "qwen/qwen3.7-max"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5253"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5758"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.73913"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.21739"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.34783"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.17391"
      }
     },
     "provider_model_id": "qwen/qwen3.7-max"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      }
     },
     "provider_model_id": "alibaba/qwen3.7-max"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "Qwen/Qwen3.7-Max"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "qwen/qwen3.7-max"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.5625"
      }
     },
     "provider_model_id": "alibaba/qwen3.7-max"
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "wafer-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "wafer.ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "1.72311"
      }
     },
     "provider_model_id": "qwen/qwen3.7-max"
    }
   ],
   "intro": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
   "released_at": "2026-05-21",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "benchmarks": {
    "intelligence_index": 46,
    "coding_index": 66,
    "agentic_index": 30.6
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.7-Max",
    "Qwen3.7-Max",
    "alibaba/qwen3.7-max",
    "qwen/qwen3.7-max",
    "qwen/qwen3.7-max-2026-05-20",
    "qwen3.7-max-2026-05-20",
    "qwen3.7-max-2026-06-08",
    "qwen3.7-max:thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.7 Max是AI代理时代的旗舰全能模型，提供全面的文本、图像和视频理解能力。它在推理、函数调用和代理任务执行性能方面表现卓越。",
    "zh-TW": "Qwen3.7 Max 是 AI 代理時代的旗艦全能模型，提供全面的文本、影像和視頻理解能力。它在推理、函數調用和代理任務執行性能方面表現卓越。",
    "ja-JP": "Qwen3.7 MaxはAIエージェント時代のフラッグシップ万能モデルで、テキスト、画像、動画理解において包括的な能力を提供します。優れた推論、関数呼び出し、エージェントタスク実行性能を備えています。",
    "ru-RU": "Qwen3.7 Max — это флагманская универсальная модель эпохи AI-агентов, предлагающая комплексные возможности в понимании текста, изображений и видео. Она обеспечивает превосходное рассуждение, вызов функций и выполнение агентных задач."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "5.29926048",
     "new": "5.29672752"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.76642016",
     "new": "1.76557584"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "5.30294184",
     "new": "5.29926048"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.76764728",
     "new": "1.76642016"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "5.30853192",
     "new": "5.30294184"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.76951064",
     "new": "1.76764728"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "5.30961588",
     "new": "5.30853192"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.76987196",
     "new": "1.76951064"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "5.30773632",
     "new": "5.30961588"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.76924544",
     "new": "1.76987196"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "5.2984422",
     "new": "5.30773632"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.7661474",
     "new": "1.76924544"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "5.29873452",
     "new": "5.2984422"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.76624484",
     "new": "1.7661474"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.7-max-us",
   "model_name": "qwen3.7-max-us",
   "display_name": "Qwen3.7-Max-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.125"
      }
     }
    }
   ],
   "released_at": "2026-06-26",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "listed",
     "note": "Qwen3.7-Max-US"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.7-plus",
   "model_name": "qwen3.7-plus",
   "display_name": "Qwen3.7 Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.285"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.282"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.128"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0564"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3525"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "qwen3.7-plus-2026-05-26",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "2",
        "cache_read": "4",
        "cache_write": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwen3-7-plus"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.032"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen/qwen3.7-plus"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "qwen/qwen3.7-plus"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29426264"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.17705056"
      }
     },
     "provider_model_id": "Qwen3.7-Plus"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "qwen3.7-plus:thinking"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3",
        "completion": "3",
        "cache_read": "3",
        "cache_write": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3",
        "completion": "3",
        "cache_read": "3",
        "cache_write": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.064"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen/qwen3.7-plus"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.42"
      }
     },
     "provider_model_id": "qwen/qwen3.7-plus"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.404"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6162"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.032"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "alibaba/qwen3.7-plus"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.28"
      }
     },
     "provider_model_id": "Qwen/Qwen3.7-Plus"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07999999999999999"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen/qwen3.7-plus"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "alibaba/qwen3.7-plus",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3",
        "completion": "3",
        "cache_read": "3",
        "cache_write": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "3.43269"
      }
     },
     "provider_model_id": "qwen/qwen3.7-plus",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3",
        "completion": "3",
        "cache_read": "3",
        "cache_write": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3",
        "completion": "3",
        "cache_read": "3",
        "cache_write": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
   "released_at": "2026-06-02",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "benchmarks": {
    "intelligence_index": 39,
    "coding_index": 55.9,
    "agentic_index": 20.8
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3.7-Plus",
    "Qwen3.7-Plus",
    "alibaba/qwen3.7-plus",
    "fireworks/qwen3.7-plus",
    "qwen/qwen3.7-plus",
    "qwen3-7-plus",
    "qwen3.7-plus-2026-05-26",
    "qwen3.7-plus:thinking"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen3.7 Plus是一款多模态交互混合代理模型，基于Qwen3.7系列的文本能力，统一了视觉与语言。它在GUI操作、视觉编码和复杂代理工作流方面表现出色。",
    "zh-TW": "Qwen3.7 Plus 是一款多模態交互混合代理模型，基於 Qwen3.7 系列的文本能力，統一視覺與語言。它在 GUI 操作、視覺編程和複雜代理工作流方面表現出色。",
    "ja-JP": "Qwen3.7 Plusはマルチモーダルインタラクティブハイブリッドエージェントモデルで、Qwen3.7シリーズのテキスト能力を基盤に、ビジョンと言語を統合しています。GUI操作、視覚的コーディング、複雑なエージェントワークフローに優れています。",
    "ru-RU": "Qwen3.7 Plus — это мультимодальная интерактивная гибридная агентная модель, основанная на текстовых возможностях серии Qwen3.7, объединяющая визуализацию и язык. Она превосходно справляется с операциями GUI, визуальным кодированием и сложными агентными рабочими процессами."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17761344",
     "new": "1.17705056"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29440336",
     "new": "0.29426264"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17843152",
     "new": "1.17761344"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29460788",
     "new": "0.29440336"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17967376",
     "new": "1.17843152"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29491844",
     "new": "0.29460788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17991464",
     "new": "1.17967376"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29497866",
     "new": "0.29491844"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17949696",
     "new": "1.17991464"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29487424",
     "new": "0.29497866"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.1774316",
     "new": "1.17949696"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2943579",
     "new": "0.29487424"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17749656",
     "new": "1.1774316"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29437414",
     "new": "0.2943579"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3.7-plus-us",
   "model_name": "qwen3.7-plus-us",
   "display_name": "Qwen3.7-Plus-US",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2026-06-26",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "Qwen3.7-Plus-US"
    }
   ]
  },
  {
   "slug": "alibaba/qwen35-122b-a10b",
   "model_name": "qwen35-122b-a10b",
   "display_name": "Qwen3.5 122B-A10B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     }
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-02-23",
   "max_input_tokens": 262144,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "listed",
     "note": "Qwen3.5 122B-A10B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen35-397b-a17b",
   "model_name": "qwen35-397b-a17b",
   "display_name": "Qwen3.5 397B-A17B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     }
    }
   ],
   "intro": "Large open Qwen multimodal MoE for visual agents and long technical tasks",
   "released_at": "2026-02-15",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.5 397B-A17B"
    }
   ]
  },
  {
   "slug": "alibaba/Qwen3Guard-Gen-0.6B",
   "model_name": "Qwen3Guard-Gen-0.6B",
   "display_name": "Qwen3Guard-Gen-0.6B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "Qwen/Qwen3Guard-Gen-0.6B"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2026-01-22",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "family": "qwen",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/Qwen3Guard-Gen-0.6B",
    "qwen3guard-gen-0.6b"
   ],
   "model_type": "safety_detection",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3Guard-Gen-0.6B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3guard-gen-8b",
   "model_name": "qwen3guard-gen-8b",
   "display_name": "Qwen3Guard-Gen-8B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "sference/qwen3guard-gen-8b"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2026-01-22",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sference/qwen3guard-gen-8b"
   ],
   "model_type": "safety_detection",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3Guard-Gen-8B"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3p6-plus",
   "model_name": "qwen3p6-plus",
   "display_name": "Qwen3.6 Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3p6-plus"
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3p6-plus"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 Plus"
    }
   ]
  },
  {
   "slug": "alibaba/qwen3p7-plus",
   "model_name": "qwen3p7-plus",
   "display_name": "Qwen 3.7 Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "accounts/fireworks/models/qwen3p7-plus"
    }
   ],
   "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
   "released_at": "2026-06-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "reasoning_config": {
    "budget_min": 1
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/qwen3p7-plus"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen 3.7 Plus"
    }
   ]
  },
  {
   "slug": "alibaba/QwenLong-L1-32B",
   "model_name": "QwenLong-L1-32B",
   "display_name": "QwenLong L1 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13999999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Tongyi-Zhiwen/QwenLong-L1-32B"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-01-25",
   "max_input_tokens": 128000,
   "max_output_tokens": 40960,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Tongyi-Zhiwen/QwenLong-L1-32B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "QwenLong L1 32B"
    }
   ]
  },
  {
   "slug": "alibaba/QwQ-32B",
   "model_name": "QwQ-32B",
   "display_name": "QwQ 32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb+lobehub-modelbank+pricetoken",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     },
     "provider_model_id": "qwq-32b"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     },
     "provider_model_id": "qwq-32b"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Qwen/QwQ-32B"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     },
     "provider_model_id": "qwq-32b"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "workers-ai/@cf/qwen/qwq-32b"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "@cf/qwen/qwq-32b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Qwen/QwQ-32B"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "qwq-32b"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "qwen/qwq-32b"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14713132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25599999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.30499999"
      }
     },
     "provider_model_id": "qwq-32b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen/qwq-32b"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      }
     },
     "provider_model_id": "Qwen/QwQ-32B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "qwq-32b"
    }
   ],
   "released_at": "2024-12",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "structured_output": true,
    "open_weights": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "intro": "Qwen reasoning model for deliberate problem solving, math, and coding",
   "docs_url": "https://nebius.com/prices-ai-studio",
   "deprecated": true,
   "deprecation_date": "2025-06-25",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/qwen/qwq-32b",
    "Qwen/QwQ-32B",
    "accounts/fireworks/models/qwq-32b",
    "qwen/qwq-32b",
    "qwq-32b",
    "qwq-32b:free",
    "workers-ai/@cf/qwen/qwq-32b"
   ],
   "intro_i18n": {
    "zh-CN": "QwQ 是 Qwen 系列中的推理模型。相比标准指令微调模型，具备更强的思维与推理能力，显著提升下游复杂任务表现。QwQ-32B 是一款中型推理模型，性能可媲美 DeepSeek-R1 和 o1-mini 等顶级模型。",
    "zh-TW": "QwQ 是 Qwen 系列中的推理模型。相較於標準指令微調模型，它具備更強的思考與推理能力，顯著提升下游任務表現，特別是在處理複雜問題時。QwQ-32B 是中型推理模型，表現可媲美 DeepSeek-R1 與 o1-mini 等頂尖模型。",
    "ja-JP": "QwQは、Qwenファミリーの推論モデルです。標準的な指示調整モデルと比較して、思考と推論能力に優れ、特に複雑な問題において下流性能を大幅に向上させます。QwQ-32Bは、DeepSeek-R1やo1-miniと並ぶ中規模の推論モデルです。",
    "ru-RU": "QwQ — модель логического вывода из семейства Qwen. По сравнению со стандартными моделями, обученными на инструкциях, она обеспечивает более глубокое мышление и логический анализ, значительно повышая производительность на сложных задачах. QwQ-32B — среднеразмерная модель, сопоставимая с ведущими моделями, такими как DeepSeek-R1 и o1-mini."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14720168",
     "new": "0.14713132"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14730394",
     "new": "0.14720168"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14745922",
     "new": "0.14730394"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14748933",
     "new": "0.14745922"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14743712",
     "new": "0.14748933"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14717895",
     "new": "0.14743712"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "QwQ 32B"
    }
   ]
  },
  {
   "slug": "alibaba/qwq-32b-arliai-rpr-v1:free",
   "model_name": "qwq-32b-arliai-rpr-v1:free",
   "display_name": "qwq-32b-arliai-rpr-v1:free",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwq-32b-arliai-rpr-v1:free"
    }
   ]
  },
  {
   "slug": "alibaba/QwQ-32B-Preview",
   "model_name": "QwQ-32B-Preview",
   "display_name": "QwQ 32B Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     },
     "provider_model_id": "qwq-32b-preview"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     },
     "provider_model_id": "qwq-32b-preview"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "Qwen/QwQ-32B-Preview"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen/qwq-32b-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "qwen/qwq-32b-preview"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "released_at": "2024-11-28",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true
   },
   "intro": "Qwen reasoning model for deliberate problem solving, math, and coding",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Qwen/QwQ-32B-Preview",
    "qwen/qwq-32b-preview",
    "qwq-32b-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Qwen QwQ 是一个实验性研究模型，专注于提升推理能力。",
    "zh-TW": "Qwen QwQ 是一個實驗性研究模型，專注於提升推理能力。",
    "ja-JP": "Qwen QwQ は、推論能力の向上に焦点を当てた実験的研究モデルです。",
    "ru-RU": "Qwen QwQ — это экспериментальная исследовательская модель, направленная на улучшение логического мышления."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "QwQ 32B Preview"
    }
   ]
  },
  {
   "slug": "alibaba/qwq-plus",
   "model_name": "qwq-plus",
   "display_name": "QwQ Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      }
     },
     "provider_model_id": "qwq-plus-2025-03-05"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.574"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    }
   ],
   "intro": "Qwen reasoning model for deliberate problem solving, math, and coding",
   "released_at": "2025-03-05",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "web_search": true
   },
   "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "qwq-plus-2025-03-05"
   ],
   "intro_i18n": {
    "zh-CN": "QwQ 推理模型基于 Qwen2.5 训练，并通过强化学习大幅提升推理能力。在数学/代码（AIME 24/25、LiveCodeBench）及通用评测（IFEval、LiveBench）中达到 DeepSeek-R1 的水平。",
    "zh-TW": "QwQ 推理模型基於 Qwen2.5 訓練，透過強化學習大幅提升推理能力。在數學/程式碼（AIME 24/25、LiveCodeBench）與部分通用基準（IFEval、LiveBench）上達到 DeepSeek-R1 的水準。",
    "ja-JP": "Qwen2.5を基盤としたQwQ推論モデルは、強化学習により推論能力を大幅に向上させています。数学やコード（AIME 24/25、LiveCodeBench）および一般ベンチマーク（IFEval、LiveBench）において、DeepSeek-R1と同等の性能を達成しています。",
    "ru-RU": "Модель логического вывода QwQ, обученная на основе Qwen2.5 с использованием RL, значительно улучшает логический анализ. Основные метрики в математике/коде (AIME 24/25, LiveCodeBench) и на общих бенчмарках (IFEval, LiveBench) достигают уровня DeepSeek-R1."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "alibaba/qwq-plus-latest",
   "model_name": "qwq-plus-latest",
   "display_name": "qwq-plus-latest",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      }
     }
    }
   ],
   "released_at": "2025-12-30",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qwq-plus-latest"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-pro-qwen-qwen2-5-7b-instruct",
   "model_name": "siliconflow-pro-qwen-qwen2-5-7b-instruct",
   "display_name": "Pro/Qwen/Qwen2.5-7B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "released_at": "2024-09-19",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/Qwen/Qwen2.5-7B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-pro-qwen-qwen2-5-coder-7b-instruct",
   "model_name": "siliconflow-pro-qwen-qwen2-5-coder-7b-instruct",
   "display_name": "Pro/Qwen/Qwen2.5-Coder-7B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "released_at": "2024-09-19",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/Qwen/Qwen2.5-Coder-7B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-pro-qwen-qwen2-5-vl-7b-instruct",
   "model_name": "siliconflow-pro-qwen-qwen2-5-vl-7b-instruct",
   "display_name": "Pro/Qwen/Qwen2.5-VL-7B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "released_at": "2025-06-17",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/Qwen/Qwen2.5-VL-7B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-pro-qwen-qwen2-7b-instruct",
   "model_name": "siliconflow-pro-qwen-qwen2-7b-instruct",
   "display_name": "Pro/Qwen/Qwen2-7B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "released_at": "2024-06-06",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/Qwen/Qwen2-7B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen2-5-14b-instruct",
   "model_name": "siliconflow-qwen-qwen2-5-14b-instruct",
   "display_name": "Qwen/Qwen2.5-14B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "released_at": "2024-09-19",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen2.5-14B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen2-5-32b-instruct",
   "model_name": "siliconflow-qwen-qwen2-5-32b-instruct",
   "display_name": "Qwen/Qwen2.5-32B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    }
   ],
   "released_at": "2024-09-19",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen2.5-32B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen2-5-72b-instruct-128k",
   "model_name": "siliconflow-qwen-qwen2-5-72b-instruct-128k",
   "display_name": "Qwen/Qwen2.5-72B-Instruct-128K",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     }
    }
   ],
   "released_at": "2024-09-19",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen2.5-72B-Instruct-128K"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen2-5-coder-32b-instruct",
   "model_name": "siliconflow-qwen-qwen2-5-coder-32b-instruct",
   "display_name": "Qwen/Qwen2.5-Coder-32B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    }
   ],
   "released_at": "2024-09-19",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen2.5-Coder-32B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen2-5-vl-32b-instruct",
   "model_name": "siliconflow-qwen-qwen2-5-vl-32b-instruct",
   "display_name": "Qwen/Qwen2.5-VL-32B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2025-06-17",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen2.5-VL-32B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen2-7b-instruct",
   "model_name": "siliconflow-qwen-qwen2-7b-instruct",
   "display_name": "Qwen/Qwen2-7B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     }
    }
   ],
   "released_at": "2024-03-13",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen2-7B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen2-vl-72b-instruct",
   "model_name": "siliconflow-qwen-qwen2-vl-72b-instruct",
   "display_name": "Qwen/Qwen2-VL-72B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     }
    }
   ],
   "released_at": "2024-09-04",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen2-VL-72B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen3-14b",
   "model_name": "siliconflow-qwen-qwen3-14b",
   "display_name": "Qwen/Qwen3-14B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2025-06-17",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-14B"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen3-235b-a22b-instruct-2507",
   "model_name": "siliconflow-qwen-qwen3-235b-a22b-instruct-2507",
   "display_name": "Qwen/Qwen3-235B-A22B-Instruct-2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.43"
      }
     }
    }
   ],
   "released_at": "2025-07-23",
   "max_input_tokens": 256003,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-235B-A22B-Instruct-2507"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen3-235b-a22b-thinking-2507",
   "model_name": "siliconflow-qwen-qwen3-235b-a22b-thinking-2507",
   "display_name": "Qwen/Qwen3-235B-A22B-Thinking-2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.43"
      }
     }
    }
   ],
   "released_at": "2025-07-29",
   "max_input_tokens": 256003,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-235B-A22B-Thinking-2507"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen3-30b",
   "model_name": "siliconflow-qwen-qwen3-30b",
   "display_name": "Qwen/Qwen3-32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2025-06-17",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-32B"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-Qwen-Qwen3-30B-A3B-Instruct-2507",
   "model_name": "siliconflow-Qwen-Qwen3-30B-A3B-Instruct-2507",
   "display_name": "Qwen/Qwen3-30B-A3B-Instruct-2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-30B-A3B-Instruct-2507"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-Qwen-Qwen3-30B-A3B-Thinking-2507",
   "model_name": "siliconflow-Qwen-Qwen3-30B-A3B-Thinking-2507",
   "display_name": "Qwen/Qwen3-30B-A3B-Thinking-2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-30B-A3B-Thinking-2507"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen3-coder-30b-a22b-instruct",
   "model_name": "siliconflow-qwen-qwen3-coder-30b-a22b-instruct",
   "display_name": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-08-04",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-Coder-30B-A3B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen3-next-80b-a3b-thinking-2507",
   "model_name": "siliconflow-qwen-qwen3-next-80b-a3b-thinking-2507",
   "display_name": "Qwen/Qwen3-Next-80B-A3B-Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.572"
      }
     }
    }
   ],
   "released_at": "2025-09-30",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-Next-80B-A3B-Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen3-omni-30b-a3b-instruct",
   "model_name": "siliconflow-qwen-qwen3-omni-30b-a3b-instruct",
   "display_name": "Qwen/Qwen3-Omni-30B-A3B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-10-13",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-Omni-30B-A3B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen3-Omni-30b-a3b-thinking",
   "model_name": "siliconflow-qwen-qwen3-Omni-30b-a3b-thinking",
   "display_name": "Qwen/Qwen3-Omni-30B-A3B-Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-10-13",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-Omni-30B-A3B-Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen3-vl-30b-a3b-instruct",
   "model_name": "siliconflow-qwen-qwen3-vl-30b-a3b-instruct",
   "display_name": "Qwen/Qwen3-VL-30B-A3B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-10-13",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-VL-30B-A3B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwen3-vl-30b-a3b-thinking",
   "model_name": "siliconflow-qwen-qwen3-vl-30b-a3b-thinking",
   "display_name": "Qwen/Qwen3-VL-30B-A3B-Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-10-13",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-VL-30B-A3B-Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-Qwen-Qwen3-VL-32B-Instruct",
   "model_name": "siliconflow-Qwen-Qwen3-VL-32B-Instruct",
   "display_name": "Qwen/Qwen3-VL-32B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.572"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-VL-32B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-Qwen-Qwen3-VL-32B-Thinking",
   "model_name": "siliconflow-Qwen-Qwen3-VL-32B-Thinking",
   "display_name": "Qwen/Qwen3-VL-32B-Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.429"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-VL-32B-Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-Qwen-Qwen3-VL-8B-Thinking",
   "model_name": "siliconflow-Qwen-Qwen3-VL-8B-Thinking",
   "display_name": "Qwen/Qwen3-VL-8B-Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.715"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-VL-8B-Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen-qwq-32b",
   "model_name": "siliconflow-qwen-qwq-32b",
   "display_name": "Qwen/QwQ-32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2025-03-06",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/QwQ-32B"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen3-next-80b-A3b-instruct",
   "model_name": "siliconflow-qwen3-next-80b-A3b-instruct",
   "display_name": "Qwen/Qwen3-Next-80B-A3B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.572"
      }
     }
    }
   ],
   "released_at": "2025-09-30",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-Next-80B-A3B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/siliconflow-qwen3-omni-a30b- a3b-captioner",
   "model_name": "siliconflow-qwen3-omni-a30b- a3b-captioner",
   "display_name": "Qwen/Qwen3-Omni-30B-A3B-Captioner",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-10-13",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen/Qwen3-Omni-30B-A3B-Captioner"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen2-5-7b-Instruct",
   "model_name": "sophnet-qwen2-5-7b-Instruct",
   "display_name": "sophnet/Qwen2.5-7B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen2.5-7B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen2-5-vl-32b-instruct",
   "model_name": "sophnet-qwen2-5-vl-32b-instruct",
   "display_name": "sophnet/Qwen2.5-VL-32B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.43"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen2.5-VL-32B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen2-5-vl-72b-instruct",
   "model_name": "sophnet-qwen2-5-vl-72b-instruct",
   "display_name": "sophnet/Qwen2.5-VL-72B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.86"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen2.5-VL-72B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen2-5-vl-7b-instruct",
   "model_name": "sophnet-qwen2-5-vl-7b-instruct",
   "display_name": "sophnet/Qwen2.5-VL-7B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen2.5-VL-7B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen2-vl-72b-instruct",
   "model_name": "sophnet-qwen2-vl-72b-instruct",
   "display_name": "sophnet/Qwen2-VL-72B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.86"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen2-VL-72B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen2-vl-7b-instruct",
   "model_name": "sophnet-qwen2-vl-7b-instruct",
   "display_name": "sophnet/Qwen2-VL-7B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen2-VL-7B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-14b",
   "model_name": "sophnet-qwen3-14b",
   "display_name": "sophnet/Qwen3-14B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-14B"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-235b-a22b",
   "model_name": "sophnet-qwen3-235b-a22b",
   "display_name": "sophnet/Qwen3-235B-A22B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.71"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-235B-A22B"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-235b-a22b-instruct-2507",
   "model_name": "sophnet-qwen3-235b-a22b-instruct-2507",
   "display_name": "sophnet/Qwen3-235B-A22B-Instruct-2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28600000000000003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14"
      }
     }
    }
   ],
   "released_at": "2025-08-04",
   "max_input_tokens": 262000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-235B-A22B-Instruct-2507"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-235b-A22b-thinking-2507",
   "model_name": "sophnet-qwen3-235b-A22b-thinking-2507",
   "display_name": "sophnet/Qwen3-235B-A22B-Thinking-2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.86"
      }
     }
    }
   ],
   "released_at": "2025-09-29",
   "max_input_tokens": 80000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-235B-A22B-Thinking-2507"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-30b-a3b-thinking-2507",
   "model_name": "sophnet-qwen3-30b-a3b-thinking-2507",
   "display_name": "sophnet/Qwen3-30B-A3B-Thinking-2507",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-09-09",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-30B-A3B-Thinking-2507"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-32b",
   "model_name": "sophnet-qwen3-32b",
   "display_name": "sophnet/Qwen3-32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1429"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5715"
      }
     }
    }
   ],
   "released_at": "2025-08-04",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-32B"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-coder",
   "model_name": "sophnet-qwen3-coder",
   "display_name": "sophnet/Qwen3-Coder",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.43"
      }
     }
    }
   ],
   "released_at": "2025-08-04",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-Coder"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-next-80b-a3b-instruct",
   "model_name": "sophnet-qwen3-next-80b-a3b-instruct",
   "display_name": "sophnet/Qwen3-Next-80B-A3B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5715"
      }
     }
    }
   ],
   "released_at": "2025-09-24",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-Next-80B-A3B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-next-80b-a3b-thinking",
   "model_name": "sophnet-qwen3-next-80b-a3b-thinking",
   "display_name": "sophnet/Qwen3-Next-80B-A3B-Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.43"
      }
     }
    }
   ],
   "released_at": "2025-09-24",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-Next-80B-A3B-Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-vl-235b-A22b-instruct",
   "model_name": "sophnet-qwen3-vl-235b-A22b-instruct",
   "display_name": "sophnet/Qwen3-VL-235B-A22B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.143"
      }
     }
    }
   ],
   "released_at": "2025-09-29",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-VL-235B-A22B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwen3-vl-235b-a22b-thinking",
   "model_name": "sophnet-qwen3-vl-235b-a22b-thinking",
   "display_name": "sophnet/Qwen3-VL-235B-A22B-Thinking",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.86"
      }
     }
    }
   ],
   "released_at": "2025-09-29",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-VL-235B-A22B-Thinking"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwq-32b",
   "model_name": "sophnet-qwq-32b",
   "display_name": "sophnet/QwQ-32B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/QwQ-32B"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwq2-5-32b-instruct",
   "model_name": "sophnet-qwq2-5-32b-instruct",
   "display_name": "sophnet/Qwen2.5-32B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen2.5-32B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/sophnet-qwq2-5-72b-instruct",
   "model_name": "sophnet-qwq2-5-72b-instruct",
   "display_name": "sophnet/Qwen2.5-72B-Instruct",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.71"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen2.5-72B-Instruct"
    }
   ]
  },
  {
   "slug": "alibaba/tim-qwen3.6-27b",
   "model_name": "tim-qwen3.6-27b",
   "display_name": "TIM-Qwen3.6 27B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "subconscious",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "subconscious/tim-qwen3.6-27b"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-05-11",
   "max_input_tokens": 8192,
   "max_output_tokens": 5000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "subconscious/tim-qwen3.6-27b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "subconscious",
     "charge": "completion",
     "old": "0",
     "new": "3"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "subconscious",
     "charge": "prompt",
     "old": "0",
     "new": "0.3"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TIM-Qwen3.6 27B"
    }
   ]
  },
  {
   "slug": "alibaba/Tongyi-DeepResearch-30B-A3B",
   "model_name": "Tongyi-DeepResearch-30B-A3B",
   "display_name": "Tongyi DeepResearch 30B A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24000000000000002"
      }
     },
     "provider_model_id": "Alibaba-NLP/Tongyi-DeepResearch-30B-A3B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "alibaba/tongyi-deepresearch-30b-a3b"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-08-26",
   "max_input_tokens": 128000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "yi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Alibaba-NLP/Tongyi-DeepResearch-30B-A3B",
    "alibaba/tongyi-deepresearch-30b-a3b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Tongyi DeepResearch 30B A3B"
    }
   ]
  },
  {
   "slug": "alibaba/tongyi-intent-detect-v3",
   "model_name": "tongyi-intent-detect-v3",
   "display_name": "Tongyi Intent Detect V3",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.144"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.143"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.144"
      }
     }
    }
   ],
   "released_at": "2024-01",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 8192,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "yi",
   "capabilities": {},
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Tongyi Intent Detect V3"
    }
   ]
  },
  {
   "slug": "alibaba/umans-qwen3.6-35b-a3b",
   "model_name": "umans-qwen3.6-35b-a3b",
   "display_name": "Qwen3.6 35B A3B",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "umans-ai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
   "released_at": "2026-04-17",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwen3.6 35B A3B"
    }
   ]
  },
  {
   "slug": "alibaba/wan-v2-6",
   "model_name": "wan-v2-6",
   "display_name": "Wan 2.6",
   "vendor": "alibaba",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-12-01",
   "max_input_tokens": 400000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "wanx/wan-v2-6"
   ],
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan 2.6"
    }
   ]
  },
  {
   "slug": "alibaba/wan-v2.5-t2v-preview",
   "model_name": "wan-v2.5-t2v-preview",
   "display_name": "Wan v2.5 Text-to-Video Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_480p": {
       "unit": "per_second",
       "price": "0.05"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.15"
      }
     },
     "provider_model_id": "alibaba/wan-v2.5-t2v-preview"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-09-24",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "o",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/wan-v2.5-t2v-preview"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan v2.5 Text-to-Video Preview"
    }
   ]
  },
  {
   "slug": "alibaba/wan-v2.6-i2v",
   "model_name": "wan-v2.6-i2v",
   "display_name": "Wan v2.6 Image-to-Video",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.15"
      }
     },
     "provider_model_id": "alibaba/wan-v2.6-i2v"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-12-16",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "o",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/wan-v2.6-i2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan v2.6 Image-to-Video"
    }
   ]
  },
  {
   "slug": "alibaba/wan-v2.6-i2v-flash",
   "model_name": "wan-v2.6-i2v-flash",
   "display_name": "Wan v2.6 Image-to-Video Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.05"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.075"
      }
     },
     "provider_model_id": "alibaba/wan-v2.6-i2v-flash"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-12-16",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "o",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/wan-v2.6-i2v-flash"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan v2.6 Image-to-Video Flash"
    }
   ]
  },
  {
   "slug": "alibaba/wan-v2.6-r2v",
   "model_name": "wan-v2.6-r2v",
   "display_name": "Wan v2.6 Reference-to-Video",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.15"
      }
     },
     "provider_model_id": "alibaba/wan-v2.6-r2v"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-12-16",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "o",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/wan-v2.6-r2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan v2.6 Reference-to-Video"
    }
   ]
  },
  {
   "slug": "alibaba/wan-v2.6-r2v-flash",
   "model_name": "wan-v2.6-r2v-flash",
   "display_name": "Wan v2.6 Reference-to-Video Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.05"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.075"
      }
     },
     "provider_model_id": "alibaba/wan-v2.6-r2v-flash"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-12-16",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "o",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/wan-v2.6-r2v-flash"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan v2.6 Reference-to-Video Flash"
    }
   ]
  },
  {
   "slug": "alibaba/wan-v2.6-t2v",
   "model_name": "wan-v2.6-t2v",
   "display_name": "Wan v2.6 Text-to-Video",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.15"
      }
     },
     "provider_model_id": "alibaba/wan-v2.6-t2v"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-12-16",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "o",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/wan-v2.6-t2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan v2.6 Text-to-Video"
    }
   ]
  },
  {
   "slug": "alibaba/wan-v2.7-r2v",
   "model_name": "wan-v2.7-r2v",
   "display_name": "Wan v2.7 Reference-to-Video",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.15"
      }
     },
     "provider_model_id": "alibaba/wan-v2.7-r2v"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-04-07",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "o",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/wan-v2.7-r2v"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "Wan v2.7 Reference-to-Video"
    }
   ]
  },
  {
   "slug": "alibaba/wan-v2.7-t2v",
   "model_name": "wan-v2.7-t2v",
   "display_name": "Wan v2.7 Text-to-Video",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.15"
      }
     },
     "provider_model_id": "alibaba/wan-v2.7-t2v"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-04-07",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "o",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alibaba/wan-v2.7-t2v"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "Wan v2.7 Text-to-Video"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.2-i2v-flash",
   "model_name": "wan2.2-i2v-flash",
   "display_name": "Wan2.2 I2V Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.029412"
      }
     }
    }
   ],
   "released_at": "2025-08-11",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.2极速版提供超快速生成，具有更准确的提示理解和摄像机控制能力。保持视觉元素的一致性，同时显著提升整体稳定性和成功率。",
    "zh-TW": "萬象2.2速度版提供超高速生成，具備更精確的提示理解及相機控制。保持視覺元素的一致性，同時顯著提升整體穩定性及成功率。",
    "ja-JP": "Wanxiang 2.2スピードエディションは、超高速生成を提供し、プロンプトの理解とカメラ制御がより正確になりました。視覚要素の一貫性を維持しながら、全体的な安定性と成功率を大幅に向上させます。",
    "ru-RU": "Wanxiang 2.2 Speed Edition обеспечивает ультрабыструю генерацию, с более точным пониманием подсказок и управлением камерой. Она поддерживает согласованность визуальных элементов, значительно улучшая общую стабильность и успешность."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.2 I2V Flash"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.2-i2v-plus",
   "model_name": "wan2.2-i2v-plus",
   "display_name": "Wan2.2 I2V Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.102941"
      }
     }
    }
   ],
   "released_at": "2025-07-28",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.2专业版提供更准确的提示理解和可控的摄像机运动。保持视觉元素的一致性，同时显著提升稳定性和成功率，生成更丰富、更详细的内容。",
    "zh-TW": "萬象2.2專業版提供更精確的提示理解及可控的相機運動。保持視覺元素的一致性，同時顯著提升穩定性及成功率，並生成更豐富、更詳細的內容。",
    "ja-JP": "Wanxiang 2.2プロエディションは、プロンプトの理解がより正確になり、制御可能なカメラ動作を提供します。視覚要素の一貫性を維持しながら、安定性と成功率を大幅に向上させ、より豊かで詳細なコンテンツを生成します。",
    "ru-RU": "Wanxiang 2.2 Pro Edition предлагает более точное понимание подсказок и управляемые движения камеры. Она поддерживает согласованность визуальных элементов, значительно улучшая стабильность и успешность, и генерирует более богатый и детализированный контент."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.2 I2V Plus"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.2-kf2v-flash",
   "model_name": "wan2.2-kf2v-flash",
   "display_name": "Wan2.2 KF2V Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.029412"
      }
     }
    }
   ],
   "released_at": "2025-09-12",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.2极速版",
    "zh-TW": "萬象2.2速度版",
    "ja-JP": "Wanxiang 2.2スピードエディション",
    "ru-RU": "Wanxiang 2.2 Speed Edition"
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.2 KF2V Flash"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.2-kf2v-plus",
   "model_name": "wan2.2-kf2v-plus",
   "display_name": "Wan2.2 KF2V Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.102941"
      }
     }
    }
   ],
   "released_at": "2025-09-12",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.2专业版",
    "zh-TW": "萬象2.2專業版",
    "ja-JP": "Wanxiang 2.2プラスエディション",
    "ru-RU": "Wanxiang 2.2 Plus Edition"
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.2 KF2V Plus"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.2-t2i-flash",
   "model_name": "wan2.2-t2i-flash",
   "display_name": "Wanxiang2.2 T2I Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.020588"
      }
     }
    }
   ],
   "released_at": "2025-07-28",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.2 Flash是最新模型，在创造力、稳定性和真实感方面进行了升级，提供快速生成和高价值。",
    "zh-TW": "萬象 2.2 Flash 是最新模型，在創意、穩定性和真實感方面進行了升級，提供快速生成和高價值。",
    "ja-JP": "Wanxiang 2.2 Flashは、創造性、安定性、リアリズムの向上を伴う最新モデルで、高速生成と高い価値を提供します。",
    "ru-RU": "Wanxiang 2.2 Flash — это последняя модель с улучшениями в креативности, стабильности и реалистичности, обеспечивающая быструю генерацию и высокую ценность."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.2 T2I Flash"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.2-t2i-plus",
   "model_name": "wan2.2-t2i-plus",
   "display_name": "Wanxiang2.2 T2I Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     }
    }
   ],
   "released_at": "2025-07-28",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.2 Plus是最新模型，在创造力、稳定性和真实感方面进行了升级，生成更丰富的细节。",
    "zh-TW": "萬象 2.2 Plus 是最新模型，在創意、穩定性和真實感方面進行了升級，生成更豐富的細節。",
    "ja-JP": "Wanxiang 2.2 Plusは、創造性、安定性、リアリズムの向上を伴う最新モデルで、より豊かな詳細を生成します。",
    "ru-RU": "Wanxiang 2.2 Plus — это последняя модель с улучшениями в креативности, стабильности и реалистичности, создающая более богатые детали."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.2 T2I Plus"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.2-t2v-plus",
   "model_name": "wan2.2-t2v-plus",
   "display_name": "Wan2.2 T2V Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.102941"
      }
     }
    }
   ],
   "released_at": "2025-07-28",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.2专业版提供更准确的提示理解，生成稳定流畅的动作，并生成更丰富、更详细的视觉效果。",
    "zh-TW": "萬象2.2專業版提供更精確的提示理解，生成穩定且流暢的動作影像，並產生更豐富、更詳細的視覺效果。",
    "ja-JP": "Wanxiang 2.2プロエディションは、プロンプトの理解がより正確になり、安定した滑らかな動きの生成を提供し、より豊かで詳細なビジュアルを生成します。",
    "ru-RU": "Wanxiang 2.2 Pro Edition обеспечивает более точное понимание подсказок, стабильную и плавную генерацию движений, а также создает более богатые и детализированные визуальные эффекты."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.2 T2V Plus"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.5-i2i-preview",
   "model_name": "wan2.5-i2i-preview",
   "display_name": "Wanxiang2.5 I2I Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     }
    }
   ],
   "released_at": "2025-09-23",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.5 I2I Preview支持单图编辑和多图融合。",
    "zh-TW": "萬象 2.5 I2I Preview 支持單圖編輯和多圖融合。",
    "ja-JP": "Wanxiang 2.5 I2I Previewは、単一画像編集と複数画像の融合をサポートします。",
    "ru-RU": "Wanxiang 2.5 I2I Preview поддерживает редактирование одного изображения и слияние нескольких изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.5 I2I Preview"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.5-i2v-preview",
   "model_name": "wan2.5-i2v-preview",
   "display_name": "Wan2.5 I2V Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.147059"
      }
     }
    }
   ],
   "released_at": "2025-09-23",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.5预览版支持自动配音生成以及自定义音频文件的嵌入。",
    "zh-TW": "萬象2.5預覽版支持自動配音生成及整合自定義音頻文件。",
    "ja-JP": "Wanxiang 2.5プレビューは、自動音声生成とカスタムオーディオファイルの組み込みをサポートします。",
    "ru-RU": "Wanxiang 2.5 Preview поддерживает автоматическую генерацию озвучки и возможность добавления пользовательских аудиофайлов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.5 I2V Preview"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.5-t2i-preview",
   "model_name": "wan2.5-t2i-preview",
   "display_name": "Wanxiang2.5 T2I Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     }
    }
   ],
   "released_at": "2025-09-23",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.5 T2I支持在总像素面积和纵横比限制内灵活选择图像尺寸。",
    "zh-TW": "萬象 2.5 T2I 支持在總像素面積和長寬比限制內靈活選擇圖像尺寸。",
    "ja-JP": "Wanxiang 2.5 T2Iは、総ピクセルエリアとアスペクト比の制約内で画像寸法の柔軟な選択をサポートします。",
    "ru-RU": "Wanxiang 2.5 T2I поддерживает гибкий выбор размеров изображения в пределах общей площади пикселей и ограничений соотношения сторон."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.5 T2I Preview"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.5-t2v-preview",
   "model_name": "wan2.5-t2v-preview",
   "display_name": "Wan2.5 T2V Preview",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.147059"
      }
     }
    }
   ],
   "released_at": "2025-09-23",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.5预览版支持自动配音生成以及自定义音频文件的嵌入。",
    "zh-TW": "萬象2.5預覽版支持自動配音生成及整合自定義音頻文件。",
    "ja-JP": "Wanxiang 2.5プレビューは、自動音声生成とカスタムオーディオファイルの組み込みをサポートします。",
    "ru-RU": "Wanxiang 2.5 Preview поддерживает автоматическую генерацию озвучки и возможность добавления пользовательских аудиофайлов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.5 T2V Preview"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.6-i2v",
   "model_name": "wan2.6-i2v",
   "display_name": "Wan2.6 I2V",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.147059"
      }
     }
    }
   ],
   "released_at": "2025-12-16",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.6引入多镜头叙事能力，同时支持自动配音生成以及自定义音频文件的嵌入。",
    "zh-TW": "萬象2.6引入多鏡頭敘事能力，同時支持自動配音生成及整合自定義音頻文件。",
    "ja-JP": "Wanxiang 2.6は、マルチショットの物語能力を導入し、自動音声生成とカスタムオーディオファイルの組み込みもサポートします。",
    "ru-RU": "Wanxiang 2.6 вводит возможности многокадрового повествования, а также поддерживает автоматическую генерацию озвучки и возможность добавления пользовательских аудиофайлов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.6 I2V"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.6-i2v-flash",
   "model_name": "wan2.6-i2v-flash",
   "display_name": "Wan2.6 I2V Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.073529"
      }
     }
    }
   ],
   "released_at": "2026-01-17",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.6引入多镜头叙事能力，同时支持自动配音生成以及自定义音频文件的嵌入。",
    "zh-TW": "萬象2.6引入多鏡頭敘事能力，同時支持自動配音生成及整合自定義音頻文件。",
    "ja-JP": "Wanxiang 2.6は、マルチショットの物語能力を導入し、自動音声生成とカスタムオーディオファイルの組み込みもサポートします。",
    "ru-RU": "Wanxiang 2.6 вводит возможности многокадрового повествования, а также поддерживает автоматическую генерацию озвучки и возможность добавления пользовательских аудиофайлов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.6 I2V Flash"
    }
   ]
  },
  {
   "slug": "alibaba/Wan2.6-image",
   "model_name": "Wan2.6-image",
   "display_name": "Wanxiang2.6 Image",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     },
     "provider_model_id": "wan2.6-image"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "Wan-AI/Wan2.6-image"
    }
   ],
   "released_at": "2025-07-28",
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Wan-AI/Wan2.6-image",
    "wan2.6-image"
   ],
   "intro_i18n": {
    "zh-CN": "万象2.6 Image支持图像编辑和混合图像-文本布局输出。",
    "zh-TW": "萬象 2.6 Image 支持圖像編輯和混合圖文佈局輸出。",
    "ja-JP": "Wanxiang 2.6 Imageは、画像編集と画像とテキストの混合レイアウト出力をサポートします。",
    "ru-RU": "Wanxiang 2.6 Image поддерживает редактирование изображений и смешанный вывод макета изображений и текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.6 Image"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.6-r2v",
   "model_name": "wan2.6-r2v",
   "display_name": "Wan2.6 R2V",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.073529"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "37.29"
      }
     }
    }
   ],
   "released_at": "2025-12-16",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.6参考转视频支持参考特定角色或任何物体，准确保持外观和声音的一致性，并支持多角色参考协同表演。注意：使用视频作为参考时，输入视频也将计入成本。请参阅模型定价文档了解详情。",
    "zh-TW": "萬象2.6參考生成影像支持參考特定角色或任意物件，精確保持外觀及聲音的一致性，並支持多角色參考共同表演。注意：使用影像作為參考時，輸入影像也將計入成本。請參閱模型定價文檔了解詳情。",
    "ja-JP": "Wanxiang 2.6参照からビデオは、特定のキャラクターやオブジェクトを参照し、外観と声の一貫性を正確に維持し、複数キャラクターの参照による共演を可能にします。注：ビデオを参照として使用する場合、入力ビデオもコストに含まれます。モデルの価格設定ドキュメントを参照してください。",
    "ru-RU": "Wanxiang 2.6 Reference-to-Video поддерживает ссылки на конкретных персонажей или любые объекты, точно сохраняя согласованность внешнего вида и голоса, а также позволяет использовать ссылки на нескольких персонажей для совместного исполнения. Примечание: при использовании видео в качестве ссылок входное видео также будет учитываться в стоимости. Пожалуйста, ознакомьтесь с документацией по ценообразованию модели для получения подробной информации."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.6 R2V"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.6-r2v-flash",
   "model_name": "wan2.6-r2v-flash",
   "display_name": "Wan2.6 R2V Flash",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.147059"
      }
     }
    }
   ],
   "released_at": "2025-12-16",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.6参考转视频极速版提供更快的生成速度和更高的性价比。支持参考特定角色或任何物体，准确保持外观和声音的一致性，并支持多角色参考协同表演。",
    "zh-TW": "萬象2.6參考生成影像——速度版提供更快的生成速度及更高的性價比。支持參考特定角色或任意物件，精確保持外觀及聲音的一致性，並支持多角色參考共同表演。",
    "ja-JP": "Wanxiang 2.6参照からビデオ – Flashは、より高速な生成と優れたコストパフォーマンスを提供します。特定のキャラクターやオブジェクトを参照し、外観と声の一貫性を正確に維持し、複数キャラクターの参照による共演を可能にします。",
    "ru-RU": "Wanxiang 2.6 Reference-to-Video – Flash предлагает более быструю генерацию и лучшую стоимость. Она поддерживает ссылки на конкретных персонажей или любые объекты, точно сохраняя согласованность внешнего вида и голоса, а также позволяет использовать ссылки на нескольких персонажей для совместного исполнения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.6 R2V Flash"
    }
   ]
  },
  {
   "slug": "alibaba/Wan2.6-T2I",
   "model_name": "Wan2.6-T2I",
   "display_name": "Wanxiang2.6 T2I",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     },
     "provider_model_id": "wan2.6-t2i"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "Wan-AI/Wan2.6-T2I"
    }
   ],
   "released_at": "2025-12-16",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Wan-AI/Wan2.6-T2I",
    "wan2.6-t2i"
   ],
   "intro_i18n": {
    "zh-CN": "万象2.6 T2I支持在总像素面积和纵横比限制内灵活选择图像尺寸（与万象2.5相同）。",
    "zh-TW": "萬象 2.6 T2I 支持在總像素面積和長寬比限制內靈活選擇圖像尺寸（與萬象 2.5 相同）。",
    "ja-JP": "Wanxiang 2.6 T2Iは、総ピクセルエリアとアスペクト比の制約内で画像寸法の柔軟な選択をサポートします（Wanxiang 2.5と同様）。",
    "ru-RU": "Wanxiang 2.6 T2I поддерживает гибкий выбор размеров изображения в пределах общей площади пикселей и ограничений соотношения сторон (аналогично Wanxiang 2.5)."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.6 T2I"
    }
   ]
  },
  {
   "slug": "alibaba/Wan2.6-T2V",
   "model_name": "Wan2.6-T2V",
   "display_name": "Wan2.6 T2V",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.147059"
      }
     },
     "provider_model_id": "wan2.6-t2v"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "37.29"
      }
     },
     "provider_model_id": "wan2.6-t2v"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.1"
      }
     },
     "provider_model_id": "Wan-AI/Wan2.6-T2V"
    }
   ],
   "released_at": "2025-12-16",
   "model_type": "video_generation",
   "capabilities": {
    "audio_input": true
   },
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "video"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Wan-AI/Wan2.6-T2V",
    "wan2.6-t2v"
   ],
   "intro_i18n": {
    "zh-CN": "万象2.6引入多镜头叙事能力，同时支持自动配音生成以及自定义音频文件的嵌入。",
    "zh-TW": "萬象2.6引入多鏡頭敘事能力，同時支持自動配音生成及整合自定義音頻文件。",
    "ja-JP": "Wanxiang 2.6は、マルチショットの物語能力を導入し、自動音声生成とカスタムオーディオファイルの組み込みもサポートします。",
    "ru-RU": "Wanxiang 2.6 вводит возможности многокадрового повествования, а также поддерживает автоматическую генерацию озвучки и возможность добавления пользовательских аудиофайлов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.6 T2V"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.7-i2v-2026-04-25",
   "model_name": "wan2.7-i2v-2026-04-25",
   "display_name": "Wan2.7 I2V",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.147059"
      }
     },
     "provider_model_id": "wan2.7-i2v"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.1"
      }
     },
     "provider_model_id": "Wan-AI/wan2.7-i2v"
    }
   ],
   "released_at": "2026-04-03",
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "video_input": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Wan-AI/wan2.7-i2v",
    "wan2.7-i2v"
   ],
   "intro_i18n": {
    "zh-CN": "万象 2.7 图生视频在表现力全面升级。剧情场景中情绪细腻自然，动作场景紧凑有力。结合更具动感与节奏感的镜头切换，整体性能与叙事能力大幅增强。",
    "zh-TW": "萬象 2.7 圖生影在性能上全面升級。戲劇場景情感細緻自然，動作場景張力十足，並結合更具節奏感與動態性的鏡頭轉換，呈現更強的整體表現力與故事敘事能力。",
    "ja-JP": "Wanxiang 2.7 Image-to-Videoは、性能能力において包括的なアップグレードを提供します。ドラマチックなシーンでは繊細で自然な感情表現を特徴とし、アクションシーンでは激しくインパクトのある演出を実現します。より動的でリズムに基づいたショットの切り替えを組み合わせることで、全体的な性能とストーリーテリングを強化します。",
    "ru-RU": "Wanxiang 2.7 Image-to-Video получила комплексное обновление возможностей. Драматические сцены демонстрируют естественную эмоциональную выразительность, а экшен-сцены — динамичность и силу. В сочетании с более выразительными и ритмичными переходами модель обеспечивает улучшенное повествование и визуальный эффект."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.7 I2V"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.7-image",
   "model_name": "wan2.7-image",
   "display_name": "Wanxiang2.7 Image",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2026-04-01",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 8192,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.7图像，图像生成速度更快。",
    "zh-TW": "萬象2.7影像，影像生成速度更快。",
    "ja-JP": "Wanxiang 2.7画像は、より高速な画像生成速度を提供します。",
    "ru-RU": "Wanxiang 2.7 Image обеспечивает более быструю скорость генерации изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.7 Image"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.7-image-pro",
   "model_name": "wan2.7-image-pro",
   "display_name": "Wanxiang2.7 Image Pro",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.073529"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2026-04-01",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 8192,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.7图像专业版，支持4K高清输出。",
    "zh-TW": "萬象2.7影像專業版，支持4K高清輸出。",
    "ja-JP": "Wanxiang 2.7画像プロフェッショナルエディションは、4K高解像度出力をサポートします。",
    "ru-RU": "Wanxiang 2.7 Image Professional Edition поддерживает вывод в 4K высоком разрешении."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.7 Image Pro"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.7-r2v",
   "model_name": "wan2.7-r2v",
   "display_name": "Wan2.7 R2V",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.147059"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.1"
      }
     },
     "provider_model_id": "Wan-AI/wan2.7-r2v"
    }
   ],
   "released_at": "2026-04-03",
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "video_input": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Wan-AI/wan2.7-r2v"
   ],
   "intro_i18n": {
    "zh-CN": "万象2.7参考转视频为角色、道具和场景提供更稳定的参考。支持最多5张混合参考图像或视频，以及音频音调参考。结合升级的核心能力，提供更强的表现力和表达能力。",
    "zh-TW": "萬象2.7參考生成影像提供更穩定的角色、道具及場景參考。支持最多5張混合參考影像或影像，以及音頻音調參考。結合升級的核心能力，提供更強的性能及表現力。",
    "ja-JP": "Wanxiang 2.7参照からビデオは、キャラクター、小道具、シーンのより安定した参照を提供します。最大5つの混合参照画像またはビデオをサポートし、オーディオトーンの参照も可能です。アップグレードされたコア能力と組み合わせることで、より強力なパフォーマンスと表現力を提供します。",
    "ru-RU": "Wanxiang 2.7 Reference-to-Video предлагает более стабильные ссылки для персонажей, реквизита и сцен. Поддерживает до 5 смешанных эталонных изображений или видео, а также ссылки на аудиотон. В сочетании с обновленными основными возможностями обеспечивает более сильную производительность и выразительность."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.7 R2V"
    }
   ]
  },
  {
   "slug": "alibaba/wan2.7-t2v-2026-04-25",
   "model_name": "wan2.7-t2v-2026-04-25",
   "display_name": "Wan2.7 T2V",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.147059"
      }
     },
     "provider_model_id": "wan2.7-t2v"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.1"
      }
     },
     "provider_model_id": "Wan-AI/wan2.7-t2v"
    }
   ],
   "released_at": "2026-04-03",
   "model_type": "video_generation",
   "capabilities": {
    "audio_input": true
   },
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "video"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Wan-AI/wan2.7-t2v",
    "wan2.7-t2v"
   ],
   "intro_i18n": {
    "zh-CN": "万象 2.7 文生视频在表现力全面升级。剧情场景中情绪细腻自然，动作场景紧凑有力。结合更具节奏的镜头切换，在演绎与叙事方面表现更为出色。",
    "zh-TW": "萬象 2.7 文生影在性能上全面升級。戲劇場景情感細緻自然，動作場景張力十足，並強化鏡頭節奏與動態切換，讓表演與敘事能力更上層樓。",
    "ja-JP": "Wanxiang 2.7 Text-to-Videoは、性能能力において包括的なアップグレードを提供します。ドラマチックなシーンでは繊細で自然な感情表現を特徴とし、アクションシーンでは激しくインパクトのある演出を実現します。より動的でリズムに基づいたショットの切り替えを組み合わせることで、全体的な演技とストーリーテリング性能を強化します。",
    "ru-RU": "Wanxiang 2.7 Text-to-Video получила комплексное обновление возможностей. Драматические сцены стали более эмоционально выразительными, а динамичные эпизоды — более впечатляющими. Улучшенные ритмичные переходы создают более сильный общий эффект и выразительность повествования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.7 T2V"
    }
   ]
  },
  {
   "slug": "alibaba/wanx-v1",
   "model_name": "wanx-v1",
   "display_name": "Wanxiang v1",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.023529"
      }
     }
    }
   ],
   "released_at": "2024-05-22",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "基础文本转图像模型。对应通义万象 1.0 通用版。",
    "zh-TW": "基礎文字轉圖像模型。對應通義萬象 1.0 通用版。",
    "ja-JP": "基本的なテキストから画像への変換モデル。Tongyi Wanxiang 1.0 Generalに対応。",
    "ru-RU": "Базовая модель преобразования текста в изображение. Соответствует Tongyi Wanxiang 1.0 General."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang v1"
    }
   ]
  },
  {
   "slug": "alibaba/wanx2.0-t2i-turbo",
   "model_name": "wanx2.0-t2i-turbo",
   "display_name": "Wanxiang2.0 T2I Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.005882"
      }
     }
    }
   ],
   "released_at": "2025-01-17",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "擅长纹理人像，速度适中，成本较低。对应通义万象 2.0 极速版。",
    "zh-TW": "擅長紋理人像，速度適中、成本較低。對應通義萬象 2.0 Speed。",
    "ja-JP": "中程度の速度と低コストで質感のあるポートレートに優れています。Tongyi Wanxiang 2.0 Speedに対応。",
    "ru-RU": "Отличается текстурированными портретами при умеренной скорости и низкой стоимости. Соответствует Tongyi Wanxiang 2.0 Speed."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.0 T2I Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/wanx2.1-i2v-plus",
   "model_name": "wanx2.1-i2v-plus",
   "display_name": "Wanxiang2.1 I2V Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.102941"
      }
     }
    }
   ],
   "released_at": "2025-01-17",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.1专业版提供更精致的视觉效果和更高质量的图像。",
    "zh-TW": "萬象2.1專業版提供更精緻且高質量的影像。",
    "ja-JP": "Wanxiang 2.1プロエディションは、より視覚的に洗練され、高品質な画像を提供します。",
    "ru-RU": "Wanxiang 2.1 Pro Edition обеспечивает более утонченное визуальное оформление и изображения более высокого качества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.1 I2V Plus"
    }
   ]
  },
  {
   "slug": "alibaba/wanx2.1-i2v-turbo",
   "model_name": "wanx2.1-i2v-turbo",
   "display_name": "Wanxiang2.1 I2V Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.035294"
      }
     }
    }
   ],
   "released_at": "2025-02-25",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.1极速版提供高性价比。",
    "zh-TW": "萬象2.1速度版提供高性價比。",
    "ja-JP": "Wanxiang 2.1スピードエディションは、高いコストパフォーマンスを提供します。",
    "ru-RU": "Wanxiang 2.1 Speed Edition предлагает высокую стоимость."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.1 I2V Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/wanx2.1-t2i-plus",
   "model_name": "wanx2.1-t2i-plus",
   "display_name": "Wanxiang2.1 T2I Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     }
    }
   ],
   "released_at": "2025-01-08",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "全面升级版本，图像细节更丰富，生成速度略慢。对应通义万象 2.1 专业版。",
    "zh-TW": "全面升級版本，圖像細節更豐富，速度略慢。對應通義萬象 2.1 Pro。",
    "ja-JP": "画像のディテールがより豊かになった完全アップグレード版で、やや速度は遅めです。Tongyi Wanxiang 2.1 Proに対応。",
    "ru-RU": "Полностью обновленная версия с более богатыми деталями изображения и немного меньшей скоростью. Соответствует Tongyi Wanxiang 2.1 Pro."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.1 T2I Plus"
    }
   ]
  },
  {
   "slug": "alibaba/wanx2.1-t2i-turbo",
   "model_name": "wanx2.1-t2i-turbo",
   "display_name": "Wanxiang2.1 T2I Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.020588"
      }
     }
    }
   ],
   "released_at": "2025-01-08",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "全面升级版本，生成速度快，整体质量强，性价比高。对应通义万象 2.1 极速版。",
    "zh-TW": "全面升級版本，生成快速、整體品質強、性價比高。對應通義萬象 2.1 Speed。",
    "ja-JP": "高速生成、全体的な品質の高さ、高いコストパフォーマンスを備えた完全アップグレード版です。Tongyi Wanxiang 2.1 Speedに対応。",
    "ru-RU": "Полностью обновленная версия с быстрой генерацией, высоким общим качеством и отличной ценностью. Соответствует Tongyi Wanxiang 2.1 Speed."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.1 T2I Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/wanx2.1-t2v",
   "model_name": "wanx2.1-t2v",
   "display_name": "wanx2.1-t2v",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "43.5"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "wanx2.1-t2v"
    }
   ]
  },
  {
   "slug": "alibaba/wanx2.1-t2v-plus",
   "model_name": "wanx2.1-t2v-plus",
   "display_name": "Wanxiang2.1 T2V Plus",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.102941"
      }
     }
    }
   ],
   "released_at": "2025-01-08",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.1专业版提供更丰富的视觉纹理和更高质量的图像。",
    "zh-TW": "萬象2.1專業版提供更豐富的視覺紋理及更高質量的影像。",
    "ja-JP": "Wanxiang 2.1プロエディションは、より豊かな視覚的テクスチャと高品質な画像を提供します。",
    "ru-RU": "Wanxiang 2.1 Pro Edition обеспечивает более богатую визуальную текстуру и изображения более высокого качества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.1 T2V Plus"
    }
   ]
  },
  {
   "slug": "alibaba/wanx2.1-t2v-turbo",
   "model_name": "wanx2.1-t2v-turbo",
   "display_name": "Wanxiang2.1 T2V Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.035294"
      }
     }
    }
   ],
   "released_at": "2025-01-08",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万象2.1极速版提供卓越的性价比。",
    "zh-TW": "萬象2.1速度版提供卓越的性價比。",
    "ja-JP": "Wanxiang 2.1スピードエディションは、優れたコストパフォーマンスを提供します。",
    "ru-RU": "Wanxiang 2.1 Speed Edition предлагает отличное соотношение цены и качества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wanxiang2.1 T2V Turbo"
    }
   ]
  },
  {
   "slug": "alibaba/z-image-turbo",
   "model_name": "z-image-turbo",
   "display_name": "Z-Image Turbo",
   "vendor": "alibaba",
   "pricing": [
    {
     "provider": "alibaba",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.014706"
      }
     }
    }
   ],
   "released_at": "2025-12-19",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Z-Image是一个轻量级文本生成图像模型，能够快速生成图像，支持中英文文本渲染，并灵活适应多种分辨率和纵横比。",
    "zh-TW": "Z-Image 是一款輕量級文本生成圖像模型，能快速生成圖像，支持中英文文本渲染，並靈活適應多種分辨率和長寬比。",
    "ja-JP": "Z-Imageは軽量なテキストから画像生成モデルで、迅速に画像を生成し、中国語と英語のテキストレンダリングをサポートし、複数の解像度とアスペクト比に柔軟に適応します。",
    "ru-RU": "Z-Image — это легковесная модель генерации изображений из текста, которая может быстро создавать изображения, поддерживает рендеринг текста на китайском и английском языках, а также гибко адаптируется к различным разрешениям и соотношениям сторон."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Z-Image Turbo"
    }
   ]
  },
  {
   "slug": "amazon/amazon-nova-lite",
   "model_name": "amazon-nova-lite",
   "display_name": "Amazon Nova Lite",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Amazon Nova Lite"
    }
   ]
  },
  {
   "slug": "amazon/amazon-nova-micro",
   "model_name": "amazon-nova-micro",
   "display_name": "Amazon Nova Micro",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Amazon Nova Micro"
    }
   ]
  },
  {
   "slug": "amazon/amazon-nova-premier",
   "model_name": "amazon-nova-premier",
   "display_name": "Amazon Nova Premier",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Amazon Nova Premier"
    }
   ]
  },
  {
   "slug": "amazon/amazon-nova-pro",
   "model_name": "amazon-nova-pro",
   "display_name": "Amazon Nova Pro",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Amazon Nova Pro"
    }
   ]
  },
  {
   "slug": "amazon/amazon.nova-2-multimodal-embeddings-v1:0",
   "model_name": "amazon.nova-2-multimodal-embeddings-v1:0",
   "display_name": "amazon.nova-2-multimodal-embeddings-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.135"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00006"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0006"
      },
      "audio_input": {
       "unit": "per_second",
       "price": "0.00014"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "region": "us-east-1"
    }
   ],
   "docs_url": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/model-catalog/serverless/amazon.nova-2-multimodal-embeddings-v1:0",
   "max_input_tokens": 8172,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "video_input": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "amazon/amazon.nova-2-sonic-v1:0",
   "model_name": "amazon.nova-2-sonic-v1:0",
   "display_name": "amazon.nova-2-sonic-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3.63"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.396"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "14.52"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.311"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.91"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.363"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "11.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.92"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.319"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.651"
      }
     },
     "region": "us-west-2"
    }
   ],
   "capabilities": {
    "function_calling": true,
    "audio_input": true,
    "audio_output": true
   },
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "model_type": "realtime_omni",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "amazon.nova-2-sonic-v1:0"
    }
   ]
  },
  {
   "slug": "amazon/amazon.nova-reel-v1:1",
   "model_name": "amazon.nova-reel-v1:1",
   "display_name": "amazon.nova-reel-v1:1",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.08"
      }
     },
     "provider_model_id": "amazon.nova-reel-v1:0"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon.nova-reel-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "amazon.nova-reel-v1:1"
    }
   ]
  },
  {
   "slug": "amazon/amazon.nova-sonic-v1:0",
   "model_name": "amazon.nova-sonic-v1:0",
   "display_name": "amazon.nova-sonic-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3.4"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "13.6"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3.7"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "14.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.288"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "4.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.065"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "16.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3.4"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "13.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "us-east-1"
    }
   ],
   "capabilities": {
    "function_calling": true
   },
   "max_input_tokens": 300000,
   "modalities": {
    "input": [],
    "output": [
     "text"
    ]
   },
   "model_type": "realtime_omni",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "amazon.nova-sonic-v1:0"
    }
   ]
  },
  {
   "slug": "amazon/amazon.rerank-v1:0",
   "model_name": "amazon.rerank-v1:0",
   "display_name": "amazon.rerank-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1000"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.001"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.001"
      }
     },
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.001"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.001"
      }
     },
     "region": "us-west-2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "amazon.rerank-v1:0"
    }
   ]
  },
  {
   "slug": "amazon/amazon.titan-embed-g1-text-02",
   "model_name": "amazon.titan-embed-g1-text-02",
   "display_name": "amazon.titan-embed-g1-text-02",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_embedding",
   "capabilities": {},
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "amazon/amazon.titan-embed-image-v1",
   "model_name": "amazon.titan-embed-image-v1",
   "display_name": "amazon.titan-embed-image-v1",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00006"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "3.125",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00007"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00008"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00007"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00008"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00006"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00006"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1",
   "max_input_tokens": 128,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "amazon/amazon.titan-embed-text-v1",
   "model_name": "amazon.titan-embed-text-v1",
   "display_name": "amazon.titan-embed-text-v1",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_embedding",
   "capabilities": {},
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "amazon/amazon.titan-embed-text-v2:0",
   "model_name": "amazon.titan-embed-text-v2:0",
   "display_name": "amazon.titan-embed-text-v2:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029"
      }
     },
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.417241"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02459"
      }
     },
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.500203"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.027"
      }
     },
     "region": "ap-northeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.024"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.027"
      }
     },
     "region": "ap-south-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "region": "ap-southeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.026"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.027"
      }
     },
     "region": "eu-central-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.021"
      }
     },
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.023"
      }
     },
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.021"
      }
     },
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.026"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "region": "eu-west-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "region": "us-gov-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "region": "us-gov-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.024"
      }
     },
     "region": "us-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_embedding",
   "capabilities": {},
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "amazon/amazon.titan-image-generator-v1",
   "model_name": "amazon.titan-image-generator-v1",
   "display_name": "amazon.titan-image-generator-v1",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.008"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.01"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.0107"
      }
     },
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.013"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.0101"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.018"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-west-2"
    }
   ],
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "amazon/amazon.titan-image-generator-v2",
   "model_name": "amazon.titan-image-generator-v2",
   "display_name": "amazon.titan-image-generator-v2",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.008"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      }
     }
    }
   ],
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "amazon/amazon.titan-image-generator-v2:0",
   "model_name": "amazon.titan-image-generator-v2:0",
   "display_name": "amazon.titan-image-generator-v2:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.008"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.012"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.012"
      }
     },
     "region": "us-west-2"
    }
   ],
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "amazon/amazon.titan-text-express-v1",
   "model_name": "amazon.titan-text-express-v1",
   "display_name": "amazon.titan-text-express-v1",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.076923",
        "completion": "0.176471"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.825"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.788"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.863"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.788"
      }
     },
     "region": "eu-west-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "region": "us-gov-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 42000,
   "max_output_tokens": 8000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "released_at": "2024-12-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "titan",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "amazon/amazon.titan-text-express-v1:0:8k",
   "model_name": "amazon.titan-text-express-v1:0:8k",
   "display_name": "Titan Text G1 - Express",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2024-12-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "titan",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Titan Text G1 - Express"
    }
   ]
  },
  {
   "slug": "amazon/amazon.titan-text-lite-v1",
   "model_name": "amazon.titan-text-lite-v1",
   "display_name": "amazon.titan-text-lite-v1",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.25",
        "completion": "0.25"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "region": "eu-west-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 42000,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "amazon/amazon.titan-text-premier-v1:0",
   "model_name": "amazon.titan-text-premier-v1:0",
   "display_name": "amazon.titan-text-premier-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "region": "us-east-1"
    }
   ],
   "max_input_tokens": 42000,
   "max_output_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "amazon/amazon.titan-tg1-large",
   "model_name": "amazon.titan-tg1-large",
   "display_name": "amazon.titan-tg1-large",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "amazon.titan-tg1-large"
    }
   ]
  },
  {
   "slug": "amazon/nova-2-lite-v1",
   "model_name": "nova-2-lite-v1",
   "display_name": "Nova 2 Lite",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "amazon/nova-2-lite-v1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5099999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.25"
      }
     },
     "provider_model_id": "amazon/nova-2-lite-v1"
    },
    {
     "provider": "nova",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "amazon/nova-2-lite-v1"
    }
   ],
   "max_input_tokens": 1000000,
   "family": "Nova",
   "capabilities": {
    "vision": true,
    "video_input": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2024-12-01",
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "pdf",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "benchmarks": {
    "intelligence_index": 18.2,
    "coding_index": 23,
    "agentic_index": 3.1
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon/nova-2-lite-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nova 2 Lite"
    }
   ]
  },
  {
   "slug": "amazon/nova-lite-v1",
   "model_name": "nova-lite-v1",
   "display_name": "Nova Lite",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.062"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.247"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "amazon/nova-lite-v1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0595"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.238"
      }
     },
     "provider_model_id": "amazon/nova-lite-v1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "amazon/nova-lite-v1"
    }
   ],
   "max_input_tokens": 300000,
   "family": "Nova",
   "capabilities": {
    "vision": true,
    "video_input": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true,
    "reasoning": true
   },
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-12-06",
   "max_output_tokens": 5120,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2024-10",
   "model_type": "vision_understanding",
   "deprecated": true,
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon/nova-lite-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nova Lite"
    }
   ]
  },
  {
   "slug": "amazon/nova-micro-v1",
   "model_name": "nova-micro-v1",
   "display_name": "Nova Micro",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.036"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.143"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "amazon/nova-micro-v1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0357"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1394"
      }
     },
     "provider_model_id": "amazon/nova-micro-v1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "amazon/nova-micro-v1"
    }
   ],
   "max_input_tokens": 128000,
   "family": "Nova",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-12-06",
   "max_output_tokens": 5120,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2024-10",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon/nova-micro-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nova Micro"
    }
   ]
  },
  {
   "slug": "amazon/nova-premier-v1",
   "model_name": "nova-premier-v1",
   "display_name": "Nova Premier",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "amazon/nova-premier-v1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "amazon/nova-premier-v1"
    }
   ],
   "max_input_tokens": 1000000,
   "family": "Nova",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2025-11-01",
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon/nova-premier-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nova Premier"
    }
   ]
  },
  {
   "slug": "amazon/nova-pro-v1",
   "model_name": "nova-pro-v1",
   "display_name": "Nova Pro",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "computeprices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.96"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.94"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.76"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.32"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.84"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.36"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.21"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.52"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.92"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.52"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.72"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "me-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "me-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "us-gov-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.96"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "us-gov-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "us.amazon.nova-pro-v1",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.016"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.061"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "amazon/nova-pro-v1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7989999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.1959999999999997"
      }
     },
     "provider_model_id": "amazon/nova-pro-v1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "amazon/nova-pro-v1"
    }
   ],
   "max_input_tokens": 300000,
   "family": "Nova",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "structured_output": true,
    "stream": true,
    "reasoning": true
   },
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2024-12-03",
   "knowledge_cutoff": "2024-04",
   "max_output_tokens": 5000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "deprecated": true,
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon/nova-pro-v1",
    "us.amazon.nova-pro-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nova Pro"
    }
   ]
  },
  {
   "slug": "amazon/regional.amazon.nova-2-lite-v1:0",
   "model_name": "regional.amazon.nova-2-lite-v1:0",
   "display_name": "regional.amazon.nova-2-lite-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     }
    }
   ],
   "intro": "Amazon Nova 2 Lite is an advanced multimodal reasoning model that intelligently balances performance and efficiency by dynamically adjusting reasoning depth based on task complexity. With flexible controls for developers to adjust the reasoning process, Nova 2 Lite delivers superior results for agentic workflows across software development, consumer experiences and enterprise application.",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.amazon.nova-2-lite-v1:0"
    }
   ]
  },
  {
   "slug": "amazon/rerank-v4.0-fast",
   "model_name": "rerank-v4.0-fast",
   "display_name": "rerank-v4.0-fast",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2000"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rerank-v4.0-fast"
    }
   ]
  },
  {
   "slug": "amazon/rerank-v4.0-pro",
   "model_name": "rerank-v4.0-pro",
   "display_name": "rerank-v4.0-pro",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2500"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "cohere",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.0025"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "listed",
     "note": "rerank-v4.0-pro"
    }
   ]
  },
  {
   "slug": "amazon/stability.sd3-5-large-v1:0",
   "model_name": "stability.sd3-5-large-v1:0",
   "display_name": "stability.sd3-5-large-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.08"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 77,
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "amazon/stability.sd3-large-v1:0",
   "model_name": "stability.sd3-large-v1:0",
   "display_name": "stability.sd3-large-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.00000008"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.00000008"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 77,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "amazon/stability.stable-diffusion-xl-v0",
   "model_name": "stability.stable-diffusion-xl-v0",
   "display_name": "stability.stable-diffusion-xl-v0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.018"
      }
     }
    }
   ],
   "max_input_tokens": 77,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "amazon/stability.stable-diffusion-xl-v1",
   "model_name": "stability.stable-diffusion-xl-v1",
   "display_name": "stability.stable-diffusion-xl-v1",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    }
   ],
   "max_input_tokens": 77,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "amazon/stability.stable-image-core-v1:1",
   "model_name": "stability.stable-image-core-v1:1",
   "display_name": "stability.stable-image-core-v1:1",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "stability.stable-image-core-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00000004"
      }
     },
     "provider_model_id": "stability.stable-image-core-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00000004"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "stability.stable-image-core-v1:0",
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 77,
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "stability.stable-image-core-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "amazon/stability.stable-image-ultra-v1:1",
   "model_name": "stability.stable-image-ultra-v1:1",
   "display_name": "stability.stable-image-ultra-v1:1",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.14"
      }
     },
     "provider_model_id": "stability.stable-image-ultra-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00000014"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.14"
      }
     },
     "provider_model_id": "stability.stable-image-ultra-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00000014"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.14"
      }
     },
     "provider_model_id": "stability.stable-image-ultra-v1:0",
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 77,
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "stability.stable-image-ultra-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "amazon/titan-embed-text-v2",
   "model_name": "titan-embed-text-v2",
   "display_name": "Titan Text Embeddings V2",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "amazon/titan-embed-text-v2"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "amazon/titan-embed-text-v2"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2024-04-30",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "titan-embed",
   "capabilities": {},
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon/titan-embed-text-v2"
   ],
   "intro_i18n": {
    "zh-CN": "Amazon Titan Text Embeddings V2 是一个轻量级、高效的多语言嵌入模型，支持 1024、512 和 256 维度。",
    "zh-TW": "Amazon Titan Text Embeddings V2 是一個輕量級、高效的多語言嵌入模型，支援 1024、512 和 256 維度。",
    "ja-JP": "Amazon Titan Text Embeddings V2 は軽量で効率的な多言語埋め込みモデルで、1024、512、256次元をサポートします。",
    "ru-RU": "Amazon Titan Text Embeddings V2 — это легкая и эффективная многоязычная модель эмбеддингов, поддерживающая размеры 1024, 512 и 256."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Titan Text Embeddings V2"
    }
   ]
  },
  {
   "slug": "amazon/us.amazon.nova-2-lite-v1:0",
   "model_name": "us.amazon.nova-2-lite-v1:0",
   "display_name": "us.amazon.nova-2-lite-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "amazon.nova-2-lite-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.01"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ap-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.01"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.96"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ap-northeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.95"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.41"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.39"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ap-southeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.63"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.71"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ap-southeast-4"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.41"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.39"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ap-southeast-5"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.41"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.39"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ap-southeast-7"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.67"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.085"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.81"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "ca-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.10725"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.429"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.597"
      }
     },
     "provider_model_id": "eu.amazon.nova-2-lite-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.550042"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.363"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.992"
      }
     },
     "provider_model_id": "eu.amazon.nova-2-lite-v1:0",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.132"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.411"
      }
     },
     "provider_model_id": "eu.amazon.nova-2-lite-v1:0",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.363"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.205"
      }
     },
     "provider_model_id": "eu.amazon.nova-2-lite-v1:0",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0935"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.374"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.157"
      }
     },
     "provider_model_id": "eu.amazon.nova-2-lite-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.105"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.52"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.121"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.484"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.059"
      }
     },
     "provider_model_id": "eu.amazon.nova-2-lite-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.095"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.13"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "il-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "me-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0975"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.21"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "us-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "global.amazon.nova-2-lite-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.335"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.822"
      }
     },
     "provider_model_id": "nova-2-lite"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "nova-2-Lite"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "amazon/nova-2-lite"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2024-12-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "knowledge_cutoff": "2024-10",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon.nova-2-lite-v1:0",
    "amazon/nova-2-lite",
    "apac.amazon.nova-2-lite-v1:0",
    "eu.amazon.nova-2-lite-v1:0",
    "global.amazon.nova-2-lite-v1:0",
    "jp.amazon.nova-2-lite-v1:0",
    "nova-2-Lite",
    "nova-2-lite"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "amazon/us.amazon.nova-2-pro-preview-20251202-v1:0",
   "model_name": "us.amazon.nova-2-pro-preview-20251202-v1:0",
   "display_name": "us.amazon.nova-2-pro-preview-20251202-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.1875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.546875"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.1875"
      }
     },
     "provider_model_id": "amazon.nova-2-pro-preview-20251202-v1:0"
    }
   ],
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon.nova-2-pro-preview-20251202-v1:0",
    "apac.amazon.nova-2-pro-preview-20251202-v1:0",
    "eu.amazon.nova-2-pro-preview-20251202-v1:0"
   ]
  },
  {
   "slug": "amazon/us.amazon.nova-canvas-v1:0",
   "model_name": "us.amazon.nova-canvas-v1:0",
   "display_name": "us.amazon.nova-canvas-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "provider_model_id": "amazon.nova-canvas-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "provider_model_id": "amazon.nova-canvas-v1:0",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "provider_model_id": "amazon.nova-canvas-v1:0",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "provider_model_id": "amazon.nova-canvas-v1:0",
     "region": "us-east-1"
    }
   ],
   "max_input_tokens": 2600,
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon.nova-canvas-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "amazon/us.amazon.nova-lite-v1:0",
   "model_name": "us.amazon.nova-lite-v1:0",
   "display_name": "us.amazon.nova-lite-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "2",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.288"
      }
     },
     "provider_model_id": "apac.amazon.nova-lite-v1:0",
     "region": "ap-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.288"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.666667",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.071"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.284"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0178"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.685393",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.071"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.284"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0178"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.685393",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.081"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.324"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0202"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.485149",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.063"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.252"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0157"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.910828",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.065"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0162"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.851852",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.288"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.666667",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.288"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.666667",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.064"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.256"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.016"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.875"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.078"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.312"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0195"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.538462",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.065"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0162"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.851852",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.096"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.384"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.024"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.25",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.066"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.264"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0165"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.818182",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.069"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.276"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0172"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.744186",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.084"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.336"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.352"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.363636",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0187"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "il-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "me-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "2",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "me-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "2",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "us-gov-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.288"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "us-gov-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.666667",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.077"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.308"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "us-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "amazon.nova-lite-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "2",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "amazon/nova-lite"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "amazon/nova-lite"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-12-03",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 300000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova-lite",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true,
    "assistant_prefill": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon.nova-lite-v1:0",
    "amazon/nova-lite",
    "apac.amazon.nova-lite-v1:0",
    "ca.amazon.nova-lite-v1:0",
    "eu.amazon.nova-lite-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "一款极低成本的多模态模型，能够以极快速度处理图像、视频和文本输入。",
    "zh-TW": "一款極低成本的多模態模型，能以極快速度處理圖像、影片與文字輸入。",
    "ja-JP": "非常に低コストで、画像、動画、テキスト入力を超高速で処理できるマルチモーダルモデルです。",
    "ru-RU": "Очень недорогая мультимодальная модель с чрезвычайно быстрой обработкой изображений, видео и текста."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "assistant_prefill: false→true"
    }
   ]
  },
  {
   "slug": "amazon/us.amazon.nova-micro-v1:0",
   "model_name": "us.amazon.nova-micro-v1:0",
   "display_name": "us.amazon.nova-micro-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.00875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "2",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "ap-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0105"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.042"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.168"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "apac.amazon.nova-micro-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.666667",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0103"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.041"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.164"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "apac.amazon.nova-micro-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.699029",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0103"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.041"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.164"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "apac.amazon.nova-micro-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.699029",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0117"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.047"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.188"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "apac.amazon.nova-micro-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.495726",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.037"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.148"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0093"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.88172",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.042"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "apac.amazon.nova-micro-v1:0",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.416667",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0115"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.046"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.184"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "eu.amazon.nova-micro-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.521739",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0095"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.038"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.152"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "eu.amazon.nova-micro-v1:0",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.842105",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.014"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.056"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.224"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "eu.amazon.nova-micro-v1:0",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.25",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0097"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.039"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.156"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "eu.amazon.nova-micro-v1:0",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.804124",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "eu.amazon.nova-micro-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.75",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.049"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.196"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.013"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.052"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.208"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "eu.amazon.nova-micro-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.346154",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.011"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.176"
      }
     },
     "provider_model_id": "eu.amazon.nova-micro-v1:0",
     "region": "il-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0087"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "apac.amazon.nova-micro-v1:0",
     "region": "me-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "2.011494",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "me-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.00875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.04375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.00875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "2",
        "cache_write": "1.6"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "us-gov-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.042"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.168"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "us-gov-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.04375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.00875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "amazon.nova-micro-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "2",
        "cache_write": "1.6"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.00875"
      }
     },
     "provider_model_id": "amazon/nova-micro"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "amazon/nova-micro"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-12-03",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova-micro",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "assistant_prefill": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon.nova-micro-v1:0",
    "amazon/nova-micro",
    "apac.amazon.nova-micro-v1:0",
    "eu.amazon.nova-micro-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "一款仅支持文本的模型，具备超低延迟和极低成本。",
    "zh-TW": "一款僅支援文字的模型，提供超低延遲與極低成本的運算效能。",
    "ja-JP": "超低レイテンシかつ非常に低コストで動作するテキスト専用モデルです。",
    "ru-RU": "Только текстовая модель с ультранизкой задержкой и минимальными затратами."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "assistant_prefill: false→true"
    }
   ]
  },
  {
   "slug": "amazon/us.amazon.nova-premier-v1:0",
   "model_name": "us.amazon.nova-premier-v1:0",
   "display_name": "us.amazon.nova-premier-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm+pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "amazon.nova-premier-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "max_output_tokens": 10000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "released_at": "2024-12-03",
   "knowledge_cutoff": "2024-10",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon.nova-premier-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "amazon/us.amazon.nova-pro-v1:0",
   "model_name": "us.amazon.nova-pro-v1:0",
   "display_name": "us.amazon.nova-pro-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "2",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.96"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.666667",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.684211",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.94"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.76"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.235"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.702128",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.32"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.481481",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.84"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.36"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.904762",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2175"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.83908",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.96"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "apac.amazon.nova-pro-v1:0",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.416667",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2625"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.52381",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2175"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.83908",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.21"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.25",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.52"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1.818182",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.92"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.73913",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.52"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.72"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.295"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1.355932",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "il-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "me-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "2",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "me-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "2",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "us-gov-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.96"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "us-gov-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.12"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "us-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "amazon.nova-pro-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "1",
        "cache_read": "2",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "amazon/nova-pro"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "amazon/nova-pro"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2024-12-03",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 300000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova-pro",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true,
    "assistant_prefill": true
   },
   "model_type": "vision_understanding",
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "amazon.nova-pro-v1:0",
    "amazon/nova-pro",
    "apac.amazon.nova-pro-v1:0",
    "eu.amazon.nova-pro-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "一款功能强大的多模态模型，在准确性、速度和成本之间实现最佳平衡，适用于多种任务。",
    "zh-TW": "一款功能強大的多模態模型，在準確性、速度與成本之間達到最佳平衡，適用於各類任務。",
    "ja-JP": "幅広いタスクにおいて、精度、速度、コストの最適なバランスを実現する高性能マルチモーダルモデルです。",
    "ru-RU": "Высокопроизводительная мультимодальная модель с оптимальным балансом точности, скорости и стоимости для широкого спектра задач."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "assistant_prefill: false→true"
    }
   ]
  },
  {
   "slug": "amazon/us.twelvelabs.marengo-embed-2-7-v1:0",
   "model_name": "us.twelvelabs.marengo-embed-2-7-v1:0",
   "display_name": "us.twelvelabs.marengo-embed-2-7-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "70"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      }
     },
     "provider_model_id": "eu.twelvelabs.marengo-embed-2-7-v1:0"
    }
   ],
   "max_input_tokens": 77,
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "eu.twelvelabs.marengo-embed-2-7-v1:0",
    "twelvelabs.marengo-embed-2-7-v1:0"
   ]
  },
  {
   "slug": "amazon/us.twelvelabs.pegasus-1-2-v1:0",
   "model_name": "us.twelvelabs.pegasus-1-2-v1:0",
   "display_name": "us.twelvelabs.pegasus-1-2-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "litellm",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "eu.twelvelabs.pegasus-1-2-v1:0"
    }
   ],
   "model_type": "vision_understanding",
   "capabilities": {
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "eu.twelvelabs.pegasus-1-2-v1:0",
    "twelvelabs.pegasus-1-2-v1:0"
   ]
  },
  {
   "slug": "amazon/writer.palmyra-vision-7b-v1:0",
   "model_name": "writer.palmyra-vision-7b-v1:0",
   "display_name": "writer.palmyra-vision-7b-v1:0",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "ap-southeast-4"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "writer.palmyra-vision-7b"
    }
   ],
   "capabilities": {
    "vision": true
   },
   "max_input_tokens": 4000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "writer.palmyra-vision-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "writer.palmyra-vision-7b-v1:0"
    }
   ]
  },
  {
   "slug": "amazon/writer.palmyra-x4-v1:0",
   "model_name": "writer.palmyra-x4-v1:0",
   "display_name": "Palmyra X4",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "us.writer.palmyra-x4-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "us.writer.palmyra-x4-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "us.writer.palmyra-x4-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "us.writer.palmyra-x4-v1:0",
     "region": "us-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "us.writer.palmyra-x4-v1:0",
     "region": "us-west-2"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-04-28",
   "max_input_tokens": 122880,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "palmyra",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "us.writer.palmyra-x4-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "amazon/writer.palmyra-x5-v1:0",
   "model_name": "writer.palmyra-x5-v1:0",
   "display_name": "Palmyra X5",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "us.writer.palmyra-x5-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "us.writer.palmyra-x5-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "us.writer.palmyra-x5-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "us.writer.palmyra-x5-v1:0",
     "region": "us-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "us.writer.palmyra-x5-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "writer/palmyra-x5"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "writer/palmyra-x5"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-04-28",
   "max_input_tokens": 1040000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "palmyra",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "palmyra-x5",
    "us.writer.palmyra-x5-v1:0",
    "writer/palmyra-x5"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "amazon/zai.glm-4.7",
   "model_name": "zai.glm-4.7",
   "display_name": "GLM-4.7",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.266"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.266"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.266"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "cerebras",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-glm-4.7"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-12-22",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "model_type": "deep_thinking",
   "status": "beta",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "functions",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-glm-4.7"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.7是智谱的新一代旗舰模型，总参数量为3550亿，活跃参数量为320亿，在通用对话、推理和代理能力方面全面升级。GLM-4.7增强了交错思维，并引入了保留思维和回合级思维。",
    "zh-TW": "GLM-4.7 是智譜的新一代旗艦模型，擁有3550億總參數和320億活躍參數，在通用對話、推理和代理能力方面全面升級。GLM-4.7 增強了交錯思考，並引入了保留思考和回合級思考。",
    "ja-JP": "GLM-4.7はZhipuの新世代フラッグシップモデルで、355Bの総パラメータと32Bのアクティブパラメータを備え、一般的な対話、推論、エージェント機能が完全にアップグレードされています。GLM-4.7はインターリーブド思考を強化し、保存思考およびターンレベル思考を導入しています。",
    "ru-RU": "GLM-4.7 — это новая флагманская модель Zhipu с 355B общих параметров и 32B активных параметров, полностью обновлённая в области общего диалога, рассуждений и агентных возможностей. GLM-4.7 улучшает Перемежающееся Мышление и вводит Сохранённое Мышление и Мышление на уровне хода."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    }
   ]
  },
  {
   "slug": "amazon/zai.glm-4.7-flash",
   "model_name": "zai.glm-4.7-flash",
   "display_name": "GLM-4.7-Flash",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0721"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.412"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0721"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.412"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2026-01-19",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 200000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm-flash",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "amazon/zai.glm-5",
   "model_name": "zai.glm-5",
   "display_name": "GLM-5",
   "vendor": "amazon",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "models-dev+litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.96"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.96"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-03-18",
   "max_input_tokens": 202752,
   "max_output_tokens": 101376,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "antgroup/Ling-1T",
   "model_name": "Ling-1T",
   "display_name": "Ling-1T",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.548"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.192"
      }
     },
     "provider_model_id": "inclusionAI/Ling-1T"
    },
    {
     "provider": "bailing",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "inclusionai/ling-1t"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-10",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ling",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inclusionAI/Ling-1T",
    "inclusionai/ling-1t"
   ],
   "intro_i18n": {
    "zh-CN": "Ling-1T 是 inclusionAI 推出的 1T MoE 模型，专为高强度推理任务与大上下文工作负载优化。",
    "zh-TW": "Ling-1T 是 inclusionAI 推出的 1 兆參數 MoE 模型，專為高強度推理任務與大上下文工作負載而優化。",
    "ja-JP": "Ling-1T は、inclusionAI による 1T MoE モデルで、高度な推論タスクや大規模コンテキスト処理に最適化されています。",
    "ru-RU": "Ling-1T — MoE-модель от inclusionAI с триллионом параметров, оптимизированная для задач с высокой нагрузкой на мышление и работы с большим контекстом."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ling-1T"
    }
   ]
  },
  {
   "slug": "antgroup/Ling-2.5-1T",
   "model_name": "Ling-2.5-1T",
   "display_name": "Ling-2.5-1T",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "antgroup",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "released_at": "2026-02-16",
   "max_input_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "作为Ling系列最新的旗舰实时模型，Ling-2.5-1T在模型架构、令牌效率和偏好对齐方面进行了全面升级，旨在将可访问AI的质量提升到一个新高度。",
    "zh-TW": "作為 Ling 系列最新的旗艦實時模型，Ling-2.5-1T 在模型架構、令牌效率和偏好對齊方面進行了全面升級，旨在將可訪問 AI 的質量提升到新高度。",
    "ja-JP": "Lingシリーズの最新フラッグシップリアルタイムモデルであるLing-2.5-1Tは、モデルアーキテクチャ、トークン効率、嗜好整合性において包括的なアップグレードを導入し、アクセス可能なAIの品質を新たなレベルに引き上げることを目指しています。",
    "ru-RU": "Как последняя флагманская модель реального времени в серии Ling, Ling-2.5-1T представляет собой комплексные улучшения архитектуры модели, эффективности токенов и выравнивания предпочтений, направленные на повышение качества доступного ИИ на новый уровень."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ling-2.5-1T"
    }
   ]
  },
  {
   "slug": "antgroup/Ling-2.6-1T",
   "model_name": "Ling-2.6-1T",
   "display_name": "Ling-2.6-1T",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "antgroup",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.661765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "inclusionAI/Ling-2.6-1T"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-1t"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-1t"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-1t"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-1t"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-1t"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "novita/inclusionai/ling-2.6-1t"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.0984625"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0263631"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1318155"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-1t"
    }
   ],
   "released_at": "2026-04-29",
   "max_input_tokens": 262144,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true,
    "structured_output": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ling",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inclusionAI/Ling-2.6-1T",
    "inclusionai/ling-2.6-1t",
    "novita/inclusionai/ling-2.6-1t"
   ],
   "intro_i18n": {
    "zh-CN": "最新的旗舰大语言模型，支持100万令牌上下文窗口，实现从逻辑推理到任务执行的端到端工作流程。",
    "zh-TW": "最新的旗艦大型語言模型，支持 1M 令牌上下文窗口，實現從邏輯推理到任務執行的端到端工作流程。",
    "ja-JP": "最新のフラッグシップ大規模言語モデルで、1Mトークンのコンテキストウィンドウをサポートし、論理的推論からタスク実行までのエンドツーエンドのワークフローを可能にします。",
    "ru-RU": "Последняя флагманская модель крупного языкового ИИ, поддерживающая контекстное окно на 1 миллион токенов и обеспечивающая сквозной рабочий процесс от логического рассуждения до выполнения задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ling-2.6-1T"
    }
   ]
  },
  {
   "slug": "antgroup/ling-2.6-flash:free",
   "model_name": "ling-2.6-flash:free",
   "display_name": "Ling-2.6-flash",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "antgroup",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      }
     },
     "provider_model_id": "Ling-2.6-flash"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-flash"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-flash"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-flash"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-flash"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-flash"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ling-2.6-flash-free"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.002"
      }
     },
     "provider_model_id": "inclusionai/ling-2.6-flash"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "novita/inclusionai/ling-2.6-flash"
    }
   ],
   "released_at": "2026-04-22",
   "max_input_tokens": 262144,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true,
    "structured_output": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ling",
   "knowledge_cutoff": "2025-06",
   "deprecated": true,
   "status": "deprecated",
   "benchmarks": {
    "intelligence_index": 14.1,
    "coding_index": 25.3,
    "agentic_index": 2.3
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Ling-2.6-flash",
    "inclusionai/ling-2.6-flash",
    "inclusionai/ling-2.6-flash:free",
    "ling-2.6-flash-free",
    "novita/inclusionai/ling-2.6-flash"
   ],
   "intro_i18n": {
    "zh-CN": "Ling-2.6-flash是Ling系列最新一代高性价比模型。采用专家混合（MoE）架构，总参数量为1000亿，每个令牌激活参数为61亿，在推理性能和计算成本之间实现了最佳平衡。",
    "zh-TW": "Ling-2.6-flash 是 Ling 系列最新一代高性價比模型。採用專家混合（MoE）架構，總參數量為 1000 億，每個令牌激活參數數量為 61 億，在推理性能與計算成本之間實現了最佳平衡。",
    "ja-JP": "Ling-2.6-flashはLingシリーズの最新世代の高コストパフォーマンスモデルです。Mixture-of-Experts（MoE）アーキテクチャを採用し、総パラメータ数は100B、トークンごとの活性化パラメータ数は6.1Bで、推論性能と計算コストの最適なバランスを実現しています。",
    "ru-RU": "Ling-2.6-flash — это модель последнего поколения с высокой производительностью и стоимостью в серии Ling. Она использует архитектуру Mixture-of-Experts (MoE) с общим количеством параметров 100 миллиардов и 6,1 миллиарда активированных параметров на токен, достигая оптимального баланса между производительностью вывода и вычислительными затратами."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ling-2.6-flash"
    }
   ]
  },
  {
   "slug": "antgroup/Ling-flash-2.0",
   "model_name": "Ling-flash-2.0",
   "display_name": "inclusionAI/Ling-flash-2.0",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.136"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.544"
      }
     },
     "provider_model_id": "inclusionAI/Ling-flash-2.0"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     },
     "provider_model_id": "inclusionAI/Ling-flash-2.0"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "inclusionAI/Ling-flash-2.0"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "inclusionAI/Ling-flash-2.0"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     },
     "provider_model_id": "inclusionai/ling-flash-2.0"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-09-18",
   "max_input_tokens": 131000,
   "max_output_tokens": 131000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ling",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inclusionAI/Ling-flash-2.0",
    "inclusionai/ling-flash-2.0"
   ],
   "intro_i18n": {
    "zh-CN": "Ling-flash-2.0 是蚂蚁集团百灵团队推出的第三款 Ling 2.0 架构模型。该模型采用 MoE 架构，总参数量为 100B，每个 token 激活参数仅为 6.1B（非嵌入部分为 4.8B）。尽管配置轻量，但在多个基准测试中表现与 40B 密集模型甚至更大 MoE 模型相当甚至更优，探索了通过架构与训练策略实现高效能的路径。",
    "zh-TW": "Ling-flash-2.0 是螞蟻集團百靈團隊推出的第三款 Ling 2.0 架構模型。該模型為 MoE 架構，總參數量為 1000 億，但每個 token 僅啟用 61 億參數（不含嵌入為 48 億）。儘管配置輕量，卻在多項基準測試中與 400 億密集模型甚至更大型 MoE 模型相媲美甚至超越，展現出透過架構與訓練策略實現高效能的潛力。",
    "ja-JP": "Ling-flash-2.0は、Ant GroupのBailingチームによるLing 2.0アーキテクチャの第3モデルです。MoE構造で、総パラメータ数は100B、トークンごとのアクティブパラメータは6.1B（埋め込みを除くと4.8B）です。軽量構成ながら、40Bの密モデルやさらに大きなMoEモデルと同等以上の性能を複数のベンチマークで発揮し、アーキテクチャと学習戦略による高効率を追求しています。",
    "ru-RU": "Ling-flash-2.0 — третья модель архитектуры Ling 2.0 от команды Bailing компании Ant Group. Это модель MoE с 100 миллиардами параметров, из которых активно только 6.1 миллиарда на токен (4.8 миллиарда без учета эмбеддингов). Несмотря на легкую конфигурацию, она сопоставима или превосходит плотные модели на 40 миллиардов и более крупные MoE-модели по многим метрикам, демонстрируя высокую эффективность благодаря архитектуре и стратегии обучения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "inclusionAI/Ling-flash-2.0"
    }
   ]
  },
  {
   "slug": "antgroup/Ling-mini-2.0",
   "model_name": "Ling-mini-2.0",
   "display_name": "inclusionAI/Ling-mini-2.0",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.272"
      }
     },
     "provider_model_id": "inclusionAI/Ling-mini-2.0"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "inclusionAI/Ling-mini-2.0"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "inclusionAI/Ling-mini-2.0"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "inclusionai/ling-mini-2.0"
    }
   ],
   "released_at": "2025-09-10",
   "max_input_tokens": 131000,
   "max_output_tokens": 131000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "ling",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inclusionAI/Ling-mini-2.0",
    "inclusionai/ling-mini-2.0"
   ],
   "intro_i18n": {
    "zh-CN": "Ling-mini-2.0 是一款小型高性能 MoE 大模型，总参数量为 16B，每个 token 激活参数仅为 1.4B（非嵌入部分为 789M），生成速度极快。凭借高效的 MoE 设计与大规模高质量训练数据，在性能上可媲美 10B 以下密集模型及更大 MoE 模型。",
    "zh-TW": "Ling-mini-2.0 是一款小型高效能 MoE 大語言模型，總參數為 160 億，每個 token 僅啟用 14 億參數（不含嵌入為 7.89 億），具備極快的生成速度。透過高效的 MoE 設計與大量高品質訓練資料，其效能可媲美 100 億以下的密集模型與更大型的 MoE 模型。",
    "ja-JP": "Ling-mini-2.0は、16Bの総パラメータを持ち、トークンごとのアクティブパラメータは1.4B（埋め込みを除くと789M）の高性能な小型MoE LLMです。高速生成が可能で、効率的なMoE設計と高品質な大規模学習データにより、10B未満の密モデルやより大きなMoEモデルに匹敵するトップクラスの性能を実現しています。",
    "ru-RU": "Ling-mini-2.0 — компактная высокопроизводительная MoE LLM с 16 миллиардами параметров и только 1.4 миллиарда активных на токен (789 миллионов без эмбеддингов), обеспечивающая очень быструю генерацию. Благодаря эффективной архитектуре MoE и большому объему качественных обучающих данных, она достигает уровня производительности, сопоставимого с плотными моделями до 10 миллиардов и более крупными MoE-моделями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "inclusionAI/Ling-mini-2.0"
    }
   ]
  },
  {
   "slug": "antgroup/llada2.1-flash",
   "model_name": "llada2.1-flash",
   "display_name": "LLaDA2.1-flash",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.057"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "inclusionai/llada2.1-flash"
    }
   ],
   "released_at": "2026-03-16",
   "max_input_tokens": 32000,
   "capabilities": {
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inclusionai/llada2.1-flash"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LLaDA2.1-flash"
    }
   ]
  },
  {
   "slug": "antgroup/ming-flash-omini-preview",
   "model_name": "ming-flash-omini-preview",
   "display_name": "Ming-flash-omini Preview",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "inclusionai/ming-flash-omini-preview"
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 32000,
   "model_type": "omni",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inclusionai/ming-flash-omini-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Ming-flash-omni Preview 是 inclusionAI 推出的多模态模型，支持语音、图像与视频输入，图像渲染与语音识别能力提升。",
    "zh-TW": "Ming-flash-omni 預覽版是 inclusionAI 的多模態模型，支援語音、圖像與影片輸入，並提升了圖像渲染與語音辨識能力。",
    "ja-JP": "Ming-flash-omni Preview は、inclusionAI によるマルチモーダルモデルで、音声・画像・動画入力に対応し、画像描画と音声認識が向上しています。",
    "ru-RU": "Ming-flash-omni Preview — мультимодальная модель от inclusionAI, поддерживает ввод речи, изображений и видео, с улучшенной визуализацией и распознаванием речи."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ming-flash-omini Preview"
    }
   ]
  },
  {
   "slug": "antgroup/Ring-1T",
   "model_name": "Ring-1T",
   "display_name": "Ring-1T",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.548"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.192"
      }
     },
     "provider_model_id": "inclusionAI/Ring-1T"
    },
    {
     "provider": "bailing",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "inclusionai/ring-1t"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-10",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ring",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inclusionAI/Ring-1T",
    "inclusionai/ring-1t"
   ],
   "intro_i18n": {
    "zh-CN": "Ring-1T 是 inclusionAI 推出的万亿参数 MoE 推理模型，适用于大规模推理与科研任务。",
    "zh-TW": "Ring-1T 是 inclusionAI 推出的兆級參數 MoE 推理模型，適用於大規模推理與研究任務。",
    "ja-JP": "Ring-1T は、inclusionAI による 1 兆パラメータの MoE 推論モデルで、大規模な推論や研究タスクに適しています。",
    "ru-RU": "Ring-1T — MoE-модель от inclusionAI с триллионом параметров, предназначенная для масштабных задач логического вывода и исследований."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ring-1T"
    }
   ]
  },
  {
   "slug": "antgroup/ring-2.6-1t:free",
   "model_name": "ring-2.6-1t:free",
   "display_name": "Ring-2.6-1T",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "antgroup",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.661765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      }
     },
     "provider_model_id": "Ring-2.6-1T"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "inclusionai/ring-2.6-1t"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "inclusionai/ring-2.6-1t"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "inclusionai/ring-2.6-1t"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "inclusionai/ring-2.6-1t"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "inclusionai/ring-2.6-1t"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ring-2.6-1t-free"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "inclusionai/ring-2.6-1t"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "novita/inclusionai/ring-2.6-1t"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "inclusionai/ring-2.6-1t"
    }
   ],
   "released_at": "2026-05-15",
   "max_input_tokens": 262144,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "pdf_input": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ring",
   "knowledge_cutoff": "2025-12",
   "deprecated": true,
   "status": "deprecated",
   "benchmarks": {
    "intelligence_index": 30.6,
    "coding_index": 42.8,
    "agentic_index": 18.9
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Ring-2.6-1T",
    "inclusionai/ring-2.6-1t",
    "inclusionai/ring-2.6-1t:free",
    "novita/inclusionai/ring-2.6-1t",
    "ring-2.6-1t-free"
   ],
   "intro_i18n": {
    "zh-CN": "Ring-2.6-1T是一个万亿参数规模的推理模型，每次推理激活约630亿参数。专为代理工作流设计，重点关注代理能力、工具使用和长时间任务执行，在PinchBench、ClawEval、TAU2-Bench和GAIA2-search等基准测试中表现领先。模型在执行质量、延迟和成本方面进行了优化，非常适合高级编程代理、复杂推理管道和大规模自主系统。",
    "zh-TW": "Ring-2.6-1T 是一個擁有萬億參數規模的推理模型，每次推理激活約 630 億參數。專為代理工作流程設計，專注於代理能力、工具使用和長期任務執行，在 PinchBench、ClawEval、TAU2-Bench 和 GAIA2-search 等基準測試中達到領先性能。該模型在執行質量、延遲和成本方面進行了優化，非常適合高級編程代理、複雜推理管道和大規模自主系統。",
    "ja-JP": "Ring-2.6-1Tは、推論モデルのトリリオンパラメータ規模で、推論ごとに約63Bのパラメータを活性化します。エージェントワークフロー向けに設計されており、エージェント能力、ツール使用、長期タスク実行に焦点を当てています。PinchBench、ClawEval、TAU2-Bench、GAIA2-searchなどのベンチマークで最高の性能を達成しています。実行品質、レイテンシ、コストの最適化が行われており、高度なコーディングエージェント、複雑な推論パイプライン、大規模な自律システムに適しています。",
    "ru-RU": "Ring-2.6-1T — это модель для рассуждений масштаба триллиона параметров, активирующая около 63 миллиардов параметров на один вывод. Разработана для рабочих процессов агентов, с акцентом на возможности агентов, использование инструментов и выполнение задач на длинных горизонтах, достигая ведущих результатов на таких эталонах, как PinchBench, ClawEval, TAU2-Bench и GAIA2-search. Модель оптимизирована по качеству выполнения, задержке и стоимости, что делает её подходящей для продвинутых агентов программирования, сложных конвейеров рассуждений и крупномасштабных автономных систем."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ring-2.6-1T"
    }
   ]
  },
  {
   "slug": "antgroup/Ring-flash-2.0",
   "model_name": "Ring-flash-2.0",
   "display_name": "inclusionAI/Ring-flash-2.0",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.136"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.544"
      }
     },
     "provider_model_id": "inclusionAI/Ring-flash-2.0"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "inclusionAI/Ring-flash-2.0"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     },
     "provider_model_id": "inclusionai/ring-flash-2.0"
    }
   ],
   "released_at": "2025-09-29",
   "max_input_tokens": 131000,
   "max_output_tokens": 131000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "ring",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inclusionAI/Ring-flash-2.0",
    "inclusionai/ring-flash-2.0"
   ],
   "intro_i18n": {
    "zh-CN": "Ring-flash-2.0 是 inclusionAI 推出的 Ring 系列变体，面向高吞吐场景，强调速度与成本效率。",
    "zh-TW": "Ring-flash-2.0 是 inclusionAI 推出的 Ring 模型變體，專為高吞吐量場景設計，強調速度與成本效益。",
    "ja-JP": "Ring-flash-2.0 は、inclusionAI による Ring モデルのバリアントで、高スループット環境向けに速度とコスト効率を重視しています。",
    "ru-RU": "Ring-flash-2.0 — вариант модели Ring от inclusionAI для сценариев с высокой пропускной способностью, с акцентом на скорость и экономичность."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "inclusionAI/Ring-flash-2.0"
    }
   ]
  },
  {
   "slug": "antgroup/ring-mini-2.0",
   "model_name": "ring-mini-2.0",
   "display_name": "Ring-mini-2.0",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "inclusionai/ring-mini-2.0"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inclusionai/ring-mini-2.0"
   ],
   "intro_i18n": {
    "zh-CN": "Ring-mini-2.0 是 inclusionAI 推出的高吞吐轻量级 MoE 模型，专为高并发设计。",
    "zh-TW": "Ring-mini-2.0 是 inclusionAI 推出的高吞吐量輕量級 MoE 模型，專為高併發場景打造。",
    "ja-JP": "Ring-mini-2.0 は、inclusionAI による高スループット軽量 MoE モデルで、並列処理に最適化されています。",
    "ru-RU": "Ring-mini-2.0 — легковесная MoE-модель от inclusionAI с высокой пропускной способностью, разработана для параллельной обработки."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ring-mini-2.0"
    }
   ]
  },
  {
   "slug": "antgroup/siliconflow-inclusion-ai-ling-mini-2",
   "model_name": "siliconflow-inclusion-ai-ling-mini-2",
   "display_name": "inclusionAI/Ling-mini-2.0",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    }
   ],
   "released_at": "2025-09-10",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "inclusionAI/Ling-mini-2.0"
    }
   ]
  },
  {
   "slug": "antgroup/siliconflow-inclusionai-ling-flash-2",
   "model_name": "siliconflow-inclusionai-ling-flash-2",
   "display_name": "inclusionAI/Ling-flash-2.0",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.572"
      }
     }
    }
   ],
   "released_at": "2025-09-30",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "inclusionAI/Ling-flash-2.0"
    }
   ]
  },
  {
   "slug": "antgroup/siliconflow-inclusionai-ring-flash-2",
   "model_name": "siliconflow-inclusionai-ring-flash-2",
   "display_name": "inclusionAI/Ring-flash-2.0",
   "vendor": "antgroup",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.572"
      }
     }
    }
   ],
   "released_at": "2025-09-30",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "inclusionAI/Ring-flash-2.0"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-3-haiku",
   "model_name": "anthropic--claude-3-haiku",
   "display_name": "anthropic--claude-3-haiku",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "intro": "Fast Claude model for responsive assistance, classification, and lightweight agents",
   "released_at": "2024-03-13",
   "knowledge_cutoff": "2023-08",
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-3-haiku"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-3-opus",
   "model_name": "anthropic--claude-3-opus",
   "display_name": "anthropic--claude-3-opus",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2024-02-29",
   "knowledge_cutoff": "2023-08",
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-3-opus"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-3-sonnet",
   "model_name": "anthropic--claude-3-sonnet",
   "display_name": "anthropic--claude-3-sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2024-03-04",
   "knowledge_cutoff": "2023-08",
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-3-sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-3.5-sonnet",
   "model_name": "anthropic--claude-3.5-sonnet",
   "display_name": "anthropic--claude-3.5-sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2024-10-22",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 200000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-3.5-sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-3.7-sonnet",
   "model_name": "anthropic--claude-3.7-sonnet",
   "display_name": "anthropic--claude-3.7-sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-02-24",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-3.7-sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-4-opus",
   "model_name": "anthropic--claude-4-opus",
   "display_name": "anthropic--claude-4-opus",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-05-22",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-4-opus"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-4-sonnet",
   "model_name": "anthropic--claude-4-sonnet",
   "display_name": "anthropic--claude-4-sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-05-22",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-4-sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-4.5-haiku",
   "model_name": "anthropic--claude-4.5-haiku",
   "display_name": "anthropic--claude-4.5-haiku",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "intro": "Fast Claude model for responsive assistance, classification, and lightweight agents",
   "released_at": "2025-10-15",
   "knowledge_cutoff": "2025-02",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-4.5-haiku"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-4.5-opus",
   "model_name": "anthropic--claude-4.5-opus",
   "display_name": "anthropic--claude-4.5-opus",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-11-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-4.5-opus"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-4.5-sonnet",
   "model_name": "anthropic--claude-4.5-sonnet",
   "display_name": "anthropic--claude-4.5-sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-09-29",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-4.5-sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-4.6-opus",
   "model_name": "anthropic--claude-4.6-opus",
   "display_name": "anthropic--claude-4.6-opus",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-4.6-opus"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-4.6-sonnet",
   "model_name": "anthropic--claude-4.6-sonnet",
   "display_name": "anthropic--claude-4.6-sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2026-02-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-4.6-sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-4.7-opus",
   "model_name": "anthropic--claude-4.7-opus",
   "display_name": "anthropic--claude-4.7-opus",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-04-16",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic--claude-4.7-opus"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic--claude-4.8-opus",
   "model_name": "anthropic--claude-4.8-opus",
   "display_name": "anthropic--claude-4.8-opus",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    }
   ],
   "intro": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
   "released_at": "2026-05-28",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "anthropic--claude-4.8-opus"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-3-5-haiku",
   "model_name": "anthropic-claude-3-5-haiku",
   "display_name": "Claude 3.5 Haiku",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "anthropic-claude-3-5-haiku-20241022"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "anthropic-claude-3.5-haiku"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2024-11-05",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic-claude-3-5-haiku-20241022",
    "anthropic-claude-3.5-haiku"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 3.5 Haiku"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-3-5-haiku-20241022-Code",
   "model_name": "anthropic-claude-3-5-haiku-20241022-Code",
   "display_name": "claude-3-5-haiku-20241022（Claude Code）",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "released_at": "2025-09-15",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3-5-haiku-20241022（Claude Code）"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-3-5-haiku-latest",
   "model_name": "anthropic-claude-3-5-haiku-latest",
   "display_name": "claude-3-5-haiku-latest",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "released_at": "2025-08-06",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3-5-haiku-latest"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-3-haiku-20240307",
   "model_name": "anthropic-claude-3-haiku-20240307",
   "display_name": "claude-3-haiku-20240307",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "released_at": "2024-03-07",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3-haiku-20240307"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-3-opus",
   "model_name": "anthropic-claude-3-opus",
   "display_name": "Claude 3 Opus",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2024-02-29",
   "knowledge_cutoff": "2023-08",
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 3 Opus"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-3.5-sonnet",
   "model_name": "anthropic-claude-3.5-sonnet",
   "display_name": "Claude 3.5 Sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2024-06-20",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 200000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 3.5 Sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-3.7-sonnet",
   "model_name": "anthropic-claude-3.7-sonnet",
   "display_name": "Claude 3.7 Sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-02-24",
   "knowledge_cutoff": "2024-11",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 3.7 Sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-4.1-opus",
   "model_name": "anthropic-claude-4.1-opus",
   "display_name": "Claude Opus 4.1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-08-05",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.1"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-4.5-haiku",
   "model_name": "anthropic-claude-4.5-haiku",
   "display_name": "Claude Haiku 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "intro": "Fast Claude model for responsive assistance, classification, and lightweight agents",
   "released_at": "2025-10-15",
   "knowledge_cutoff": "2025-02",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Haiku 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-4.5-sonnet",
   "model_name": "anthropic-claude-4.5-sonnet",
   "display_name": "Claude Sonnet 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-09-29",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-4.6-sonnet",
   "model_name": "anthropic-claude-4.6-sonnet",
   "display_name": "Claude Sonnet 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2026-02-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4.6"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-fable-5",
   "model_name": "anthropic-claude-fable-5",
   "display_name": "Anthropic Claude Fable 5",
   "vendor": "anthropic",
   "pricing": [],
   "intro": "Claude model for creative writing, analysis, and controlled agent workflows",
   "released_at": "2026-06-09",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-fable",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Anthropic Claude Fable 5"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-haiku-4.5",
   "model_name": "anthropic-claude-haiku-4.5",
   "display_name": "Claude Haiku 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "anthropic-claude-haiku-4-5-20251001"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "intro": "Fast Claude model for responsive assistance, classification, and lightweight agents",
   "released_at": "2025-10-15",
   "knowledge_cutoff": "2025-02",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic-claude-haiku-4-5-20251001"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Haiku 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-opus-4",
   "model_name": "anthropic-claude-opus-4",
   "display_name": "Claude Opus 4",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "anthropic-claude-opus-4-20250514"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-05-22",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic-claude-opus-4-20250514"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-opus-4-1-20250805",
   "model_name": "anthropic-claude-opus-4-1-20250805",
   "display_name": "claude-opus-4-1-20250805",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    }
   ],
   "released_at": "2025-08-05",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-1-20250805"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-opus-4-1-20250805-thinking",
   "model_name": "anthropic-claude-opus-4-1-20250805-thinking",
   "display_name": "claude-opus-4-1-20250805-thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    }
   ],
   "released_at": "2025-10-09",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-1-20250805-thinking"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-opus-4-20250514-thinking",
   "model_name": "anthropic-claude-opus-4-20250514-thinking",
   "display_name": "claude-opus-4-20250514-thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    }
   ],
   "released_at": "2025-05-27",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-20250514-thinking"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-opus-4-7",
   "model_name": "anthropic-claude-opus-4-7",
   "display_name": "Claude Opus 4.7",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic-claude-opus-4.7"
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-04-16",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic-claude-opus-4.7"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.7"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-opus-4-8",
   "model_name": "anthropic-claude-opus-4-8",
   "display_name": "Claude Opus 4.8",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic-claude-opus-4.8"
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-05-28",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic-claude-opus-4.8"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.8"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-opus-4.5",
   "model_name": "anthropic-claude-opus-4.5",
   "display_name": "Claude Opus 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic-claude-opus-4-5-20251101"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-11-24",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic-claude-opus-4-5-20251101"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-opus-4.6",
   "model_name": "anthropic-claude-opus-4.6",
   "display_name": "Claude Opus 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.6"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-sonnet-4",
   "model_name": "anthropic-claude-sonnet-4",
   "display_name": "Claude Sonnet 4",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic-claude-sonnet-4-20250514"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-05-22",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic-claude-sonnet-4-20250514"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-sonnet-4-20250514-thinking",
   "model_name": "anthropic-claude-sonnet-4-20250514-thinking",
   "display_name": "claude-sonnet-4-20250514-thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2025-05-27",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-20250514-thinking"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-sonnet-4-5-20250929",
   "model_name": "anthropic-claude-sonnet-4-5-20250929",
   "display_name": "claude-sonnet-4-5-20250929",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2025-09-29",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-5-20250929"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-sonnet-4-5-20250929-thinking",
   "model_name": "anthropic-claude-sonnet-4-5-20250929-thinking",
   "display_name": "claude-sonnet-4-5-20250929-thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2025-09-29",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-5-20250929-thinking"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-sonnet-4-6",
   "model_name": "anthropic-claude-sonnet-4-6",
   "display_name": "claude-sonnet-4-6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2026-02-17",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-6"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-claude-sonnet-4-6-thinking",
   "model_name": "anthropic-claude-sonnet-4-6-thinking",
   "display_name": "claude-sonnet-4-6-thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2026-02-17",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-6-thinking"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic-opus-4-6",
   "model_name": "anthropic-opus-4-6",
   "display_name": "anthropic-opus-4-6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic-opus-4-6"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic.claude-mythos-preview",
   "model_name": "anthropic.claude-mythos-preview",
   "display_name": "anthropic.claude-mythos-preview",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anthropic.claude-mythos-preview"
    }
   ]
  },
  {
   "slug": "anthropic/anthropic.claude-v2",
   "model_name": "anthropic.claude-v2",
   "display_name": "Claude 2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     }
    }
   ],
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2023-07-11",
   "knowledge_cutoff": "2023-08",
   "max_input_tokens": 100000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "intro_i18n": {
    "zh-CN": "一款功能全面的模型，擅长处理复杂对话、创意生成和详细指令执行等任务。",
    "zh-TW": "一款功能全面的模型，涵蓋複雜對話、創意生成與精確指令執行等任務。",
    "ja-JP": "複雑な対話や創造的な生成、詳細な指示の実行など、幅広いタスクに対応可能な高性能モデルです。",
    "ru-RU": "Высокопроизводительная модель для задач от сложного диалога и креативной генерации до точного следования инструкциям."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 2"
    }
   ]
  },
  {
   "slug": "anthropic/cd-3-5-hk-20241022",
   "model_name": "cd-3-5-hk-20241022",
   "display_name": "Claude 3.5 Haiku",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "pa/cd-3-5-hk-20241022"
    }
   ],
   "intro": "Our fastest model. Intelligence at blazing speeds. Multilingual and vision capabilities. 8,192 max output tokens. Training data cut-off: July 2024. API model name: claude-3-5-haiku-20241022",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 200000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "pa/cd-3-5-hk-20241022"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 3.5 Haiku"
    }
   ]
  },
  {
   "slug": "anthropic/cd-3-5-st-20241022",
   "model_name": "cd-3-5-st-20241022",
   "display_name": "Claude 3.5 Sonnet v2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "pa/cd-3-5-st-20241022"
    }
   ],
   "intro": "Our previous intelligent model with high level of intelligence and capability. Fast latency with multilingual and vision capabilities, but no extended thinking. 8,192 max output tokens. Training data cut-off: April 2024. Upgraded version API: claude-3-5-sonnet-20241022, Previous version API: claude-3-5-sonnet-20240620",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 200000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "pa/cd-3-5-st-20241022"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 3.5 Sonnet v2"
    }
   ]
  },
  {
   "slug": "anthropic/cd-3-7-st-20250219",
   "model_name": "cd-3-7-st-20250219",
   "display_name": "Claude 3.7 Sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "pa/cd-3-7-st-20250219"
    }
   ],
   "intro": "High-performance model with toggleable extended thinking for complex reasoning tasks. Combines high intelligence with the ability to think through problems step-by-step. Fast latency with 64,000 max output tokens. API model name: claude-3-7-sonnet-20250219",
   "knowledge_cutoff": "2025-02",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "pa/cd-3-7-st-20250219"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 3.7 Sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/cd-3-hk-20240307",
   "model_name": "cd-3-hk-20240307",
   "display_name": "Claude 3 Haiku",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "pa/cd-3-hk-20240307"
    }
   ],
   "intro": "Claude 3 Haiku is Anthropic's fastest and most compact model. Designed for near-instant responsiveness and seamless AI experiences that mimic human interactions. Multilingual and vision capabilities. 4,096 max output tokens. Training data cut-off: August 2023. API model name: claude-3-haiku-20240307",
   "knowledge_cutoff": "2024-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "pa/cd-3-hk-20240307"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 3 Haiku"
    }
   ]
  },
  {
   "slug": "anthropic/cd-op-4-20250514",
   "model_name": "cd-op-4-20250514",
   "display_name": "Claude Opus 4",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "pa/cd-op-4-20250514"
    }
   ],
   "intro": "Our previous flagship model with very high intelligence and capability. Supports extended thinking, multilingual capabilities, and vision processing. Moderately fast latency with 32,000 max output tokens. Training data cut-off: March 2025. API model name: claude-opus-4-20250514",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "stop",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "pa/cd-op-4-20250514"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4"
    }
   ]
  },
  {
   "slug": "anthropic/cd-st-4-20250514",
   "model_name": "cd-st-4-20250514",
   "display_name": "Claude Sonnet 4",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "pa/cd-st-4-20250514",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "High-performance model with high intelligence and balanced performance. Supports extended thinking, multilingual capabilities, and vision processing. Fast latency with 64,000 max output tokens. API model name: claude-sonnet-4-20250514",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "stop",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "pa/cd-st-4-20250514"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4"
    }
   ]
  },
  {
   "slug": "anthropic/claude",
   "model_name": "claude",
   "display_name": "Claude 2.1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      },
      "audio_input": {
       "unit": "per_second",
       "price": "0.0455"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0.0455"
      }
     },
     "provider_model_id": "anthropic.claude-v2:1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     },
     "provider_model_id": "anthropic.claude-v2:1",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     },
     "provider_model_id": "anthropic.claude-v2:1",
     "region": "ap-southeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     },
     "provider_model_id": "anthropic.claude-v2:1",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "65.36"
      }
     },
     "provider_model_id": "anthropic.claude-v2:1",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "65.36"
      }
     },
     "provider_model_id": "anthropic.claude-v2:1",
     "region": "us-west-2"
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     },
     "provider_model_id": "anthropic.claude-v2:1"
    }
   ],
   "max_input_tokens": 100000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2023-11-21",
   "knowledge_cutoff": "2023-08",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-v2:1"
   ],
   "intro_i18n": {
    "zh-CN": "Claude 2 的升级版，具备双倍上下文窗口，并在长文档处理和 RAG 场景中提升了可靠性、幻觉率和基于证据的准确性。",
    "zh-TW": "Claude 2 的升級版，具備雙倍上下文視窗，並在長文件與檢索增強生成（RAG）任務中提升可靠性、降低幻覺率與提升基於證據的準確性。",
    "ja-JP": "Claude 2 のアップデート版で、コンテキストウィンドウが2倍に拡張され、長文文書や RAG における信頼性、幻覚率、根拠に基づく正確性が向上しています。",
    "ru-RU": "Обновленная версия Claude 2 с удвоенным контекстом, улучшенной надежностью, сниженным уровнем галлюцинаций и повышенной точностью на основе доказательств для длинных документов и RAG."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 2.1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-2",
   "model_name": "claude-2",
   "display_name": "claude-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.8"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     },
     "provider_model_id": "anthropic/claude-2"
    }
   ],
   "intro": "Claude 2 is Anthropic's previous generation model, offering reliable performance for various tasks. This includes Claude 2.0 and Claude 2.1.\n",
   "max_input_tokens": 200000,
   "capabilities": {
    "function_calling": true
   },
   "max_output_tokens": 8191,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-2.0",
   "model_name": "claude-2.0",
   "display_name": "Claude 2.0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "39.6"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     }
    }
   ],
   "released_at": "2023-07-11",
   "knowledge_cutoff": "2023",
   "max_input_tokens": 100000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Claude 2 提供关键的企业级改进，包括领先的 20 万 token 上下文窗口、减少幻觉、系统提示支持，以及新测试功能：工具调用。",
    "zh-TW": "Claude 2 提供企業級關鍵改進，包括領先的 20 萬 token 上下文、降低幻覺、系統提示與新測試功能：工具調用。",
    "ja-JP": "Claude 2は、200Kトークンのコンテキスト、幻覚の削減、システムプロンプト、ツール呼び出しの新機能など、エンタープライズ向けの主要な改善を提供します。",
    "ru-RU": "Claude 2 предлагает ключевые улучшения для бизнеса, включая контекст до 200 тысяч токенов, снижение галлюцинаций, системные подсказки и новую функцию тестирования — вызов инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 2.0"
    }
   ]
  },
  {
   "slug": "anthropic/claude-2.1",
   "model_name": "claude-2.1",
   "display_name": "Claude 2.1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "39.6"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     }
    }
   ],
   "capabilities": {},
   "released_at": "2023-11-21",
   "knowledge_cutoff": "2023",
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Claude 2 提供关键的企业级改进，包括领先的 20 万 token 上下文窗口、减少幻觉、系统提示支持，以及新测试功能：工具调用。",
    "zh-TW": "Claude 2 提供企業級關鍵改進，包括領先的 20 萬 token 上下文、降低幻覺、系統提示與新測試功能：工具調用。",
    "ja-JP": "Claude 2は、200Kトークンのコンテキスト、幻覚の削減、システムプロンプト、ツール呼び出しの新機能など、エンタープライズ向けの主要な改善を提供します。",
    "ru-RU": "Claude 2 предлагает ключевые улучшения для бизнеса, включая контекст до 200 тысяч токенов, снижение галлюцинаций, системные подсказки и новую функцию тестирования — вызов инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 2.1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-5-haiku",
   "model_name": "claude-3-5-haiku",
   "display_name": "Claude 3.5 Haiku",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "truefoundry+helicone-registry+computeprices+portkey+llmdb+llm-prices-www",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-3-5-haiku-20241022",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "claude-3-5-haiku-20241022"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+helicone-registry+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "anthropic.claude-3-5-haiku-20241022-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-5-haiku-20241022-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-5-haiku-20241022-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-5-haiku-20241022-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "anthropic/claude-3-5-haiku"
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+truefoundry+helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "claude-3-5-haiku@20241022",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "claude-3-5-haiku@20241022"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7999999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "claude-3.5-haiku"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.76"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.8"
      }
     },
     "provider_model_id": "claude-3-5-haiku-20241022"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-haiku"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "claude-3-5-haiku-20241022"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-haiku"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-haiku"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-haiku"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-haiku"
    }
   ],
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "assistant_prefill": true,
    "vision": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true,
    "reasoning": true
   },
   "intro": "Our fastest model. Intelligence at blazing speeds. Multilingual and vision capabilities. 8,192 max output tokens. Training data cut-off: July 2024. API model name: claude-3-5-haiku-20241022",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 200000,
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "family": "Haiku",
   "released_at": "2024-10-22",
   "deprecated": true,
   "status": "deprecated",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-3-5-haiku-20241022-v1:0",
    "anthropic/claude-3-5-haiku",
    "anthropic/claude-3-5-haiku-20241022",
    "anthropic/claude-3-5-haiku@20241022",
    "anthropic/claude-3.5-haiku",
    "claude-3-5-haiku-20241022",
    "claude-3-5-haiku@20241022",
    "claude-3.5-haiku",
    "claude-3.5-haiku-20241022",
    "eu.anthropic.claude-3-5-haiku-20241022-v1:0",
    "us.anthropic.claude-3-5-haiku-20241022-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "Claude 3.5 Haiku 提升了速度、编程准确性和工具使用能力，适用于对速度和工具交互要求较高的场景。",
    "zh-TW": "Claude 3.5 Haiku 提升了速度、程式碼準確性與工具使用能力，適用於對速度與工具互動有高要求的場景。",
    "ja-JP": "Claude 3.5 Haiku は、速度、コーディング精度、ツール使用の性能が強化されており、速度とツール連携が求められるシナリオに適しています。",
    "ru-RU": "Claude 3.5 Haiku отличается повышенной скоростью, точностью программирования и эффективным использованием инструментов, подходит для сценариев с высокими требованиями к скорости и взаимодействию с инструментами."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 3.5 Haiku"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-5-haiku-latest",
   "model_name": "claude-3-5-haiku-latest",
   "display_name": "claude-3-5-haiku-latest",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "intro": "Fastest, most cost-effective model",
   "max_input_tokens": 200000,
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "released_at": "2024-10-22",
   "knowledge_cutoff": "2024-07",
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Claude 3.5 Haiku 提供快速响应，适用于轻量级任务。",
    "zh-TW": "Claude 3.5 Haiku 提供快速回應，適用於輕量任務。",
    "ja-JP": "Claude 3.5 Haikuは、軽量タスク向けに高速な応答を提供します。",
    "ru-RU": "Claude 3.5 Haiku обеспечивает быстрые ответы для легких задач."
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3-5-haiku-latest"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-5-sonnet",
   "model_name": "claude-3-5-sonnet",
   "display_name": "Claude 3.5 Sonnet v2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-3-5-sonnet-20240620",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+helicone-registry+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-3-5-sonnet-20240620-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_write": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
     "region": "ap-northeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
     "region": "ap-south-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      }
     },
     "provider_model_id": "us-gov.anthropic.claude-3-5-sonnet-20240620-v1:0",
     "region": "us-gov-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.6",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic.claude-3-5-sonnet-20241022-v2:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic.claude-3-5-sonnet-20240620-v1:0"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-sonnet"
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-3-5-sonnet",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-3-5-sonnet@20240620"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.25"
      }
     },
     "provider_model_id": "claude-3-5-sonnet-20241022"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-sonnet"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-3.5-sonnet"
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-sonnet"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-sonnet"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-sonnet"
    }
   ],
   "intro": "Claude 3.5 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.",
   "max_input_tokens": 200000,
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "assistant_prefill": true,
    "vision": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true,
    "reasoning": true,
    "computer_use": true
   },
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "knowledge_cutoff": "2024-10",
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "family": "Sonnet",
   "released_at": "2024-06-20",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-3-5-sonnet-20240620-v1:0",
    "anthropic.claude-3-5-sonnet-20241022-v2:0",
    "anthropic/claude-3-5-sonnet",
    "anthropic/claude-3-5-sonnet@20240620",
    "anthropic/claude-3.5-sonnet",
    "anthropic/claude-3.5-sonnet-20240620",
    "apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
    "apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
    "claude-3-5-sonnet-20240620",
    "claude-3-5-sonnet-20241022",
    "claude-3-5-sonnet@20240620",
    "claude-3-5-sonnet@20241022",
    "claude-3.5-sonnet",
    "eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
    "eu.anthropic.claude-3-5-sonnet-20241022-v2:0",
    "us-gov.anthropic.claude-3-5-sonnet-20240620-v1:0",
    "us.anthropic.claude-3-5-sonnet-20240620-v1:0",
    "us.anthropic.claude-3-5-sonnet-20241022-v2:0"
   ],
   "intro_i18n": {
    "zh-CN": "Claude 3.5 Sonnet 提升了行业标准，在广泛评估中超越竞争对手和 Claude 3 Opus，同时保持中等速度和成本。",
    "zh-TW": "Claude 3.5 Sonnet 提升了業界標準，在多項評估中超越競爭對手與 Claude 3 Opus，同時維持中階速度與成本。",
    "ja-JP": "Claude 3.5 Sonnet は業界標準を引き上げ、幅広い評価において競合他社や Claude 3 Opus を上回る性能を発揮しながら、中程度の速度とコストを維持します。",
    "ru-RU": "Claude 3.5 Sonnet поднимает отраслевой стандарт, превосходя конкурентов и Claude 3 Opus по широкому спектру оценок, сохраняя при этом средний уровень скорости и стоимости."
   },
   "price_history": [
    {
     "date": "2026-07-05",
     "kind": "listed",
     "note": "Claude 3.5 Sonnet v2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-5-sonnet-latest",
   "model_name": "claude-3-5-sonnet-latest",
   "display_name": "claude-3-5-sonnet-latest",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "assistant_prefill": true,
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3-5-sonnet-latest"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-5-sonnet-v2",
   "model_name": "claude-3-5-sonnet-v2",
   "display_name": "Anthropic: Claude 3.5 Sonnet v2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+helicone-registry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-3-5-sonnet-v2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.30000000000000004"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-3.5-sonnet-v2"
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2024-10-22",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 200000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-3-5-sonnet-v2",
    "anthropic/claude-3-5-sonnet-v2@20241022",
    "claude-3-5-sonnet-v2@20241022",
    "claude-3.5-sonnet-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Anthropic: Claude 3.5 Sonnet v2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-7-sonnet-20250219",
   "model_name": "claude-3-7-sonnet-20250219",
   "display_name": "claude-3-7-sonnet-20250219",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "litellm+helicone-registry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-3.7-sonnet",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "claude-3-7-sonnet"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+helicone-registry+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-3-7-sonnet-20240620-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.416667",
        "completion": "0.416667"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      }
     },
     "provider_model_id": "us-gov.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "us-gov-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-7-sonnet-20250219-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-7-sonnet-20250219-v1:0"
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-3-7-sonnet"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+helicone-registry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-3-7-sonnet@20250219",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "claude-3-7-sonnet@20250219"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.30000000000000004"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-3.7-sonnet"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.25"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-3.7-sonnet"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+helicone-registry+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0048"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-3.7-sonnet"
    },
    {
     "provider": "replicate",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "claude-3-7-sonnet"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-3-7-sonnet"
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "claude-3-7-sonnet"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-3.7-sonnet"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-3.7-sonnet"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-3.7-sonnet"
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-02-19",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "web_search": true,
    "assistant_prefill": true,
    "stream": true
   },
   "intro": "High-performance model with toggleable extended thinking for complex reasoning tasks. Combines high intelligence with the ability to think through problems step-by-step. Fast latency with 64,000 max output tokens. API model name: claude-3-7-sonnet-20250219",
   "knowledge_cutoff": "2025-02",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "released_at": "2025-02-19",
   "family": "claude-sonnet",
   "status": "deprecated",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-3-7-sonnet-20240620-v1:0",
    "anthropic.claude-3-7-sonnet-20250219-v1:0",
    "anthropic/claude-3-7-sonnet",
    "anthropic/claude-3-7-sonnet@20250219",
    "anthropic/claude-3.7-sonnet",
    "anthropic/claude-3.7-sonnet:thinking",
    "apac.anthropic.claude-3-7-sonnet-20250219-v1:0",
    "claude-3-7-sonnet",
    "claude-3-7-sonnet@20250219",
    "claude-3.7-sonnet",
    "claude-3.7-sonnet:thinking",
    "eu.anthropic.claude-3-7-sonnet-20250219-v1:0",
    "us-gov.anthropic.claude-3-7-sonnet-20250219-v1:0",
    "us.anthropic.claude-3-7-sonnet-20250219-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "Claude 3.7 Sonnet 是升级版 Sonnet 模型，具备更强的推理和编程能力，适用于企业级复杂任务。",
    "zh-TW": "Claude 3.7 Sonnet 是升級版的 Sonnet 模型，具備更強的推理與程式能力，適用於企業級複雜任務。",
    "ja-JP": "Claude 3.7 Sonnet は、推論力とコーディング能力が強化された Sonnet モデルのアップグレード版で、企業レベルの複雑なタスクに適しています。",
    "ru-RU": "Claude 3.7 Sonnet — обновленная модель Sonnet с улучшенными логическими и программными возможностями, подходящая для сложных корпоративных задач."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "replicate",
     "charge": "completion",
     "old": "0.015",
     "new": "15"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-7-sonnet-latest",
   "model_name": "claude-3-7-sonnet-latest",
   "display_name": "Claude 3.7 Sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "pydantic-prices+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     },
     "provider_model_id": "anthropic/claude-3-7-sonnet-latest"
    }
   ],
   "intro": "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities.",
   "max_input_tokens": 200000,
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "assistant_prefill": true,
    "vision": true,
    "pdf_input": true,
    "reasoning": true,
    "stream": true
   },
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "deprecated": true,
   "knowledge_cutoff": "2025-02",
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "released_at": "2025-03-13",
   "family": "claude-sonnet",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-3-7-sonnet-latest"
   ],
   "intro_i18n": {
    "zh-CN": "Claude 3.7 Sonnet 是 Anthropic 最新、最强大的模型，适用于高度复杂的任务，在性能、智能、流畅性和理解力方面表现卓越。",
    "zh-TW": "Claude 3.7 Sonnet 是 Anthropic 最新且最強大的模型，適用於高度複雜任務，具備卓越的效能、智慧、流暢度與理解力。",
    "ja-JP": "Claude 3.7 Sonnetは、Anthropicの最新かつ最も高性能なモデルで、非常に複雑なタスクにおいて卓越した性能、知性、流暢さ、理解力を発揮します。",
    "ru-RU": "Claude 3.7 Sonnet — последняя и самая мощная модель от Anthropic для высокосложных задач, превосходящая по производительности, интеллекту, беглости и пониманию."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 3.7 Sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-7-sonnet-v2@20250219",
   "model_name": "claude-3-7-sonnet-v2@20250219",
   "display_name": "claude-3-7-sonnet-v2@20250219",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3-7-sonnet-v2@20250219"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-haiku-20240307",
   "model_name": "claude-3-haiku-20240307",
   "display_name": "claude-3-haiku-20240307",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-3-haiku",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "claude-3-haiku-20240229"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3125"
      }
     },
     "provider_model_id": "anthropic.claude-3-haiku-20240307-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "eu.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "eu.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "eu.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "us-gov.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "us-gov-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-haiku-20240307-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "anthropic.claude-3-haiku-20240307-v1:0"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "anthropic/claude-3-haiku"
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "claude-3-haiku"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "anthropic/claude-3-haiku",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "claude-3-haiku"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1875"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "anthropic/claude-3-haiku"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0004"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "anthropic/claude-3-haiku"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "anthropic/claude-3-haiku"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "anthropic/claude-3-haiku"
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true
   },
   "intro": "Fastest, most cost-effective model",
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "knowledge_cutoff": "2024-03",
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "released_at": "2024-03-13",
   "family": "claude-haiku",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-3-haiku-20240307-v1:0",
    "anthropic/claude-3-haiku",
    "anthropic/claude-3-haiku-20240307",
    "anthropic/claude-3-haiku@20240307",
    "apac.anthropic.claude-3-haiku-20240307-v1:0",
    "claude-3-haiku",
    "claude-3-haiku-20240229",
    "claude-3-haiku@20240307",
    "eu.anthropic.claude-3-haiku-20240307-v1:0",
    "us-gov.anthropic.claude-3-haiku-20240307-v1:0",
    "us.anthropic.claude-3-haiku-20240307-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "Claude 3 Haiku 是 Anthropic 迄今最快、最紧凑的模型，能为简单查询提供近乎即时的响应。它支持图像输入，具备 200K 上下文窗口，带来流畅自然的 AI 交互体验。",
    "zh-TW": "Claude 3 Haiku 是 Anthropic 速度最快、體積最小的模型，能即時回應簡單查詢，提供流暢自然的 AI 體驗，並支援圖像輸入與 200K 的上下文視窗。",
    "ja-JP": "Claude 3 Haiku は Anthropic の中で最も高速かつコンパクトなモデルで、シンプルな質問に対してほぼ即時の応答を提供します。人間らしい自然な AI 体験を実現し、200K のコンテキストウィンドウで画像入力にも対応しています。",
    "ru-RU": "Claude 3 Haiku — самая быстрая и компактная модель от Anthropic, обеспечивающая почти мгновенные ответы на простые запросы. Обеспечивает плавное, человекоподобное взаимодействие с ИИ и поддерживает ввод изображений с контекстом до 200 тысяч токенов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-haiku:beta",
   "model_name": "claude-3-haiku:beta",
   "display_name": "claude-3-haiku:beta",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "assistant_prefill": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3-haiku:beta"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-opus-20240229",
   "model_name": "claude-3-opus-20240229",
   "display_name": "claude-3-opus-20240229",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "litellm+truefoundry+computeprices+portkey+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "claude-3-opus",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "82.5"
      }
     },
     "provider_model_id": "claude-3-opus@20240229"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic.claude-3-opus-20240229-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-opus-20240229-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-opus-20240229-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "anthropic.claude-3-opus-20240229-v1:0"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-3-opus"
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "claude-3-opus"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "anthropic/claude-3-opus",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "claude-3-opus"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "claude-3-opus"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-3-opus"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-3-opus"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-3-opus"
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "deprecated": true,
   "model_type": "vision_understanding",
   "deprecation_date": "2026-05-01",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "knowledge_cutoff": "2023-08",
   "family": "Opus",
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2024-03-04",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-3-opus-20240229-v1:0",
    "anthropic/claude-3-opus",
    "anthropic/claude-3-opus@20240229",
    "claude-3-opus",
    "claude-3-opus@20240229",
    "eu.anthropic.claude-3-opus-20240229-v1:0",
    "us.anthropic.claude-3-opus-20240229-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "Claude 3 Opus 是 Anthropic 最强大的 AI 模型，在处理高度复杂任务方面表现卓越。它能流畅应对开放式提示和新颖场景，具备类人理解能力，并支持图像输入和 200K 上下文窗口。",
    "zh-TW": "Claude 3 Opus 是 Anthropic 最強大的 AI 模型，在處理高度複雜任務時展現最先進的效能，具備開放式提示與新穎情境的流暢應對能力，並支援圖像輸入與 200K 的上下文視窗。",
    "ja-JP": "Claude 3 Opus は Anthropic の中で最も高性能な AI モデルで、非常に複雑なタスクにおいて最先端のパフォーマンスを発揮します。自由形式のプロンプトや新しいシナリオにも高度な流暢さと人間のような理解力で対応し、200K のコンテキストウィンドウで画像入力にも対応しています。",
    "ru-RU": "Claude 3 Opus — самая мощная модель от Anthropic с передовыми возможностями для сложных задач. Обеспечивает свободную генерацию и понимание новых сценариев, поддерживает ввод изображений и контекст до 200 тысяч токенов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-opus-latest",
   "model_name": "claude-3-opus-latest",
   "display_name": "claude-3-opus-latest",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "pydantic-prices+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Claude 3 Opus was Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.",
   "max_input_tokens": 200000,
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "assistant_prefill": true,
    "vision": true
   },
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3-opus-latest"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-opus:beta",
   "model_name": "claude-3-opus:beta",
   "display_name": "claude-3-opus:beta",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3-opus:beta"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3-sonnet",
   "model_name": "claude-3-sonnet",
   "display_name": "Claude Sonnet 3",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "claude-3-sonnet-20240229"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "claude-3-sonnet-20240229"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic.claude-3-sonnet-20240229-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-sonnet-20240229-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-sonnet-20240229-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-sonnet-20240229-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-sonnet-20240229-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-3-sonnet-20240229-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-3-sonnet-20240229-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-3-sonnet-20240229-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-3-sonnet-20240229-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-sonnet-20240229-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "us.anthropic.claude-3-sonnet-20240229-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic.claude-3-sonnet-20240229-v1:0"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "anthropic/claude-3-sonnet"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-3-sonnet",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "claude-3-sonnet@20240229"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "claude-3-sonnet-20240229"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0048"
      }
     },
     "provider_model_id": "anthropic/claude-3-sonnet"
    }
   ],
   "intro": "Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.",
   "max_input_tokens": 200000,
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true
   },
   "released_at": "2024-03-04",
   "knowledge_cutoff": "2023-08",
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "model_type": "vision_understanding",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-3-sonnet-20240229-v1:0",
    "anthropic/claude-3-sonnet",
    "anthropic/claude-3-sonnet@20240229",
    "apac.anthropic.claude-3-sonnet-20240229-v1:0",
    "claude-3-sonnet-20240229",
    "claude-3-sonnet@20240229",
    "eu.anthropic.claude-3-sonnet-20240229-v1:0",
    "us.anthropic.claude-3-sonnet-20240229-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "Claude 3 Sonnet 在智能与速度之间实现平衡，适用于企业级工作负载，具备高性价比。支持图像输入和 200K 上下文窗口，是大规模 AI 部署的可靠选择。",
    "zh-TW": "Claude 3 Sonnet 在智慧與速度之間取得平衡，適用於企業級工作負載，提供高性價比與可靠的大規模部署能力，並支援圖像輸入與 200K 的上下文視窗。",
    "ja-JP": "Claude 3 Sonnet は、企業向けのワークロードにおいて知性と速度のバランスを取り、低コストで高い価値を提供します。大規模な AI 導入における信頼性の高い主力モデルとして設計されており、200K のコンテキストウィンドウで画像入力にも対応しています。",
    "ru-RU": "Claude 3 Sonnet сочетает интеллект и скорость для корпоративных задач, предлагая высокую ценность при низкой стоимости. Надежен для масштабируемого внедрения ИИ и поддерживает ввод изображений с контекстом до 200 тысяч токенов."
   },
   "price_history": [
    {
     "date": "2026-07-05",
     "kind": "listed",
     "note": "Claude Sonnet 3"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3.5-haiku:beta",
   "model_name": "claude-3.5-haiku:beta",
   "display_name": "claude-3.5-haiku:beta",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3.5-haiku:beta"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3.5-sonnet:beta",
   "model_name": "claude-3.5-sonnet:beta",
   "display_name": "claude-3.5-sonnet:beta",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic/claude-3.5-sonnet:beta"
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-3.5-sonnet:beta"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3.5-sonnet:beta"
    }
   ]
  },
  {
   "slug": "anthropic/claude-3.7-sonnet:beta",
   "model_name": "claude-3.7-sonnet:beta",
   "display_name": "claude-3.7-sonnet:beta",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0048"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "anthropic/claude-3.7-sonnet:beta"
    }
   ],
   "max_output_tokens": 128000,
   "deprecated": true,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true,
    "prompt_caching": true,
    "reasoning": true,
    "pdf_input": true
   },
   "max_input_tokens": 200000,
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-3.7-sonnet:beta"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-3.7-sonnet:beta"
    }
   ]
  },
  {
   "slug": "anthropic/claude-4-5-sonnet",
   "model_name": "claude-4-5-sonnet",
   "display_name": "Claude 4.5 Sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.259"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.296"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.293"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-4.5-sonnet"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.30000000000000004"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-4.5-sonnet"
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-09-30",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-07",
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-4.5-sonnet",
    "claude-4.5-sonnet"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.5 Sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/claude-4-6-sonnet",
   "model_name": "claude-4-6-sonnet",
   "display_name": "Claude Sonnet 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17.92"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.30000000000000004"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-4.6-sonnet"
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2026-02-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "claude-4.6-sonnet"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4.6"
    }
   ]
  },
  {
   "slug": "anthropic/claude-4-opus-20250514",
   "model_name": "claude-4-opus-20250514",
   "display_name": "claude-4-opus-20250514",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "82.5"
      }
     },
     "provider_model_id": "claude-4-opus"
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "claude-4-opus"
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "claude-4-opus"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "82.5"
      }
     },
     "provider_model_id": "deepinfra/anthropic/claude-4-opus"
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "deprecated": true,
   "released_at": "2025-06-12",
   "knowledge_cutoff": "2025-03",
   "family": "claude-opus",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-4-opus",
    "claude-4-opus",
    "deepinfra/anthropic/claude-4-opus"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "anthropic/claude-4-sonnet-20250514",
   "model_name": "claude-4-sonnet-20250514",
   "display_name": "claude-4-sonnet-20250514",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write": "2",
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "claude-4-sonnet"
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-4-sonnet"
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "claude-4-sonnet"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "deepinfra/anthropic/claude-4-sonnet"
    }
   ],
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "web_search": true,
    "assistant_prefill": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "deprecated": true,
   "released_at": "2026-07-09",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-4-sonnet",
    "claude-4-sonnet",
    "deepinfra/anthropic/claude-4-sonnet"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "anthropic/claude-4.0-opus",
   "model_name": "claude-4.0-opus",
   "display_name": "Claude 4.0 Opus",
   "vendor": "anthropic",
   "pricing": [],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-08-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.0 Opus"
    }
   ]
  },
  {
   "slug": "anthropic/claude-4.0-sonnet",
   "model_name": "claude-4.0-sonnet",
   "display_name": "Claude 4.0 Sonnet",
   "vendor": "anthropic",
   "pricing": [],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-08-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.0 Sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/claude-4.1-opus",
   "model_name": "claude-4.1-opus",
   "display_name": "Claude 4.1 Opus",
   "vendor": "anthropic",
   "pricing": [],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-08-06",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.1 Opus"
    }
   ]
  },
  {
   "slug": "anthropic/claude-4.5-haiku",
   "model_name": "claude-4.5-haiku",
   "display_name": "Claude 4.5 Haiku",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09999999999999999"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "intro": "Fast Claude model for responsive assistance, classification, and lightweight agents",
   "released_at": "2025-10-16",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2025-10",
   "family": "claude-haiku",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.5 Haiku"
    }
   ]
  },
  {
   "slug": "anthropic/claude-4.5-opus",
   "model_name": "claude-4.5-opus",
   "display_name": "Claude 4.5 Opus",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-11-25",
   "max_input_tokens": 200000,
   "max_output_tokens": 200000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-11",
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.5 Opus"
    }
   ]
  },
  {
   "slug": "anthropic/claude-4.6-opus",
   "model_name": "claude-4.6-opus",
   "display_name": "Anthropic: Claude Opus 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5000000000000001"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    }
   ],
   "knowledge_cutoff": "2026-02",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Anthropic: Claude Opus 4.6"
    }
   ]
  },
  {
   "slug": "anthropic/claude-code",
   "model_name": "claude-code",
   "display_name": "claude-code",
   "vendor": "anthropic",
   "pricing": [],
   "intro": "Claude model for careful reasoning, writing, coding, and tool use",
   "released_at": "2025-11-27",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "poetools/claude-code"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-code"
    }
   ]
  },
  {
   "slug": "anthropic/claude-fable-5",
   "model_name": "claude-fable-5",
   "display_name": "Claude Fable 5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic.claude-fable-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "af-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-northeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-northeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-south-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-southeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-southeast-4"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-southeast-5"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-southeast-6"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ap-southeast-7"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "ca-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "eu.anthropic.claude-fable-5",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "eu.anthropic.claude-fable-5",
     "region": "eu-central-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "eu.anthropic.claude-fable-5",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "eu.anthropic.claude-fable-5",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "eu.anthropic.claude-fable-5",
     "region": "eu-south-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "eu.anthropic.claude-fable-5",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "eu.anthropic.claude-fable-5",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "eu.anthropic.claude-fable-5",
     "region": "eu-west-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "il-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "me-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "me-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "mx-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "us-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "global.anthropic.claude-fable-5",
     "region": "us-west-2"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "8.75"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "freemodel",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     }
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "provider_model_id": "anthropic.claude-fable-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "13.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5",
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "13.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    },
    {
     "provider": "xpersona",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "18"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-fable-5"
    }
   ],
   "intro": "Claude model for creative writing, analysis, and controlled agent workflows",
   "released_at": "2026-06-07",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-fable",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "computer_use": true,
    "parallel_function_calling": true,
    "assistant_prefill": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2026-01",
   "benchmarks": {
    "intelligence_index": 59.9,
    "coding_index": 76.5,
    "agentic_index": 52.8
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-fable-5",
    "anthropic/claude-fable-5",
    "eu.anthropic.claude-fable-5",
    "global.anthropic.claude-fable-5",
    "global.anthropic.claude-fable-5-v1:0",
    "us.anthropic.claude-fable-5",
    "vertex/claude-fable-5"
   ],
   "intro_i18n": {
    "zh-CN": "Claude Fable 5 是 Anthropic 最强大的模型——在 Opus 之上开辟了一个新层级，专为最具挑战性的推理和长周期代理工作而设计。",
    "zh-TW": "Claude Fable 5 是 Anthropic 最強大的模型——超越 Opus 的新層級，專為最具挑戰性的推理和長期代理工作而設計。",
    "ja-JP": "クロード・フェーブル5は、Anthropicの最も高性能なモデルです。最も高度な推論や長期的なエージェント作業に対応するため、Opusを超える新たなレベルを提供します。",
    "ru-RU": "Claude Fable 5 — это самая мощная модель Anthropic, новый уровень выше Opus для самых сложных задач, требующих глубокого анализа и долгосрочного агентного подхода."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "assistant_prefill: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-fable-5@default",
   "model_name": "claude-fable-5@default",
   "display_name": "claude-fable-5@default",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-fable-5@default"
    }
   ]
  },
  {
   "slug": "anthropic/claude-fable-5@eu",
   "model_name": "claude-fable-5@eu",
   "display_name": "vertex/claude-fable-5@eu",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "13.75"
      }
     },
     "provider_model_id": "vertex/claude-fable-5@eu"
    }
   ],
   "released_at": "2026-06-09",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-fable-5@eu"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-fable-5@eu"
    }
   ]
  },
  {
   "slug": "anthropic/claude-fable-5@us-east-1",
   "model_name": "claude-fable-5@us-east-1",
   "display_name": "bedrock/claude-fable-5@us-east-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "13.75"
      }
     },
     "provider_model_id": "bedrock/claude-fable-5@us-east-1"
    }
   ],
   "released_at": "2026-06-09",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-fable-5@us-east-1"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-fable-5@us-east-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-fable-latest",
   "model_name": "claude-fable-latest",
   "display_name": "Claude Fable Latest",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "provider_model_id": "~anthropic/claude-fable-latest"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      }
     },
     "provider_model_id": "anthropic/claude-fable-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "provider_model_id": "~anthropic/claude-fable-latest"
    }
   ],
   "intro": "Claude model for creative writing, analysis, and controlled agent workflows",
   "released_at": "2026-06-09",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-fable",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-fable-latest",
    "~anthropic/claude-fable-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Fable Latest"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-3",
   "model_name": "claude-haiku-3",
   "display_name": "Claude-Haiku-3",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.021"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-3"
    }
   ],
   "intro": "Fast Claude model for responsive assistance, classification, and lightweight agents",
   "released_at": "2024-03-09",
   "max_input_tokens": 189096,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-haiku-3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude-Haiku-3"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-3.5",
   "model_name": "claude-haiku-3.5",
   "display_name": "Claude-Haiku-3.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.068"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-3.5"
    }
   ],
   "intro": "Fast Claude model for responsive assistance, classification, and lightweight agents",
   "released_at": "2024-10-01",
   "max_input_tokens": 189096,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-haiku-3.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude-Haiku-3.5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5",
   "model_name": "claude-haiku-4-5",
   "display_name": "Claude Haiku 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+helicone-registry+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic.claude-haiku-4-5-20251001-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.55",
        "completion": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "il-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "me-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "me-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "us-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "claude-haiku-4.5"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "anthropic.claude-haiku-4-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "global.anthropic.claude-haiku-4-5-20251001-v1:0"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.43"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.089"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4.5"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "freemodel",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "claude-haiku-4.5"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "claude-haiku-4-5@20251001",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5",
     "region": "asia-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500364"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500364"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500364"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "claude-haiku-4-5@20251001"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09999999999999999"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4.5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4.5"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5-20251001"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4.5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4.5"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.085"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4.5"
    },
    {
     "provider": "qihang-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4-5"
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "claude-haiku-4-5-20251001"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4.5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4.5"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-4.5"
    }
   ],
   "intro": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
   "released_at": "2025-10-15",
   "knowledge_cutoff": "2025-02",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5",
   "deprecation_date": "2026-10-15",
   "benchmarks": {
    "intelligence_index": 29.6,
    "coding_index": 43.9,
    "agentic_index": 16.4
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-haiku-4-5",
    "anthropic.claude-haiku-4-5-20251001-v1:0",
    "anthropic.claude-haiku-4-5@20251001",
    "anthropic/claude-haiku-4-5",
    "anthropic/claude-haiku-4-5-20251001",
    "anthropic/claude-haiku-4-5@20251001",
    "anthropic/claude-haiku-4.5",
    "apac.anthropic.claude-haiku-4-5-20251001-v1:0",
    "au.anthropic.claude-haiku-4-5-20251001-v1:0",
    "bedrock/claude-haiku-4-5",
    "claude-haiku-4-5-20251001",
    "claude-haiku-4-5-free",
    "claude-haiku-4-5@20251001",
    "claude-haiku-4.5",
    "eu.anthropic.claude-haiku-4-5-20251001-v1:0",
    "global.anthropic.claude-haiku-4-5-20251001-v1:0",
    "jp.anthropic.claude-haiku-4-5-20251001-v1:0",
    "pa/claude-haiku-4-5-20251001",
    "us.anthropic.claude-haiku-4-5-20251001-v1:0",
    "vertex/claude-haiku-4-5",
    "vertexanthropic/claude-haiku-4-5"
   ],
   "intro_i18n": {
    "zh-CN": "Claude Haiku 4.5 是 Anthropic 的高性能快速模型，在保持高准确率的同时实现极低延迟。",
    "zh-TW": "Claude Haiku 4.5 是 Anthropic 的高效能快速模型，在保持高準確度的同時提供極低延遲。",
    "ja-JP": "Claude Haiku 4.5 は Anthropic の高性能高速モデルで、非常に低いレイテンシを維持しながら高い精度を実現します。",
    "ru-RU": "Claude Haiku 4.5 — высокопроизводительная быстрая модель от Anthropic с очень низкой задержкой и высокой точностью."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5-20251001-cc",
   "model_name": "claude-haiku-4-5-20251001-cc",
   "display_name": "claude-haiku-4-5-20251001-cc",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.37"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      }
     }
    }
   ],
   "released_at": "2026-06-17",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-haiku-4-5-20251001-cc"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5-20251001-dd",
   "model_name": "claude-haiku-4-5-20251001-dd",
   "display_name": "claude-haiku-4-5-20251001-dd",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     }
    }
   ],
   "released_at": "2026-03-30",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-haiku-4-5-20251001-dd"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5-20251001-r",
   "model_name": "claude-haiku-4-5-20251001-r",
   "display_name": "claude-haiku-4-5-20251001-r",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "released_at": "2026-06-04",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-haiku-4-5-20251001-r"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5-20251001-thinking",
   "model_name": "claude-haiku-4-5-20251001-thinking",
   "display_name": "Claude Haiku 4.5 Thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-10-15",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Haiku 4.5 Thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5@ap-northeast-1",
   "model_name": "claude-haiku-4-5@ap-northeast-1",
   "display_name": "bedrock/claude-haiku-4-5@ap-northeast-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     },
     "provider_model_id": "bedrock/claude-haiku-4-5@ap-northeast-1"
    }
   ],
   "released_at": "2026-07-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-haiku-4-5@ap-northeast-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-haiku-4-5@ap-northeast-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5@eu-central-1",
   "model_name": "claude-haiku-4-5@eu-central-1",
   "display_name": "bedrock/claude-haiku-4-5@eu-central-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     },
     "provider_model_id": "bedrock/claude-haiku-4-5@eu-central-1"
    }
   ],
   "released_at": "2025-10-23",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-haiku-4-5@eu-central-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-haiku-4-5@eu-central-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5@eu-north-1",
   "model_name": "claude-haiku-4-5@eu-north-1",
   "display_name": "bedrock/claude-haiku-4-5@eu-north-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     },
     "provider_model_id": "bedrock/claude-haiku-4-5@eu-north-1"
    }
   ],
   "released_at": "2025-10-23",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-haiku-4-5@eu-north-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-haiku-4-5@eu-north-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5@eu-west-1",
   "model_name": "claude-haiku-4-5@eu-west-1",
   "display_name": "bedrock/claude-haiku-4-5@eu-west-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     },
     "provider_model_id": "bedrock/claude-haiku-4-5@eu-west-1"
    }
   ],
   "released_at": "2025-10-23",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-haiku-4-5@eu-west-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-haiku-4-5@eu-west-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5@eu-west-3",
   "model_name": "claude-haiku-4-5@eu-west-3",
   "display_name": "bedrock/claude-haiku-4-5@eu-west-3",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     },
     "provider_model_id": "bedrock/claude-haiku-4-5@eu-west-3"
    }
   ],
   "released_at": "2025-10-23",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-haiku-4-5@eu-west-3"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-haiku-4-5@eu-west-3"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5@europe-west1",
   "model_name": "claude-haiku-4-5@europe-west1",
   "display_name": "vertex/claude-haiku-4-5@europe-west1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     },
     "provider_model_id": "vertex/claude-haiku-4-5@europe-west1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-haiku-4-5@europe-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-haiku-4-5@europe-west1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5@us-east-1",
   "model_name": "claude-haiku-4-5@us-east-1",
   "display_name": "bedrock/claude-haiku-4-5@us-east-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     },
     "provider_model_id": "bedrock/claude-haiku-4-5@us-east-1"
    }
   ],
   "released_at": "2025-10-23",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-haiku-4-5@us-east-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-haiku-4-5@us-east-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5@us-east-2",
   "model_name": "claude-haiku-4-5@us-east-2",
   "display_name": "bedrock/claude-haiku-4-5@us-east-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     },
     "provider_model_id": "bedrock/claude-haiku-4-5@us-east-2"
    }
   ],
   "released_at": "2025-10-23",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-haiku-4-5@us-east-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-haiku-4-5@us-east-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5@us-east5",
   "model_name": "claude-haiku-4-5@us-east5",
   "display_name": "vertex/claude-haiku-4-5@us-east5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     },
     "provider_model_id": "vertex/claude-haiku-4-5@us-east5"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-haiku-4-5@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-haiku-4-5@us-east5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-4-5@us-west-2",
   "model_name": "claude-haiku-4-5@us-west-2",
   "display_name": "bedrock/claude-haiku-4-5@us-west-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     },
     "provider_model_id": "bedrock/claude-haiku-4-5@us-west-2"
    }
   ],
   "released_at": "2025-10-23",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-haiku-4-5@us-west-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-haiku-4-5@us-west-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-haiku-latest",
   "model_name": "claude-haiku-latest",
   "display_name": "Anthropic: Claude Haiku Latest",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "~anthropic/claude-haiku-latest"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "anthropic/claude-haiku-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "~anthropic/claude-haiku-latest"
    }
   ],
   "intro": "Fast Claude model for responsive assistance, classification, and lightweight agents",
   "released_at": "2026-04-27",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "family": "claude-haiku",
   "reasoning_config": {
    "budget_min": 1024
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-haiku-latest",
    "~anthropic/claude-haiku-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Anthropic: Claude Haiku Latest"
    }
   ]
  },
  {
   "slug": "anthropic/claude-instant",
   "model_name": "claude-instant",
   "display_name": "claude-instant",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-instant"
    }
   ]
  },
  {
   "slug": "anthropic/claude-instant-1",
   "model_name": "claude-instant-1",
   "display_name": "claude-instant-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.793"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.793"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-instant-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-instant-1.2",
   "model_name": "claude-instant-1.2",
   "display_name": "claude-instant-1.2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.96"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-instant-1.2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-instant-v1",
   "model_name": "claude-instant-v1",
   "display_name": "Claude Instant",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "audio_input": {
       "unit": "per_second",
       "price": "0.01475"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0.01475"
      }
     },
     "provider_model_id": "anthropic.claude-instant-v1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "anthropic.claude-instant-v1",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "anthropic.claude-instant-v1",
     "region": "ap-southeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "anthropic.claude-instant-v1",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.02"
      }
     },
     "provider_model_id": "anthropic.claude-instant-v1",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.02"
      }
     },
     "provider_model_id": "anthropic.claude-instant-v1",
     "region": "us-west-2"
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "anthropic.claude-instant-v1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.63"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.51"
      }
     },
     "provider_model_id": "anthropic/claude-instant-v1"
    }
   ],
   "max_input_tokens": 100000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {},
   "deprecated": true,
   "released_at": "2023-03-01",
   "knowledge_cutoff": "2023-08",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-instant-v1",
    "anthropic/claude-instant-v1"
   ],
   "intro_i18n": {
    "zh-CN": "一款快速、经济且功能强大的模型，适用于日常对话、文本分析、摘要生成和文档问答。",
    "zh-TW": "一款快速、經濟且功能強大的模型，適用於日常對話、文字分析、摘要與文件問答。",
    "ja-JP": "日常的なチャット、テキスト分析、要約、文書の質疑応答に適した、高速かつ経済的でありながら高機能なモデルです。",
    "ru-RU": "Быстрая, экономичная и при этом мощная модель для повседневного общения, анализа текста, суммирования и вопросов по документам."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Instant"
    }
   ]
  },
  {
   "slug": "anthropic/claude-mythos-5",
   "model_name": "claude-mythos-5",
   "display_name": "Claude Mythos 5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "computeprices+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "family": "Mythos",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Mythos 5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-0",
   "model_name": "claude-opus-4-0",
   "display_name": "claude-opus-4-0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Most intelligent model for complex tasks",
   "max_input_tokens": 200000,
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "vision: true→false"
    },
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "function_calling: true→false"
    },
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "reasoning: true→false"
    },
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "prompt_caching: true→false"
    },
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "pdf_input: true→false"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-1",
   "model_name": "claude-opus-4-1",
   "display_name": "Claude Opus 4.1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-opus-4-1-20250805",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "claude-opus-4-1-20250805"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "claude-opus-4-1-20250805"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "82.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "claude-opus-4-1-20250805"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+helicone-registry+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-1-20250805-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "us.anthropic.claude-opus-4-1-20250805-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "us.anthropic.claude-opus-4-1-20250805-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "us.anthropic.claude-opus-4-1-20250805-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.82"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-1"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.1"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "claude-opus-4-1@20250805",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-1",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-1",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "claude-opus-4-1@20250805"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "claude-opus-4-1-20250805"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "67.5"
      }
     },
     "provider_model_id": "claude-opus-4-1-20250805"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.1"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "claude-opus-4-1-20250805"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.1"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-1-20250805"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     },
     "provider_model_id": "claude-opus-4-1-20250805"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0048"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.1"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.1"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "16"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.1"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-1"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "claude-opus-4-1-20250805"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.1"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.1"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.1"
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-08-05",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "status": "deprecated",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "deprecation_date": "2026-08-05",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "stop",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-opus-4-1-20250805-v1:0",
    "anthropic/claude-opus-4-1",
    "anthropic/claude-opus-4-1-20250805",
    "anthropic/claude-opus-4-1@20250805",
    "anthropic/claude-opus-4.1",
    "claude-opus-4-1-20250805",
    "claude-opus-4-1@20250805",
    "claude-opus-4.1",
    "eu.anthropic.claude-opus-4-1-20250805-v1:0",
    "pa/claude-opus-4-1-20250805",
    "us.anthropic.claude-opus-4-1-20250805-v1:0",
    "vertex/claude-opus-4-1",
    "vertexanthropic/claude-opus-4-1"
   ],
   "intro_i18n": {
    "zh-CN": "Opus 4.1 是 Anthropic 的高端模型，专为编程、复杂推理和长时间任务优化。",
    "zh-TW": "Opus 4.1 是 Anthropic 的高階模型，針對程式設計、複雜推理與長時間任務進行最佳化。",
    "ja-JP": "Opus 4.1 は、プログラミング、複雑な推論、長時間タスクに最適化された Anthropic のハイエンドモデルです。",
    "ru-RU": "Opus 4.1 — флагманская модель от Anthropic, оптимизированная для программирования, сложной логики и длительных задач."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-1-20250805-thinking",
   "model_name": "claude-opus-4-1-20250805-thinking",
   "display_name": "claude-opus-4-1-20250805-thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-05-27",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Claude Opus 4.1 Thinking 是一款高级变体，能够展示其推理过程。",
    "zh-TW": "Claude Opus 4.1 Thinking 是一個進階版本，能夠揭示其推理過程。",
    "ja-JP": "Claude Opus 4.1 Thinkingは、推論プロセスを可視化できる高度なバリアントです。",
    "ru-RU": "Claude Opus 4.1 Thinking — продвинутая версия, способная демонстрировать процесс рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-1-20250805-thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-1-thinking",
   "model_name": "claude-opus-4-1-thinking",
   "display_name": "Claude 4.1 Opus Thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.1 Opus Thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-1-thinking:1024",
   "model_name": "claude-opus-4-1-thinking:1024",
   "display_name": "Claude 4.1 Opus Thinking (1K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.1 Opus Thinking (1K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-1-thinking:32000",
   "model_name": "claude-opus-4-1-thinking:32000",
   "display_name": "Claude 4.1 Opus Thinking (32K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.1 Opus Thinking (32K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-1-thinking:32768",
   "model_name": "claude-opus-4-1-thinking:32768",
   "display_name": "Claude 4.1 Opus Thinking (32K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.1 Opus Thinking (32K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-1-thinking:8192",
   "model_name": "claude-opus-4-1-thinking:8192",
   "display_name": "Claude 4.1 Opus Thinking (8K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.1 Opus Thinking (8K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-1@us-east5",
   "model_name": "claude-opus-4-1@us-east5",
   "display_name": "vertex/claude-opus-4-1@us-east5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "vertex/claude-opus-4-1@us-east5"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-opus-4-1@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-opus-4-1@us-east5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-20250514",
   "model_name": "claude-opus-4-20250514",
   "display_name": "claude-opus-4-20250514",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "litellm+truefoundry+helicone-registry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-opus-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+helicone-registry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-20250514-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "us.anthropic.claude-opus-4-20250514-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "us.anthropic.claude-opus-4-20250514-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "us.anthropic.claude-opus-4-20250514-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.82"
      }
     },
     "provider_model_id": "claude-opus-4"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "claude-opus-4@20250514",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-opus-4@20250514"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "claude-opus-4"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "67.5"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-20250514"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0048"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "16"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "vertexanthropic/claude-opus-4"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4"
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-14",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "web_search": true,
    "assistant_prefill": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Our previous flagship model with very high intelligence and capability. Supports extended thinking, multilingual capabilities, and vision processing. Moderately fast latency with 32,000 max output tokens. Training data cut-off: March 2025. API model name: claude-opus-4-20250514",
   "knowledge_cutoff": "2025-05",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "stop",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "released_at": "2025-05-22",
   "family": "claude-opus",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "status": "deprecated",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-opus-4-20250514-v1:0",
    "anthropic/claude-opus-4",
    "anthropic/claude-opus-4-20250514",
    "anthropic/claude-opus-4@20250514",
    "claude-opus-4",
    "claude-opus-4@20250514",
    "eu.anthropic.claude-opus-4-20250514-v1:0",
    "us.anthropic.claude-opus-4-20250514-v1:0",
    "vertex/claude-opus-4",
    "vertexanthropic/claude-opus-4"
   ],
   "intro_i18n": {
    "zh-CN": "Opus 4 是 Anthropic 的旗舰模型，专为复杂任务和企业应用设计。",
    "zh-TW": "Opus 4 是 Anthropic 為複雜任務與企業應用設計的旗艦模型。",
    "ja-JP": "Opus 4 は、複雑なタスクや企業向けアプリケーションに対応するために設計された Anthropic のフラッグシップモデルです。",
    "ru-RU": "Opus 4 — флагманская модель от Anthropic, предназначенная для сложных задач и корпоративных приложений."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5",
   "model_name": "claude-opus-4-5",
   "display_name": "Claude Opus 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-opus-4-5-20251101",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "claude-opus-4-5-20251101"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "claude-opus-4-5-20251101"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "claude-opus-4-5-20251101"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+helicone-registry+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-5-20251101-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.55",
        "completion": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "il-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "me-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "me-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "us-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "claude-opus-4.5"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-5-20251101-v1:0"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.5"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "claude-opus-4.5"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "claude-opus-4-5@20251101",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5",
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500073"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5@20251101",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500073"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5@20251101",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500073"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-opus-4-5@20251101"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/claude-opus-4-5-20251101"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "22.5"
      }
     },
     "provider_model_id": "claude-opus-4-5-20251101"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "claude-opus-4-5-20251101"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.5"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5-20251101"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25.007"
      }
     },
     "provider_model_id": "claude-opus-4-5-20251101"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.5"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "5.3"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.5"
    },
    {
     "provider": "qihang-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.57"
      }
     },
     "provider_model_id": "claude-opus-4-5-20251101"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-5"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "claude-opus-4-5-20251101"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.5"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.5"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.5"
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-11-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "assistant_prefill": true,
    "web_search": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "stop",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-opus-4-5-20251101-v1:0",
    "anthropic/claude-opus-4-5",
    "anthropic/claude-opus-4-5-20251101",
    "anthropic/claude-opus-4-5@20251101",
    "anthropic/claude-opus-4.5",
    "bedrock/claude-opus-4-5",
    "claude-opus-4-5-20251101",
    "claude-opus-4-5-20251101:thinking",
    "claude-opus-4-5@20251101",
    "claude-opus-4.5",
    "eu.anthropic.claude-opus-4-5-20251101-v1:0",
    "global.anthropic.claude-opus-4-5-20251101-v1:0",
    "global.anthropic.claude-opus-4-5-v1:0",
    "pa/claude-opus-4-5-20251101",
    "us.anthropic.claude-opus-4-5-20251101-v1:0",
    "vertex/claude-opus-4-5",
    "vertexanthropic/claude-opus-4-5"
   ],
   "intro_i18n": {
    "zh-CN": "Claude Opus 4.5 是 Anthropic 的旗舰模型，结合顶级智能与可扩展性能，适用于复杂、高质量推理任务。",
    "zh-TW": "Claude Opus 4.5 是 Anthropic 的旗艦模型，結合頂尖智慧與可擴展效能，適用於複雜且高品質的推理任務。",
    "ja-JP": "Claude Opus 4.5 は Anthropic のフラッグシップモデルで、最高レベルの知性とスケーラブルな性能を兼ね備え、複雑で高品質な推論タスクに最適です。",
    "ru-RU": "Claude Opus 4.5 — флагманская модель от Anthropic, сочетающая высший интеллект с масштабируемой производительностью для сложных задач, требующих качественного логического вывода."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5-20251101-dd",
   "model_name": "claude-opus-4-5-20251101-dd",
   "display_name": "claude-opus-4-5-20251101-dd",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.75"
      }
     }
    }
   ],
   "released_at": "2025-12-26",
   "max_input_tokens": 200000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-5-20251101-dd"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5-20251101-thinking",
   "model_name": "claude-opus-4-5-20251101-thinking",
   "display_name": "claude-opus-4-5-20251101-thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-11-25",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-5-20251101-thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5-think",
   "model_name": "claude-opus-4-5-think",
   "display_name": "claude-opus-4-5-think",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-5-think"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5@eu-central-1",
   "model_name": "claude-opus-4-5@eu-central-1",
   "display_name": "bedrock/claude-opus-4-5@eu-central-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-5@eu-central-1"
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-5@eu-central-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-5@eu-central-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5@eu-north-1",
   "model_name": "claude-opus-4-5@eu-north-1",
   "display_name": "bedrock/claude-opus-4-5@eu-north-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-5@eu-north-1"
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-5@eu-north-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-5@eu-north-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5@eu-west-1",
   "model_name": "claude-opus-4-5@eu-west-1",
   "display_name": "bedrock/claude-opus-4-5@eu-west-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-5@eu-west-1"
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-5@eu-west-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-5@eu-west-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5@eu-west-3",
   "model_name": "claude-opus-4-5@eu-west-3",
   "display_name": "bedrock/claude-opus-4-5@eu-west-3",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-5@eu-west-3"
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-5@eu-west-3"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-5@eu-west-3"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5@europe-west1",
   "model_name": "claude-opus-4-5@europe-west1",
   "display_name": "vertex/claude-opus-4-5@europe-west1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "vertex/claude-opus-4-5@europe-west1"
    }
   ],
   "released_at": "2025-11-24",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-opus-4-5@europe-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-opus-4-5@europe-west1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5@us-east-1",
   "model_name": "claude-opus-4-5@us-east-1",
   "display_name": "bedrock/claude-opus-4-5@us-east-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-5@us-east-1"
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-5@us-east-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-5@us-east-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5@us-east-2",
   "model_name": "claude-opus-4-5@us-east-2",
   "display_name": "bedrock/claude-opus-4-5@us-east-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-5@us-east-2"
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-5@us-east-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-5@us-east-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5@us-east5",
   "model_name": "claude-opus-4-5@us-east5",
   "display_name": "vertex/claude-opus-4-5@us-east5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "vertex/claude-opus-4-5@us-east5"
    }
   ],
   "released_at": "2025-11-24",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-opus-4-5@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-opus-4-5@us-east5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-5@us-west-2",
   "model_name": "claude-opus-4-5@us-west-2",
   "display_name": "bedrock/claude-opus-4-5@us-west-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-5@us-west-2"
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-5@us-west-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-5@us-west-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-6",
   "model_name": "claude-opus-4-6",
   "display_name": "Claude Opus 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-opus-4-6-20260205",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices+helicone-registry+computeprices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.55",
        "completion": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.13"
      }
     },
     "provider_model_id": "claude-opus-4.6"
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "freemodel",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "claude-opus-4.6"
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6"
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "claude-opus-4-6@20260205",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6",
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500073"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6",
     "region": "eu"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500073"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6",
     "region": "us"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500073"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/claude-opus-4-6"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25.007"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "5.3"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "vertexanthropic/claude-opus-4-6"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6"
    }
   ],
   "intro": "High-end Claude for difficult coding, planning, and slower expert reasoning",
   "released_at": "2026-02-04",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "parallel_function_calling": true,
    "assistant_prefill": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "stop",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-opus-4-6",
    "anthropic.claude-opus-4-6-20260205-v1:0",
    "anthropic.claude-opus-4-6-v1:0",
    "anthropic/claude-opus-4-6",
    "anthropic/claude-opus-4.6",
    "anthropic/claude-opus-4.6:thinking",
    "bedrock/claude-opus-4-6",
    "claude-opus-4-6-20260205",
    "claude-opus-4-6@20260205",
    "claude-opus-4.6",
    "eu.anthropic.claude-opus-4-6-v1:0",
    "global.anthropic.claude-opus-4-6-v1:0",
    "pa/claude-opus-4-6",
    "stealth/claude-opus-4.6",
    "us.anthropic.claude-opus-4-6-v1:0",
    "vertex/claude-opus-4-6",
    "vertexanthropic/claude-opus-4-6"
   ],
   "intro_i18n": {
    "zh-CN": "Anthropic 的 Claude Opus 4.6 —— 具备 100 万上下文窗口的旗舰模型，拥有先进推理能力。",
    "zh-TW": "Anthropic 的 Claude Opus 4.6 —— 支援 100 萬上下文的旗艦模型，擁有先進推理能力。",
    "ja-JP": "Claude Opus 4.6 by Anthropic — 1Mコンテキストウィンドウを備えたフラッグシップモデルで、高度な推論能力を提供します。",
    "ru-RU": "Claude Opus 4.6 от Anthropic — флагманская модель с контекстом 1M и усовершенствованными возможностями рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-6-cc",
   "model_name": "claude-opus-4-6-cc",
   "display_name": "claude-opus-4-6-cc",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.25"
      }
     }
    }
   ],
   "released_at": "2026-06-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-6-cc"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-6-dd",
   "model_name": "claude-opus-4-6-dd",
   "display_name": "claude-opus-4-6-dd",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.75"
      }
     }
    }
   ],
   "released_at": "2026-03-30",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-6-dd"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-6-r",
   "model_name": "claude-opus-4-6-r",
   "display_name": "claude-opus-4-6-r",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "released_at": "2026-06-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-6-r"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-6-think",
   "model_name": "claude-opus-4-6-think",
   "display_name": "Claude Opus 4.6 Thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.6 Thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-6-thinking",
   "model_name": "claude-opus-4-6-thinking",
   "display_name": "claude-opus-4-6-thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-02-06",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-6-thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-6@default",
   "model_name": "claude-opus-4-6@default",
   "display_name": "Claude Opus 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6@default",
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6@default",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6@default",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6@default",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6@default",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-6@default",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "High-end Claude for difficult coding, planning, and slower expert reasoning",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "parallel_function_calling": true,
    "assistant_prefill": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-opus-4-6@default"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.6"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-6@europe-west1",
   "model_name": "claude-opus-4-6@europe-west1",
   "display_name": "vertex/claude-opus-4-6@europe-west1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.88"
      }
     },
     "provider_model_id": "vertex/claude-opus-4-6@europe-west1"
    }
   ],
   "released_at": "2026-02-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-opus-4-6@europe-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-opus-4-6@europe-west1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-6@us-east5",
   "model_name": "claude-opus-4-6@us-east5",
   "display_name": "vertex/claude-opus-4-6@us-east5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.88"
      }
     },
     "provider_model_id": "vertex/claude-opus-4-6@us-east5"
    }
   ],
   "released_at": "2026-02-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-opus-4-6@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-opus-4-6@us-east5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7",
   "model_name": "claude-opus-4-7",
   "display_name": "Claude Opus 4.7",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-opus-4-7-20260416",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "af-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-northeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-northeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-south-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-southeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-opus-4-7",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-opus-4-7",
     "region": "ap-southeast-4"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-southeast-5"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-southeast-6"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ap-southeast-7"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.55",
        "completion": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.55",
        "completion": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-7",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-7",
     "region": "eu-central-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-7",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-7",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-7",
     "region": "eu-south-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-7",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-7",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-7",
     "region": "eu-west-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "il-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "me-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.55",
        "completion": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.55",
        "completion": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "us-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.55",
        "completion": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.55",
        "completion": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "claude-opus-4.7"
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-7"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-7"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-7"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7"
    },
    {
     "provider": "freemodel",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "claude-opus-4.7"
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "22.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7"
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-7",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500073"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-7",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-7",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500073"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "23.75"
      }
     }
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-7"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25.007"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4998"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-7"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-7"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-7"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-7"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7"
    }
   ],
   "intro": "Stronger Opus tier for advanced software work and high-stakes reasoning",
   "released_at": "2026-04-14",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "parallel_function_calling": true,
    "assistant_prefill": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "status": "beta",
   "benchmarks": {
    "intelligence_index": 53.5,
    "coding_index": 73.6,
    "agentic_index": 44.4
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-opus-4-7",
    "anthropic/claude-opus-4-7",
    "anthropic/claude-opus-4.7",
    "anthropic/claude-opus-4.7:thinking",
    "au.anthropic.claude-opus-4-7",
    "bedrock/claude-opus-4-7",
    "claude-opus-4-7-20260416",
    "claude-opus-4.7",
    "eu.anthropic.claude-opus-4-7",
    "global.anthropic.claude-opus-4-7",
    "global.anthropic.claude-opus-4-7-v1:0",
    "jp.anthropic.claude-opus-4-7",
    "stealth/claude-opus-4.7",
    "us.anthropic.claude-opus-4-7",
    "vertex/claude-opus-4-7"
   ],
   "intro_i18n": {
    "zh-CN": "Anthropic 的 Claude Opus 4.7 —— 最新 Opus 模型，具备最先进的推理与编码表现。",
    "zh-TW": "Anthropic 的 Claude Opus 4.7 —— 最新 Opus 模型，具備最先進的推理與程式能力。",
    "ja-JP": "Claude Opus 4.7 by Anthropic — 最新のOpusモデルで、最先端の推論とコーディング能力を備えています。",
    "ru-RU": "Claude Opus 4.7 от Anthropic — последняя версия Opus с передовыми возможностями рассуждения и программирования."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "assistant_prefill: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7-cc",
   "model_name": "claude-opus-4-7-cc",
   "display_name": "claude-opus-4-7-cc",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.25"
      }
     }
    }
   ],
   "released_at": "2026-06-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-7-cc"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7-fast",
   "model_name": "claude-opus-4-7-fast",
   "display_name": "Claude Opus 4.7 Fast",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "37.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7-fast"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "37.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7-fast"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.7-fast"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "45"
      }
     }
    }
   ],
   "intro": "Stronger Opus tier for advanced software work and high-stakes reasoning",
   "released_at": "2026-05-14",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-opus-4.7-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.7 Fast"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7-r",
   "model_name": "claude-opus-4-7-r",
   "display_name": "claude-opus-4-7-r",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "released_at": "2026-06-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-7-r"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7-think",
   "model_name": "claude-opus-4-7-think",
   "display_name": "Claude Opus 4.7 Thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-04-16",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.7 Thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7-xhigh",
   "model_name": "claude-opus-4-7-xhigh",
   "display_name": "Claude Opus 4.7 XHigh",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.7 XHigh"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7@default",
   "model_name": "claude-opus-4-7@default",
   "display_name": "Claude Opus 4.7",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Stronger Opus tier for advanced software work and high-stakes reasoning",
   "released_at": "2026-04-16",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.7"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7@eu",
   "model_name": "claude-opus-4-7@eu",
   "display_name": "vertex/claude-opus-4-7@eu",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.88"
      }
     },
     "provider_model_id": "vertex/claude-opus-4-7@eu"
    }
   ],
   "released_at": "2026-02-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-opus-4-7@eu"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-opus-4-7@eu"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7@eu-central-1",
   "model_name": "claude-opus-4-7@eu-central-1",
   "display_name": "bedrock/claude-opus-4-7@eu-central-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-7@eu-central-1"
    }
   ],
   "released_at": "2026-04-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-7@eu-central-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-7@eu-central-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7@eu-north-1",
   "model_name": "claude-opus-4-7@eu-north-1",
   "display_name": "bedrock/claude-opus-4-7@eu-north-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-7@eu-north-1"
    }
   ],
   "released_at": "2026-04-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-7@eu-north-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-7@eu-north-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7@eu-west-1",
   "model_name": "claude-opus-4-7@eu-west-1",
   "display_name": "bedrock/claude-opus-4-7@eu-west-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-7@eu-west-1"
    }
   ],
   "released_at": "2026-04-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-7@eu-west-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-7@eu-west-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7@eu-west-3",
   "model_name": "claude-opus-4-7@eu-west-3",
   "display_name": "bedrock/claude-opus-4-7@eu-west-3",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-7@eu-west-3"
    }
   ],
   "released_at": "2026-04-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-7@eu-west-3"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-7@eu-west-3"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-7@us",
   "model_name": "claude-opus-4-7@us",
   "display_name": "vertex/claude-opus-4-7@us",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.88"
      }
     },
     "provider_model_id": "vertex/claude-opus-4-7@us"
    }
   ],
   "released_at": "2026-02-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-opus-4-7@us"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-opus-4-7@us"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8",
   "model_name": "claude-opus-4-8",
   "display_name": "Claude Opus 4.8",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-opus-4-8",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.454545",
        "completion": "0.454545"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-opus-4-8",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.454545",
        "completion": "0.454545"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-8",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-8",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-8",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-8",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-8",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-8",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-8",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-8",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "il-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "me-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "me-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "us-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-8",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "claude-opus-4.8"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-8"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-8"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    },
    {
     "provider": "freemodel",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "claude-opus-4.8"
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    },
    {
     "provider": "google",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-8",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500073"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-8",
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-8",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.500073"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "23.75"
      }
     }
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-8"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25.007"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4998"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.2929"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "21.4646"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4293"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "5.3662"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4-8"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8"
    }
   ],
   "intro": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
   "released_at": "2026-05-28",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "parallel_function_calling": true,
    "assistant_prefill": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "benchmarks": {
    "intelligence_index": 55.7,
    "coding_index": 74.3,
    "agentic_index": 47.2
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-opus-4-8",
    "anthropic/claude-opus-4-8",
    "anthropic/claude-opus-4.8",
    "anthropic/claude-opus-4.8:thinking",
    "au.anthropic.claude-opus-4-8",
    "bedrock/claude-opus-4-8",
    "claude-opus-4.8",
    "eu.anthropic.claude-opus-4-8",
    "global.anthropic.claude-opus-4-8",
    "global.anthropic.claude-opus-4-8-v1:0",
    "jp.anthropic.claude-opus-4-8",
    "stealth/claude-opus-4.8",
    "us.anthropic.claude-opus-4-8",
    "vertex/claude-opus-4-8"
   ],
   "intro_i18n": {
    "zh-CN": "Claude Opus 4.8 是 Anthropic 最强大的模型，在 Opus 4.7 的基础上改进了推理、代理编码和工具使用能力。",
    "zh-TW": "Claude Opus 4.8 是 Anthropic 最強大的模型，基於 Opus 4.7 進行改進，提升了推理能力、代理編碼和工具使用。",
    "ja-JP": "Claude Opus 4.8はAnthropicの最も高性能なモデルであり、Opus 4.7を基に推論、エージェント的コーディング、ツール使用の各分野で改良を加えています。",
    "ru-RU": "Claude Opus 4.8 — самая продвинутая модель от Anthropic, основанная на Opus 4.7 с улучшениями в области рассуждений, агентного кодирования и использования инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "jiekou",
     "charge": "completion",
     "old": "25",
     "new": "23.75"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "jiekou",
     "charge": "prompt",
     "old": "5",
     "new": "4.75"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "assistant_prefill: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8-cc",
   "model_name": "claude-opus-4-8-cc",
   "display_name": "claude-opus-4-8-cc",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.25"
      }
     }
    }
   ],
   "released_at": "2026-06-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-8-cc"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8-fast",
   "model_name": "claude-opus-4-8-fast",
   "display_name": "Claude Opus 4.8 Fast",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8-fast"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8-fast"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.8-fast"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "intro": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
   "released_at": "2026-05-28",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-opus-4.8-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.8 Fast"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8-r",
   "model_name": "claude-opus-4-8-r",
   "display_name": "claude-opus-4-8-r",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "released_at": "2026-06-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-opus-4-8-r"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8-think",
   "model_name": "claude-opus-4-8-think",
   "display_name": "Claude Opus 4.8",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    }
   ],
   "intro": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
   "released_at": "2026-05-28",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.8"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8@ap-northeast-1",
   "model_name": "claude-opus-4-8@ap-northeast-1",
   "display_name": "bedrock/claude-opus-4-8@ap-northeast-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-8@ap-northeast-1"
    }
   ],
   "released_at": "2026-07-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-8@ap-northeast-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-8@ap-northeast-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8@default",
   "model_name": "claude-opus-4-8@default",
   "display_name": "Claude Opus 4.8",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
   "released_at": "2026-05-28",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.8"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8@eu",
   "model_name": "claude-opus-4-8@eu",
   "display_name": "vertex/claude-opus-4-8@eu",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.88"
      }
     },
     "provider_model_id": "vertex/claude-opus-4-8@eu"
    }
   ],
   "released_at": "2026-05-28",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-opus-4-8@eu"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-opus-4-8@eu"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8@eu-central-1",
   "model_name": "claude-opus-4-8@eu-central-1",
   "display_name": "bedrock/claude-opus-4-8@eu-central-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-8@eu-central-1"
    }
   ],
   "released_at": "2026-05-29",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-8@eu-central-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-8@eu-central-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8@eu-north-1",
   "model_name": "claude-opus-4-8@eu-north-1",
   "display_name": "bedrock/claude-opus-4-8@eu-north-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-8@eu-north-1"
    }
   ],
   "released_at": "2026-05-29",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-8@eu-north-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-8@eu-north-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8@eu-west-1",
   "model_name": "claude-opus-4-8@eu-west-1",
   "display_name": "bedrock/claude-opus-4-8@eu-west-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-8@eu-west-1"
    }
   ],
   "released_at": "2026-05-29",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-8@eu-west-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-8@eu-west-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8@eu-west-3",
   "model_name": "claude-opus-4-8@eu-west-3",
   "display_name": "bedrock/claude-opus-4-8@eu-west-3",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     },
     "provider_model_id": "bedrock/claude-opus-4-8@eu-west-3"
    }
   ],
   "released_at": "2026-05-29",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-opus-4-8@eu-west-3"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-opus-4-8@eu-west-3"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-8@us",
   "model_name": "claude-opus-4-8@us",
   "display_name": "vertex/claude-opus-4-8@us",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.88"
      }
     },
     "provider_model_id": "vertex/claude-opus-4-8@us"
    }
   ],
   "released_at": "2026-05-28",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-opus-4-8@us"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-opus-4-8@us"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-thinking",
   "model_name": "claude-opus-4-thinking",
   "display_name": "Claude 4 Opus Thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-07-15",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4 Opus Thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-thinking:1024",
   "model_name": "claude-opus-4-thinking:1024",
   "display_name": "Claude 4 Opus Thinking (1K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4 Opus Thinking (1K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-thinking:32000",
   "model_name": "claude-opus-4-thinking:32000",
   "display_name": "Claude 4 Opus Thinking (32K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4 Opus Thinking (32K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-thinking:32768",
   "model_name": "claude-opus-4-thinking:32768",
   "display_name": "Claude 4 Opus Thinking (32K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4 Opus Thinking (32K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4-thinking:8192",
   "model_name": "claude-opus-4-thinking:8192",
   "display_name": "Claude 4 Opus Thinking (8K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.004"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4 Opus Thinking (8K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4.5-rp",
   "model_name": "claude-opus-4.5-rp",
   "display_name": "claude-opus-4.5-rp",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "claude-opus-4.5-rp"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4.6-fast",
   "model_name": "claude-opus-4.6-fast",
   "display_name": "Anthropic: Claude Opus 4.6 (Fast)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "37.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6-fast"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "37.5"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6-fast"
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-04-07",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-opus-4.6-fast"
   ],
   "intro_i18n": {
    "zh-CN": "Claude Opus 4.6 是 Anthropic 最智能的模型，用于构建代理和编程。",
    "zh-TW": "Claude Opus 4.6 是 Anthropic 最智能的模型，用於構建代理和編碼。",
    "ja-JP": "Claude Opus 4.6は、エージェント構築やコーディングにおいてAnthropicの最も知的なモデルです。",
    "ru-RU": "Claude Opus 4.6 — это самая интеллектуальная модель Anthropic для создания агентов и программирования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Anthropic: Claude Opus 4.6 (Fast)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4.6-rp",
   "model_name": "claude-opus-4.6-rp",
   "display_name": "claude-opus-4.6-rp",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "claude-opus-4.6-rp"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4.6:thinking:low",
   "model_name": "claude-opus-4.6:thinking:low",
   "display_name": "Claude 4.6 Opus Thinking Low",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25.007"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6:thinking:low"
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-02-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-opus-4.6:thinking:low"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.6 Opus Thinking Low"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4.6:thinking:max",
   "model_name": "claude-opus-4.6:thinking:max",
   "display_name": "Claude 4.6 Opus Thinking Max",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25.007"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6:thinking:max"
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-02-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-opus-4.6:thinking:max"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.6 Opus Thinking Max"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4.6:thinking:medium",
   "model_name": "claude-opus-4.6:thinking:medium",
   "display_name": "Claude 4.6 Opus Thinking Medium",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25.007"
      }
     },
     "provider_model_id": "anthropic/claude-opus-4.6:thinking:medium"
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-02-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-opus-4.6:thinking:medium"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4.6 Opus Thinking Medium"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-4@us-east5",
   "model_name": "claude-opus-4@us-east5",
   "display_name": "vertex/claude-opus-4@us-east5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     },
     "provider_model_id": "vertex/claude-opus-4@us-east5"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-opus-4@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-opus-4@us-east5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-45",
   "model_name": "claude-opus-45",
   "display_name": "Claude Opus 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    }
   ],
   "released_at": "2025-12-06",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 198000,
   "max_output_tokens": 49500,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus-latest",
   "model_name": "claude-opus-latest",
   "display_name": "Anthropic: Claude Opus Latest",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "~anthropic/claude-opus-latest"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25.007"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4998"
      }
     },
     "provider_model_id": "anthropic/claude-opus-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "~anthropic/claude-opus-latest"
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-04-16",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "family": "claude-opus",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-opus-latest",
    "~anthropic/claude-opus-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Anthropic: Claude Opus Latest"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus4-5",
   "model_name": "claude-opus4-5",
   "display_name": "Claude Opus 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.98"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "29.89"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.477"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-11-24",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 200000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus4-6",
   "model_name": "claude-opus4-6",
   "display_name": "Claude Opus 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.98"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "29.89"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.477"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.6"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus4-7",
   "model_name": "claude-opus4-7",
   "display_name": "Claude Opus 4.7",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.99"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.99"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-04-16",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.7"
    }
   ]
  },
  {
   "slug": "anthropic/claude-opus4-8",
   "model_name": "claude-opus4-8",
   "display_name": "Claude Opus 4.8",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "28.198"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.563"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "7.049"
      }
     }
    }
   ],
   "intro": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
   "released_at": "2026-05-28",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.8"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-3.5",
   "model_name": "claude-sonnet-3.5",
   "display_name": "Claude-Sonnet-3.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-3.5"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2024-06-05",
   "max_input_tokens": 189096,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-sonnet-3.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude-Sonnet-3.5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-3.5-june",
   "model_name": "claude-sonnet-3.5-june",
   "display_name": "Claude-Sonnet-3.5-June",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-3.5-june"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2024-11-18",
   "max_input_tokens": 189096,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-sonnet-3.5-june"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude-Sonnet-3.5-June"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-3.7",
   "model_name": "claude-sonnet-3.7",
   "display_name": "Claude-Sonnet-3.7",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-3.7"
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-02-19",
   "max_input_tokens": 196608,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-sonnet-3.7"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude-Sonnet-3.7"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-0",
   "model_name": "claude-sonnet-4-0",
   "display_name": "claude-sonnet-4-0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Optimal balance of intelligence, cost, and speed",
   "max_input_tokens": 200000,
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "vision: true→false"
    },
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "function_calling: true→false"
    },
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "reasoning: true→false"
    },
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "prompt_caching: true→false"
    },
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "pdf_input: true→false"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-20250514",
   "model_name": "claude-sonnet-4-20250514",
   "display_name": "claude-sonnet-4-20250514",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "litellm+truefoundry+helicone-registry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_write": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+helicone-registry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-20250514-v1:0",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_write": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-northeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-southeast-4"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-southeast-5"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "ap-southeast-7"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "eu-south-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "eu-west-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "apac.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "me-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "us.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "us-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-20250514-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.307"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.536"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "claude-sonnet-4"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-sonnet-4"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "claude-sonnet-4@20250514",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4@20250514",
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-sonnet-4@20250514",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_write": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.30000000000000004"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-sonnet-4"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.5"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-20250514"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      }
     }
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-sonnet-4"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-sonnet-4",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-sonnet-4"
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-sonnet-4"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0048"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "vertexanthropic/claude-sonnet-4"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4"
    }
   ],
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-14",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "web_search": true,
    "assistant_prefill": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "High-performance model with high intelligence and balanced performance. Supports extended thinking, multilingual capabilities, and vision processing. Fast latency with 64,000 max output tokens. API model name: claude-sonnet-4-20250514",
   "knowledge_cutoff": "2025-05",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "stop",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "released_at": "2025-05-22",
   "family": "claude-sonnet",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "status": "deprecated",
   "benchmarks": {
    "intelligence_index": 28.9,
    "coding_index": 37.6,
    "agentic_index": 16.6
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-sonnet-4-20250514-v1:0",
    "anthropic/claude-sonnet-4",
    "anthropic/claude-sonnet-4-20250514",
    "anthropic/claude-sonnet-4@20250514",
    "apac.anthropic.claude-sonnet-4-20250514-v1:0",
    "bedrock/claude-sonnet-4",
    "claude-sonnet-4",
    "claude-sonnet-4@20250514",
    "eu.anthropic.claude-sonnet-4-20250514-v1:0",
    "global.anthropic.claude-sonnet-4-20250514-v1:0",
    "us.anthropic.claude-sonnet-4-20250514-v1:0",
    "vertex/claude-sonnet-4",
    "vertexanthropic/claude-sonnet-4"
   ],
   "intro_i18n": {
    "zh-CN": "Claude Sonnet 4 是 Anthropic 的混合推理模型，具备思考与非思考能力的结合。",
    "zh-TW": "Claude Sonnet 4 是 Anthropic 的混合推理模型，具備思考與非思考能力的結合。",
    "ja-JP": "Claude Sonnet 4 は、思考と非思考の両方の能力を備えた Anthropic のハイブリッド推論モデルです。",
    "ru-RU": "Claude Sonnet 4 — гибридная модель логического вывода от Anthropic, сочетающая режимы мышления и немышления."
   },
   "price_history": [
    {
     "date": "2026-07-05",
     "kind": "limit",
     "old": "200000",
     "new": "1000000",
     "note": "max_input_tokens"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-20250514-dd",
   "model_name": "claude-sonnet-4-20250514-dd",
   "display_name": "claude-sonnet-4-20250514-dd",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.25"
      }
     }
    }
   ],
   "released_at": "2025-12-26",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-20250514-dd"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5",
   "model_name": "claude-sonnet-4-5",
   "display_name": "Claude Sonnet 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "claude-sonnet-4-5-20250929",
     "tracks": [
      {
       "label": ">200K context (1M beta)",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2",
        "cache_write_1h": "2"
       },
       "triggers": [
        {
         "kind": "header_matches",
         "header": "anthropic-beta",
         "pattern": "context-1m-\\d{4}-\\d{2}-\\d{2}"
        },
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "claude-sonnet-4-5-20250929"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "claude-sonnet-4-5-20250929"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "claude-sonnet-4-5-20250929"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+helicone-registry+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-5-20250929-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.55",
        "completion": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_write": "2",
        "cache_read": "2",
        "cache_write_1h": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "il-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "me-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "me-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      }
     },
     "provider_model_id": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "us-gov-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      }
     },
     "provider_model_id": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "us-gov-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "us-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "claude-sonnet-4.5"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-5-20250929-v1:0"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-sonnet-4.5"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "claude-sonnet-4-5@20250929",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.501333"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_write_1h": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5",
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.515152",
        "cache_write": "0.499394"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "1",
        "cache_write": "1.001212"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5",
     "region": "eu"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.515152",
        "cache_write": "0.499394"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "1",
        "cache_write": "1.001212"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5",
     "region": "us"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.515152",
        "cache_write": "0.499394"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "1",
        "cache_write": "1.001212"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "claude-sonnet-4-5@20250929",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_write": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.30000000000000004"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "claude-sonnet-4-5-20250929",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.5"
      }
     },
     "provider_model_id": "claude-sonnet-4-5-20250929"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-sonnet-4-5-20250929"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.5"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5-20250929"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      }
     },
     "provider_model_id": "claude-sonnet-4-5-20250929"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0048"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.5",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.5"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.5"
    },
    {
     "provider": "qihang-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.14"
      }
     },
     "provider_model_id": "claude-sonnet-4-5-20250929"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-5"
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-sonnet-4-5-20250929"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.5"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.69"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.5",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.5",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.5",
        "cache_read": "2",
        "cache_write_1h": "2",
        "cache_write": "2",
        "prompt": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-09-29",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "assistant_prefill": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "stop",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "benchmarks": {
    "intelligence_index": 36.4,
    "coding_index": 52.1,
    "agentic_index": 24.6
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-sonnet-4-5-20250929-v1:0",
    "anthropic/claude-sonnet-4-5",
    "anthropic/claude-sonnet-4-5-20250929",
    "anthropic/claude-sonnet-4-5@20250929",
    "anthropic/claude-sonnet-4.5",
    "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
    "bedrock/claude-sonnet-4-5",
    "claude-sonnet-4-5-20250929",
    "claude-sonnet-4-5-20250929-v1:0",
    "claude-sonnet-4-5@20250929",
    "claude-sonnet-4.5",
    "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
    "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
    "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
    "pa/claude-sonnet-4-5-20250929",
    "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0",
    "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
    "vertex/claude-sonnet-4-5",
    "vertexanthropic/claude-sonnet-4-5"
   ],
   "intro_i18n": {
    "zh-CN": "Claude Sonnet 4.5 是 Anthropic 最新的混合推理模型，专为复杂推理和编程优化。",
    "zh-TW": "Claude Sonnet 4.5 是 Anthropic 最新的混合推理模型，針對複雜推理與程式設計進行最佳化。",
    "ja-JP": "Claude Sonnet 4.5 は、複雑な推論とコーディングに最適化された Anthropic の最新ハイブリッド推論モデルです。",
    "ru-RU": "Claude Sonnet 4.5 — новейшая гибридная модель логического вывода от Anthropic, оптимизированная для сложных рассуждений и программирования."
   },
   "price_history": [
    {
     "date": "2026-07-05",
     "kind": "limit",
     "old": "200000",
     "new": "1000000",
     "note": "max_input_tokens"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5-20250929-dd",
   "model_name": "claude-sonnet-4-5-20250929-dd",
   "display_name": "claude-sonnet-4-5-20250929-dd",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.25"
      }
     }
    }
   ],
   "released_at": "2025-12-26",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-5-20250929-dd"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5-20250929-thinking",
   "model_name": "claude-sonnet-4-5-20250929-thinking",
   "display_name": "claude-sonnet-4-5-20250929-thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-09-30",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-5-20250929-thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5-think",
   "model_name": "claude-sonnet-4-5-think",
   "display_name": "claude-sonnet-4-5-think",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-5-think"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5@eu-central-1",
   "model_name": "claude-sonnet-4-5@eu-central-1",
   "display_name": "bedrock/claude-sonnet-4-5@eu-central-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-5@eu-central-1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-5@eu-central-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-5@eu-central-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5@eu-north-1",
   "model_name": "claude-sonnet-4-5@eu-north-1",
   "display_name": "bedrock/claude-sonnet-4-5@eu-north-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-5@eu-north-1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-5@eu-north-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-5@eu-north-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5@eu-west-1",
   "model_name": "claude-sonnet-4-5@eu-west-1",
   "display_name": "bedrock/claude-sonnet-4-5@eu-west-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-5@eu-west-1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-5@eu-west-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-5@eu-west-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5@eu-west-3",
   "model_name": "claude-sonnet-4-5@eu-west-3",
   "display_name": "bedrock/claude-sonnet-4-5@eu-west-3",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-5@eu-west-3"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-5@eu-west-3"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-5@eu-west-3"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5@europe-west1",
   "model_name": "claude-sonnet-4-5@europe-west1",
   "display_name": "vertex/claude-sonnet-4-5@europe-west1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.13"
      }
     },
     "provider_model_id": "vertex/claude-sonnet-4-5@europe-west1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-sonnet-4-5@europe-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-sonnet-4-5@europe-west1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5@us-east-1",
   "model_name": "claude-sonnet-4-5@us-east-1",
   "display_name": "bedrock/claude-sonnet-4-5@us-east-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-5@us-east-1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-5@us-east-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-5@us-east-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5@us-east-2",
   "model_name": "claude-sonnet-4-5@us-east-2",
   "display_name": "bedrock/claude-sonnet-4-5@us-east-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-5@us-east-2"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-5@us-east-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-5@us-east-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5@us-east5",
   "model_name": "claude-sonnet-4-5@us-east5",
   "display_name": "vertex/claude-sonnet-4-5@us-east5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.13"
      }
     },
     "provider_model_id": "vertex/claude-sonnet-4-5@us-east5"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-sonnet-4-5@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-sonnet-4-5@us-east5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-5@us-west-2",
   "model_name": "claude-sonnet-4-5@us-west-2",
   "display_name": "bedrock/claude-sonnet-4-5@us-west-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-5@us-west-2"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-5@us-west-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-5@us-west-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6",
   "model_name": "claude-sonnet-4-6",
   "display_name": "Claude Sonnet 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+helicone-registry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-sonnet-4-6",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "il-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "me-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "me-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "us-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "claude-sonnet-4.6"
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-4-6"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "freemodel",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "claude-sonnet-4.6"
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "claude-sonnet-4-6@20260217",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.501333"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6",
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.515152",
        "cache_write": "0.499394"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1.001212"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.515152",
        "cache_write": "0.499394"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1.001212"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.515152",
        "cache_write": "0.499394"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1.001212"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "pa/claude-sonnet-4-6"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.25"
      }
     }
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.993999999999998"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "vertexanthropic/claude-sonnet-4-6"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4.6"
    }
   ],
   "intro": "Claude workhorse for coding agents, careful analysis, and production cost control",
   "released_at": "2026-02-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "stop",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "docs_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6",
   "benchmarks": {
    "intelligence_index": 47.2,
    "coding_index": 63,
    "agentic_index": 40.8
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-sonnet-4-6",
    "anthropic.claude-sonnet-4-6-20260217-v1:0",
    "anthropic.claude-sonnet-4-6-v1:0",
    "anthropic/claude-sonnet-4-6",
    "anthropic/claude-sonnet-4.6",
    "anthropic/claude-sonnet-4.6:thinking",
    "au.anthropic.claude-sonnet-4-6",
    "bedrock/claude-sonnet-4-6",
    "claude-sonnet-4-6@20260217",
    "claude-sonnet-4.6",
    "eu.anthropic.claude-sonnet-4-6",
    "eu.anthropic.claude-sonnet-4-6-v1:0",
    "global.anthropic.claude-sonnet-4-6",
    "global.anthropic.claude-sonnet-4-6-v1:0",
    "jp.anthropic.claude-sonnet-4-6",
    "pa/claude-sonnet-4-6",
    "stealth/claude-sonnet-4.6",
    "us.anthropic.claude-sonnet-4-6",
    "us.anthropic.claude-sonnet-4-6-v1:0",
    "vertex/claude-sonnet-4-6",
    "vertexanthropic/claude-sonnet-4-6"
   ],
   "intro_i18n": {
    "zh-CN": "Anthropic 的 Claude Sonnet 4.6 —— 最新 Sonnet 模型，在编码与工具使用方面表现更强。",
    "zh-TW": "Anthropic 的 Claude Sonnet 4.6 —— 最新 Sonnet，具備更卓越的程式與工具使用能力。",
    "ja-JP": "Claude Sonnet 4.6 by Anthropic — 最新のSonnetモデルで、優れたコーディングとツール使用能力を備えています。",
    "ru-RU": "Claude Sonnet 4.6 от Anthropic — последняя версия Sonnet с превосходными возможностями в программировании и использовании инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-05",
     "kind": "limit",
     "old": "64000",
     "new": "128000",
     "note": "max_output_tokens"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6-cc",
   "model_name": "claude-sonnet-4-6-cc",
   "display_name": "claude-sonnet-4-6-cc",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.55"
      }
     }
    }
   ],
   "released_at": "2026-06-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-6-cc"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6-dd",
   "model_name": "claude-sonnet-4-6-dd",
   "display_name": "claude-sonnet-4-6-dd",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.25"
      }
     }
    }
   ],
   "released_at": "2026-03-30",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-6-dd"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6-r",
   "model_name": "claude-sonnet-4-6-r",
   "display_name": "claude-sonnet-4-6-r",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "released_at": "2026-06-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-6-r"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6-think",
   "model_name": "claude-sonnet-4-6-think",
   "display_name": "Claude Sonnet 4.6 Thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2026-02-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4.6 Thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6-thinking",
   "model_name": "claude-sonnet-4-6-thinking",
   "display_name": "claude-sonnet-4-6-thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2026-02-18",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-6-thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6-v1",
   "model_name": "claude-sonnet-4-6-v1",
   "display_name": "claude-sonnet-4-6-v1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-4-6-v1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-sonnet-4-6-v1",
    "eu.anthropic.claude-sonnet-4-6-v1",
    "us.anthropic.claude-sonnet-4-6-v1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-sonnet-4-6-v1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@ap-northeast-1",
   "model_name": "claude-sonnet-4-6@ap-northeast-1",
   "display_name": "bedrock/claude-sonnet-4-6@ap-northeast-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-6@ap-northeast-1"
    }
   ],
   "released_at": "2026-07-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-6@ap-northeast-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-6@ap-northeast-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@default",
   "model_name": "claude-sonnet-4-6@default",
   "display_name": "Claude Sonnet 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6@default",
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6@default",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6@default",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6@default",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6@default",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-4-6@default",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Claude workhorse for coding agents, careful analysis, and production cost control",
   "released_at": "2026-02-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-sonnet-4-6@default"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4.6"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@eu-central-1",
   "model_name": "claude-sonnet-4-6@eu-central-1",
   "display_name": "bedrock/claude-sonnet-4-6@eu-central-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-6@eu-central-1"
    }
   ],
   "released_at": "2026-02-19",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-6@eu-central-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-6@eu-central-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@eu-north-1",
   "model_name": "claude-sonnet-4-6@eu-north-1",
   "display_name": "bedrock/claude-sonnet-4-6@eu-north-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-6@eu-north-1"
    }
   ],
   "released_at": "2026-02-19",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-6@eu-north-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-6@eu-north-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@eu-west-1",
   "model_name": "claude-sonnet-4-6@eu-west-1",
   "display_name": "bedrock/claude-sonnet-4-6@eu-west-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-6@eu-west-1"
    }
   ],
   "released_at": "2026-02-19",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-6@eu-west-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-6@eu-west-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@eu-west-3",
   "model_name": "claude-sonnet-4-6@eu-west-3",
   "display_name": "bedrock/claude-sonnet-4-6@eu-west-3",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-6@eu-west-3"
    }
   ],
   "released_at": "2026-02-19",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-6@eu-west-3"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-6@eu-west-3"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@europe-west1",
   "model_name": "claude-sonnet-4-6@europe-west1",
   "display_name": "vertex/claude-sonnet-4-6@europe-west1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "vertex/claude-sonnet-4-6@europe-west1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-sonnet-4-6@europe-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-sonnet-4-6@europe-west1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@us-east-1",
   "model_name": "claude-sonnet-4-6@us-east-1",
   "display_name": "bedrock/claude-sonnet-4-6@us-east-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-6@us-east-1"
    }
   ],
   "released_at": "2026-02-19",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-6@us-east-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-6@us-east-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@us-east-2",
   "model_name": "claude-sonnet-4-6@us-east-2",
   "display_name": "bedrock/claude-sonnet-4-6@us-east-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-6@us-east-2"
    }
   ],
   "released_at": "2026-02-19",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-6@us-east-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-6@us-east-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@us-east5",
   "model_name": "claude-sonnet-4-6@us-east5",
   "display_name": "vertex/claude-sonnet-4-6@us-east5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "vertex/claude-sonnet-4-6@us-east5"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-sonnet-4-6@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-sonnet-4-6@us-east5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-6@us-west-2",
   "model_name": "claude-sonnet-4-6@us-west-2",
   "display_name": "bedrock/claude-sonnet-4-6@us-west-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4-6@us-west-2"
    }
   ],
   "released_at": "2026-02-19",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4-6@us-west-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4-6@us-west-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-thinking",
   "model_name": "claude-sonnet-4-thinking",
   "display_name": "Claude 4 Sonnet Thinking",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-02-24",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4 Sonnet Thinking"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-thinking:1024",
   "model_name": "claude-sonnet-4-thinking:1024",
   "display_name": "Claude 4 Sonnet Thinking (1K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4 Sonnet Thinking (1K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-thinking:32768",
   "model_name": "claude-sonnet-4-thinking:32768",
   "display_name": "Claude 4 Sonnet Thinking (32K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4 Sonnet Thinking (32K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-thinking:64000",
   "model_name": "claude-sonnet-4-thinking:64000",
   "display_name": "Claude 4 Sonnet Thinking (64K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4 Sonnet Thinking (64K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4-thinking:8192",
   "model_name": "claude-sonnet-4-thinking:8192",
   "display_name": "Claude 4 Sonnet Thinking (8K)",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-22",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude 4 Sonnet Thinking (8K)"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4.5-rp",
   "model_name": "claude-sonnet-4.5-rp",
   "display_name": "claude-sonnet-4.5-rp",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "claude-sonnet-4.5-rp"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4.6-rp",
   "model_name": "claude-sonnet-4.6-rp",
   "display_name": "claude-sonnet-4.6-rp",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "claude-sonnet-4.6-rp"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4@eu-central-1",
   "model_name": "claude-sonnet-4@eu-central-1",
   "display_name": "bedrock/claude-sonnet-4@eu-central-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4@eu-central-1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4@eu-central-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4@eu-central-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4@eu-north-1",
   "model_name": "claude-sonnet-4@eu-north-1",
   "display_name": "bedrock/claude-sonnet-4@eu-north-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4@eu-north-1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4@eu-north-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4@eu-north-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4@eu-west-1",
   "model_name": "claude-sonnet-4@eu-west-1",
   "display_name": "bedrock/claude-sonnet-4@eu-west-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4@eu-west-1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4@eu-west-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4@eu-west-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4@eu-west-3",
   "model_name": "claude-sonnet-4@eu-west-3",
   "display_name": "bedrock/claude-sonnet-4@eu-west-3",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4@eu-west-3"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4@eu-west-3"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4@eu-west-3"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4@europe-west1",
   "model_name": "claude-sonnet-4@europe-west1",
   "display_name": "vertex/claude-sonnet-4@europe-west1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "vertex/claude-sonnet-4@europe-west1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-sonnet-4@europe-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-sonnet-4@europe-west1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4@us-east-1",
   "model_name": "claude-sonnet-4@us-east-1",
   "display_name": "bedrock/claude-sonnet-4@us-east-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4@us-east-1"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4@us-east-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4@us-east-1"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4@us-east-2",
   "model_name": "claude-sonnet-4@us-east-2",
   "display_name": "bedrock/claude-sonnet-4@us-east-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4@us-east-2"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4@us-east-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4@us-east-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4@us-east5",
   "model_name": "claude-sonnet-4@us-east5",
   "display_name": "vertex/claude-sonnet-4@us-east5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "vertex/claude-sonnet-4@us-east5"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-sonnet-4@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-sonnet-4@us-east5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-4@us-west-2",
   "model_name": "claude-sonnet-4@us-west-2",
   "display_name": "bedrock/claude-sonnet-4@us-west-2",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "bedrock/claude-sonnet-4@us-west-2"
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "bedrock/claude-sonnet-4@us-west-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/claude-sonnet-4@us-west-2"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-45",
   "model_name": "claude-sonnet-45",
   "display_name": "Claude Sonnet 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.69"
      }
     }
    }
   ],
   "released_at": "2025-01-15",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 198000,
   "max_output_tokens": 49500,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "claude-sonnet",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-5",
   "model_name": "claude-sonnet-5",
   "display_name": "Claude Sonnet 5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "il-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "us-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "global.anthropic.claude-sonnet-5",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.975"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.874"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.197"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_write_1h": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.501818"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5",
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "0.5",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "cache_write": "0.501818"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_write_1h": "1",
        "prompt": "1",
        "completion": "1",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-5"
    }
   ],
   "intro": "Everyday Claude agent model for coding, planning, browsing, and general work",
   "released_at": "2026-06-29",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "computer_use": true,
    "parallel_function_calling": true,
    "assistant_prefill": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "status": "beta",
   "benchmarks": {
    "intelligence_index": 53.4,
    "coding_index": 71.5,
    "agentic_index": 46.7
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-sonnet-5",
    "anthropic/claude-sonnet-5",
    "anthropic/claude-sonnet-5-free",
    "anthropic/claude-sonnet-5:thinking",
    "au.anthropic.claude-sonnet-5",
    "bedrock/claude-sonnet-5",
    "eu.anthropic.claude-sonnet-5",
    "global.anthropic.claude-sonnet-5",
    "global.anthropic.claude-sonnet-5-v1:0",
    "jp.anthropic.claude-sonnet-5",
    "us.anthropic.claude-sonnet-5",
    "vertex/claude-sonnet-5"
   ],
   "intro_i18n": {
    "zh-CN": "Claude Sonnet 5 是 Anthropic 最具主动性的 Sonnet 模型，专为持续编码、工具使用和长上下文工作流程而设计，具有 Sonnet 级别的速度和效率。",
    "zh-TW": "Claude Sonnet 5 是 Anthropic 最具代理性的 Sonnet 模型，專為持續編碼、工具使用以及長上下文工作流程而設計，具備 Sonnet 級別的速度和效率。",
    "ja-JP": "Claude Sonnet 5は、Anthropicが開発した最も主体的なSonnetモデルで、持続的なコーディング、ツールの使用、長いコンテキストのワークフローに対応し、Sonnetクラスの速度と効率を備えています。",
    "ru-RU": "Claude Sonnet 5 — это самая агентная модель Sonnet от Anthropic, созданная для устойчивого кодирования, использования инструментов и рабочих процессов с длинным контекстом, обеспечивая скорость и эффективность уровня Sonnet."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "amazon-bedrock",
     "charge": "cache_write_1h",
     "old": "6",
     "new": "4"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "anthropic",
     "charge": "cache_write_1h",
     "old": "6",
     "new": "4"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "cache_write_1h",
     "old": "6",
     "new": "4"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "google-vertex-anthropic",
     "charge": "cache_read",
     "old": "0.3",
     "new": "0.2"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "google-vertex-anthropic",
     "charge": "cache_write",
     "old": "3.75",
     "new": "2.5"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "google-vertex-anthropic",
     "charge": "cache_write_1h",
     "old": "6",
     "new": "4"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "google-vertex-anthropic",
     "charge": "completion",
     "old": "15",
     "new": "10"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "google-vertex-anthropic",
     "charge": "prompt",
     "old": "3",
     "new": "2"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "assistant_prefill: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-5@default",
   "model_name": "claude-sonnet-5@default",
   "display_name": "Claude Sonnet 5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "google-vertex-anthropic",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     }
    }
   ],
   "intro": "Everyday Claude agent model for coding, planning, browsing, and general work",
   "released_at": "2026-06-30",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 5"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "google-vertex-anthropic",
     "charge": "cache_write_1h",
     "old": "6",
     "new": "4"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-5@eu",
   "model_name": "claude-sonnet-5@eu",
   "display_name": "vertex/claude-sonnet-5@eu",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     },
     "provider_model_id": "vertex/claude-sonnet-5@eu"
    }
   ],
   "released_at": "2026-06-30",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-sonnet-5@eu"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-sonnet-5@eu"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-5@us",
   "model_name": "claude-sonnet-5@us",
   "display_name": "vertex/claude-sonnet-5@us",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     },
     "provider_model_id": "vertex/claude-sonnet-5@us"
    }
   ],
   "released_at": "2026-06-30",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "vertex/claude-sonnet-5@us"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/claude-sonnet-5@us"
    }
   ]
  },
  {
   "slug": "anthropic/claude-sonnet-latest",
   "model_name": "claude-sonnet-latest",
   "display_name": "Anthropic: Claude Sonnet Latest",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "~anthropic/claude-sonnet-latest"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2992"
      }
     },
     "provider_model_id": "anthropic/claude-sonnet-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "~anthropic/claude-sonnet-latest"
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2026-04-27",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "family": "claude-sonnet",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic/claude-sonnet-latest",
    "~anthropic/claude-sonnet-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Anthropic: Claude Sonnet Latest"
    }
   ]
  },
  {
   "slug": "anthropic/claude-v1",
   "model_name": "claude-v1",
   "display_name": "claude-v1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "anthropic",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      },
      "audio_input": {
       "unit": "per_second",
       "price": "0.0455"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0.0455"
      }
     },
     "provider_model_id": "anthropic.claude-v1"
    }
   ],
   "intro": "Retired, here to match price sources",
   "capabilities": {},
   "max_input_tokens": 100000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "claude-v1"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-3-7-sonnet",
   "model_name": "databricks-claude-3-7-sonnet",
   "display_name": "databricks-claude-3-7-sonnet",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.9999900000000002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.000020000000002"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "max_input_tokens": 200000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "assistant_prefill": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-claude-3-7-sonnet"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-haiku-4-5",
   "model_name": "databricks-claude-haiku-4-5",
   "display_name": "Claude Haiku 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
   "released_at": "2025-10-15",
   "knowledge_cutoff": "2025-02",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "assistant_prefill": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Haiku 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-opus-4",
   "model_name": "databricks-claude-opus-4",
   "display_name": "databricks-claude-opus-4",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15.000020000000002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75.00003000000001"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.499999",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "assistant_prefill": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-claude-opus-4"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-opus-4-1",
   "model_name": "databricks-claude-opus-4-1",
   "display_name": "Claude Opus 4.1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-08-05",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "assistant_prefill": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.1"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-opus-4-5",
   "model_name": "databricks-claude-opus-4-5",
   "display_name": "Claude Opus 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2025-11-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "assistant_prefill": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-opus-4-6",
   "model_name": "databricks-claude-opus-4-6",
   "display_name": "Claude Opus 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "High-end Claude for difficult coding, planning, and slower expert reasoning",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.6"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-opus-4-7",
   "model_name": "databricks-claude-opus-4-7",
   "display_name": "Claude Opus 4.7",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Stronger Opus tier for advanced software work and high-stakes reasoning",
   "released_at": "2026-04-16",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "assistant_prefill": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.7"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-sonnet-4",
   "model_name": "databricks-claude-sonnet-4",
   "display_name": "Claude Sonnet 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-09-29",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "assistant_prefill": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-sonnet-4-1",
   "model_name": "databricks-claude-sonnet-4-1",
   "display_name": "databricks-claude-sonnet-4-1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.9999900000000002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.000020000000002"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "assistant_prefill": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-claude-sonnet-4-1"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-sonnet-4-5",
   "model_name": "databricks-claude-sonnet-4-5",
   "display_name": "Claude Sonnet 4.5",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2025-09-29",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "assistant_prefill": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4.5"
    }
   ]
  },
  {
   "slug": "anthropic/databricks-claude-sonnet-4-6",
   "model_name": "databricks-claude-sonnet-4-6",
   "display_name": "Claude Sonnet 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Claude workhorse for coding agents, careful analysis, and production cost control",
   "released_at": "2026-02-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "assistant_prefill": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Sonnet 4.6"
    }
   ]
  },
  {
   "slug": "anthropic/deepclaude",
   "model_name": "deepclaude",
   "display_name": "DeepClaude",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-02-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepClaude"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-3-5-haiku-20241022-v1:0",
   "model_name": "regional.anthropic.claude-3-5-haiku-20241022-v1:0",
   "display_name": "regional.anthropic.claude-3-5-haiku-20241022-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-3-5-haiku-20241022-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-3-5-sonnet-20241022-v2:0",
   "model_name": "regional.anthropic.claude-3-5-sonnet-20241022-v2:0",
   "display_name": "regional.anthropic.claude-3-5-sonnet-20241022-v2:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "regional.anthropic.claude-3-5-sonnet-20240620-v1:0"
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "regional.anthropic.claude-3-5-sonnet-20240620-v1:0"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-3-5-sonnet-20241022-v2:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-3-7-sonnet-20250219-v1:0",
   "model_name": "regional.anthropic.claude-3-7-sonnet-20250219-v1:0",
   "display_name": "regional.anthropic.claude-3-7-sonnet-20250219-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-3-7-sonnet-20250219-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-3-haiku-20240307-v1:0",
   "model_name": "regional.anthropic.claude-3-haiku-20240307-v1:0",
   "display_name": "regional.anthropic.claude-3-haiku-20240307-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-3-haiku-20240307-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-3-opus-20240229-v1:0",
   "model_name": "regional.anthropic.claude-3-opus-20240229-v1:0",
   "display_name": "regional.anthropic.claude-3-opus-20240229-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-3-opus-20240229-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-3-sonnet-20240229-v1:0",
   "model_name": "regional.anthropic.claude-3-sonnet-20240229-v1:0",
   "display_name": "regional.anthropic.claude-3-sonnet-20240229-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-3-sonnet-20240229-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-fable-5-v1:0",
   "model_name": "regional.anthropic.claude-fable-5-v1:0",
   "display_name": "regional.anthropic.claude-fable-5-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "55"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "13.75"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-fable-5-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-haiku-4-5-20251001-v1:0",
   "model_name": "regional.anthropic.claude-haiku-4-5-20251001-v1:0",
   "display_name": "regional.anthropic.claude-haiku-4-5-20251001-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.375"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-haiku-4-5-20251001-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-opus-4-1-20250805-v1:0",
   "model_name": "regional.anthropic.claude-opus-4-1-20250805-v1:0",
   "display_name": "regional.anthropic.claude-opus-4-1-20250805-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-opus-4-1-20250805-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-opus-4-20250514-v1:0",
   "model_name": "regional.anthropic.claude-opus-4-20250514-v1:0",
   "display_name": "regional.anthropic.claude-opus-4-20250514-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "18.75"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-opus-4-20250514-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-opus-4-5-v1:0",
   "model_name": "regional.anthropic.claude-opus-4-5-v1:0",
   "display_name": "regional.anthropic.claude-opus-4-5-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-opus-4-5-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-opus-4-6-v1:0",
   "model_name": "regional.anthropic.claude-opus-4-6-v1:0",
   "display_name": "regional.anthropic.claude-opus-4-6-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-opus-4-6-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-opus-4-7-v1:0",
   "model_name": "regional.anthropic.claude-opus-4-7-v1:0",
   "display_name": "regional.anthropic.claude-opus-4-7-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-opus-4-7-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-opus-4-8-v1:0",
   "model_name": "regional.anthropic.claude-opus-4-8-v1:0",
   "display_name": "regional.anthropic.claude-opus-4-8-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-opus-4-8-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-sonnet-4-20250514-v1:0",
   "model_name": "regional.anthropic.claude-sonnet-4-20250514-v1:0",
   "display_name": "regional.anthropic.claude-sonnet-4-20250514-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-sonnet-4-20250514-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-sonnet-4-5-20250929-v1:0",
   "model_name": "regional.anthropic.claude-sonnet-4-5-20250929-v1:0",
   "display_name": "regional.anthropic.claude-sonnet-4-5-20250929-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-sonnet-4-5-20250929-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-sonnet-4-6-v1:0",
   "model_name": "regional.anthropic.claude-sonnet-4-6-v1:0",
   "display_name": "regional.anthropic.claude-sonnet-4-6-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.125"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-sonnet-4-6-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/regional.anthropic.claude-sonnet-5-v1:0",
   "model_name": "regional.anthropic.claude-sonnet-5-v1:0",
   "display_name": "regional.anthropic.claude-sonnet-5-v1:0",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "regional.anthropic.claude-sonnet-5-v1:0"
    }
   ]
  },
  {
   "slug": "anthropic/us.anthropic.claude-fable-5-v1",
   "model_name": "us.anthropic.claude-fable-5-v1",
   "display_name": "us.anthropic.claude-fable-5-v1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "50"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "provider_model_id": "anthropic.claude-fable-5-v1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-fable-5-v1",
    "eu.anthropic.claude-fable-5-v1",
    "global.anthropic.claude-fable-5-v1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.anthropic.claude-fable-5-v1"
    }
   ]
  },
  {
   "slug": "anthropic/us.anthropic.claude-opus-4-6-v1",
   "model_name": "us.anthropic.claude-opus-4-6-v1",
   "display_name": "Claude Opus 4.6",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-6-v1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "af-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ap-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ap-northeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ap-northeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ap-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ap-southeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-opus-4-6-v1",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-opus-4-6-v1",
     "region": "ap-southeast-4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ap-southeast-5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "au.anthropic.claude-opus-4-6-v1",
     "region": "ap-southeast-6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ap-southeast-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "ca-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-6-v1",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-6-v1",
     "region": "eu-central-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-6-v1",
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-6-v1",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-6-v1",
     "region": "eu-south-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-6-v1",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-6-v1",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.875"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     },
     "provider_model_id": "eu.anthropic.claude-opus-4-6-v1",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "il-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "me-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "me-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "mx-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "us-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "global.anthropic.claude-opus-4-6-v1"
    }
   ],
   "intro": "High-end Claude for difficult coding, planning, and slower expert reasoning",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "reasoning_config": {
    "budget_min": 1024
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "computer_use": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-opus-4-6-v1",
    "au.anthropic.claude-opus-4-6-v1",
    "eu.anthropic.claude-opus-4-6-v1",
    "global.anthropic.claude-opus-4-6-v1"
   ],
   "intro_i18n": {
    "zh-CN": "Claude Opus 4.6 是 Anthropic 用于构建代理和编程的最智能模型。",
    "zh-TW": "Claude Opus 4.6 是 Anthropic 用於構建代理和編碼的最智能模型。",
    "ja-JP": "Claude Opus 4.6は、エージェント構築やコーディングにおいてAnthropicの最も知的なモデルです。",
    "ru-RU": "Claude Opus 4.6 — это самая интеллектуальная модель Anthropic для создания агентов и программирования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claude Opus 4.6"
    }
   ]
  },
  {
   "slug": "anthropic/us.anthropic.claude-opus-4-7-v1",
   "model_name": "us.anthropic.claude-opus-4-7-v1",
   "display_name": "us.anthropic.claude-opus-4-7-v1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-7-v1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-opus-4-7-v1",
    "eu.anthropic.claude-opus-4-7-v1",
    "global.anthropic.claude-opus-4-7-v1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.anthropic.claude-opus-4-7-v1"
    }
   ]
  },
  {
   "slug": "anthropic/us.anthropic.claude-opus-4-8-v1",
   "model_name": "us.anthropic.claude-opus-4-8-v1",
   "display_name": "us.anthropic.claude-opus-4-8-v1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "anthropic.claude-opus-4-8-v1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-opus-4-8-v1",
    "eu.anthropic.claude-opus-4-8-v1",
    "global.anthropic.claude-opus-4-8-v1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.anthropic.claude-opus-4-8-v1"
    }
   ]
  },
  {
   "slug": "anthropic/us.anthropic.claude-sonnet-5-v1",
   "model_name": "us.anthropic.claude-sonnet-5-v1",
   "display_name": "us.anthropic.claude-sonnet-5-v1",
   "vendor": "anthropic",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "anthropic.claude-sonnet-5-v1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "anthropic-messages",
     "openai-compatible"
    ],
    "outbound": [
     "anthropic-messages"
    ]
   },
   "aliases": [
    "anthropic.claude-sonnet-5-v1",
    "eu.anthropic.claude-sonnet-5-v1",
    "global.anthropic.claude-sonnet-5-v1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.anthropic.claude-sonnet-5-v1"
    }
   ]
  },
  {
   "slug": "arcee/arcee-blitz",
   "model_name": "arcee-blitz",
   "display_name": "arcee-blitz",
   "vendor": "arcee",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "arcee-blitz"
    }
   ]
  },
  {
   "slug": "arcee/arcee-trinity-large-thinking",
   "model_name": "arcee-trinity-large-thinking",
   "display_name": "Trinity Large Thinking",
   "vendor": "arcee",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2026-04-02",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "trinity",
   "status": "beta",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Trinity Large Thinking"
    }
   ]
  },
  {
   "slug": "arcee/coder-large",
   "model_name": "coder-large",
   "display_name": "Arcee AI: Coder Large",
   "vendor": "arcee",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "arcee-ai/coder-large"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "arcee-ai/coder-large"
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2025-05-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "knowledge_cutoff": "2025-03",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "arcee-ai/coder-large"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Arcee AI: Coder Large"
    }
   ]
  },
  {
   "slug": "arcee/maestro-reasoning",
   "model_name": "maestro-reasoning",
   "display_name": "Arcee AI: Maestro Reasoning",
   "vendor": "arcee",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     },
     "provider_model_id": "arcee-ai/maestro-reasoning"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     },
     "provider_model_id": "arcee-ai/maestro-reasoning"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-05-06",
   "max_input_tokens": 131072,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "arcee-ai/maestro-reasoning"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Arcee AI: Maestro Reasoning"
    }
   ]
  },
  {
   "slug": "arcee/spotlight",
   "model_name": "spotlight",
   "display_name": "Arcee AI: Spotlight",
   "vendor": "arcee",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "arcee-ai/spotlight"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "arcee-ai/spotlight"
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2025-05-06",
   "max_input_tokens": 131072,
   "max_output_tokens": 65537,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "arcee-ai/spotlight"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Arcee AI: Spotlight"
    }
   ]
  },
  {
   "slug": "arcee/trinity-large-preview",
   "model_name": "trinity-large-preview",
   "display_name": "Trinity Large Preview",
   "vendor": "arcee",
   "pricing": [
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "trinity-large-preview-free"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "arcee-ai/trinity-large-preview"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "arcee-ai/trinity-large-preview"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2026-01-27",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 131000,
   "max_output_tokens": 131000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "trinity",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "deprecated": true,
   "status": "deprecated",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "arcee-ai/trinity-large-preview",
    "arcee-ai/trinity-large-preview:free",
    "trinity-large-preview-free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Trinity Large Preview"
    }
   ]
  },
  {
   "slug": "arcee/trinity-large-thinking",
   "model_name": "trinity-large-thinking",
   "display_name": "Trinity Large Thinking",
   "vendor": "arcee",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "arcee-ai/trinity-large-thinking"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "arcee-ai/trinity-large-thinking"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "arcee-ai/trinity-large-thinking"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8999999999999999"
      }
     },
     "provider_model_id": "arcee-ai/trinity-large-thinking"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2026-04-01",
   "max_input_tokens": 262100,
   "max_output_tokens": 80000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "trinity",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3,
     "top_p": 0.8
    }
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "arcee-ai/trinity-large-thinking",
    "arcee-ai/trinity-large-thinking:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Trinity Large Thinking"
    }
   ]
  },
  {
   "slug": "arcee/trinity-mini",
   "model_name": "trinity-mini",
   "display_name": "Trinity Mini",
   "vendor": "arcee",
   "pricing": [
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.045"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "arcee_ai/AFM/models/trinity-mini"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.045"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "arcee-ai/trinity-mini"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.045000000000000005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "arcee-ai/trinity-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.045"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "arcee-ai/trinity-mini"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.045"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "arcee-ai/trinity-mini"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.045"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "arcee-ai/trinity-mini"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "trinity",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_completion_tokens",
     "max_tokens",
     "reasoning",
     "response_format",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.15,
     "top_p": 0.75
    }
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "arcee-ai/trinity-mini",
    "arcee-ai/trinity-mini:free",
    "arcee_ai/AFM/models/trinity-mini"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Trinity Mini"
    }
   ]
  },
  {
   "slug": "arcee/virtuoso-large",
   "model_name": "virtuoso-large",
   "display_name": "Arcee AI: Virtuoso Large",
   "vendor": "arcee",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "arcee-ai/virtuoso-large"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "arcee-ai/virtuoso-large"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2025-05-06",
   "max_input_tokens": 131072,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-03",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "arcee-ai/virtuoso-large"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Arcee AI: Virtuoso Large"
    }
   ]
  },
  {
   "slug": "baai/baai/bge-small-en-v1.5",
   "model_name": "baai/bge-small-en-v1.5",
   "display_name": "BGE Small EN v1.5",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/baai/bge-small-en-v1.5"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "@cf/baai/bge-small-en-v1.5"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-04-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "bge",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/baai/bge-small-en-v1.5",
    "workers-ai/@cf/baai/bge-small-en-v1.5"
   ],
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BGE Small EN v1.5"
    }
   ]
  },
  {
   "slug": "baai/bge-base-en-v1.5",
   "model_name": "bge-base-en-v1.5",
   "display_name": "BGE Base EN v1.5",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.067"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/baai/bge-base-en-v1.5"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.067"
      }
     },
     "provider_model_id": "@cf/baai/bge-base-en-v1.5"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "BAAI/bge-base-en-v1.5"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "baai/bge-base-en-v1.5"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/BAAI/bge-base-en-v1.5"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.008"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "BAAI/bge-base-en-v1.5"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-04-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "bge",
   "capabilities": {
    "prompt_caching": true,
    "stream": true
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/baai/bge-base-en-v1.5",
    "BAAI/bge-base-en-v1.5",
    "baai/bge-base-en-v1.5",
    "deepinfra/BAAI/bge-base-en-v1.5",
    "workers-ai/@cf/baai/bge-base-en-v1.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BGE Base EN v1.5"
    }
   ]
  },
  {
   "slug": "baai/bge-en-icl",
   "model_name": "bge-en-icl",
   "display_name": "BGE-ICL",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "BAAI/bge-en-icl"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "BAAI/bge-en-icl"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepinfra/BAAI/bge-en-icl"
    }
   ],
   "docs_url": "https://nebius.com/prices-ai-studio",
   "max_input_tokens": 32768,
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "released_at": "2024-07-30",
   "knowledge_cutoff": "2024-06",
   "family": "text-embedding",
   "max_output_tokens": 8192,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "BAAI/bge-en-icl",
    "deepinfra/BAAI/bge-en-icl"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BGE-ICL"
    }
   ]
  },
  {
   "slug": "baai/bge-large-en",
   "model_name": "bge-large-en",
   "display_name": "bge-large-en",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bge-large-en"
    }
   ]
  },
  {
   "slug": "baai/bge-large-en-v1-5",
   "model_name": "bge-large-en-v1-5",
   "display_name": "BGE Large EN v1.5",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.034"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.034"
      }
     },
     "provider_model_id": "BAAI/bge-large-en-v1.5"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/baai/bge-large-en-v1.5"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "@cf/baai/bge-large-en-v1.5"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "BAAI/bge-large-en-v1.5"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "baai/bge-large-en-v1.5"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepinfra/BAAI/bge-large-en-v1.5"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.008"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.008"
      }
     }
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2025-04-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "bge",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/baai/bge-large-en-v1.5",
    "BAAI/bge-large-en-v1.5",
    "baai/bge-large-en-v1.5",
    "deepinfra/BAAI/bge-large-en-v1.5",
    "workers-ai/@cf/baai/bge-large-en-v1.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BGE Large EN v1.5"
    }
   ]
  },
  {
   "slug": "baai/bge-large-zh",
   "model_name": "bge-large-zh",
   "display_name": "bge-large-zh",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bge-large-zh"
    }
   ]
  },
  {
   "slug": "baai/bge-large-zh-v1.5",
   "model_name": "bge-large-zh-v1.5",
   "display_name": "BAAI/bge-large-zh-v1.5",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.034"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.034"
      }
     },
     "provider_model_id": "BAAI/bge-large-zh-v1.5"
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "BAAI/bge-large-zh-v1.5"
   ],
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BAAI/bge-large-zh-v1.5"
    }
   ]
  },
  {
   "slug": "baai/bge-m3",
   "model_name": "bge-m3",
   "display_name": "BGE M3",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.012"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/baai/bge-m3"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.012"
      }
     },
     "provider_model_id": "@cf/baai/bge-m3"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "BAAI/bge-m3"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "baai/bge-m3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "baai/bge-m3"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepinfra/BAAI/bge-m3"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2024-01-30",
   "max_input_tokens": 8192,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "bge",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/baai/bge-m3",
    "BAAI/bge-m3",
    "baai/bge-m3",
    "deepinfra/BAAI/bge-m3",
    "workers-ai/@cf/baai/bge-m3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BGE M3"
    }
   ]
  },
  {
   "slug": "baai/bge-m3-multi",
   "model_name": "bge-m3-multi",
   "display_name": "BAAI/bge-m3-multi",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "BAAI/bge-m3-multi"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepinfra/BAAI/bge-m3-multi"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true
   },
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "BAAI/bge-m3-multi",
    "deepinfra/BAAI/bge-m3-multi"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BAAI/bge-m3-multi"
    }
   ]
  },
  {
   "slug": "baai/bge-multilingual-gemma2",
   "model_name": "bge-multilingual-gemma2",
   "display_name": "BGE Multilingual Gemma2",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "BAAI/bge-multilingual-gemma2"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2024-07-26",
   "max_input_tokens": 8191,
   "max_output_tokens": 3072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "docs_url": "https://nebius.com/prices-ai-studio",
   "model_type": "text_embedding",
   "knowledge_cutoff": "2024-06",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "BAAI/bge-multilingual-gemma2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BGE Multilingual Gemma2"
    }
   ]
  },
  {
   "slug": "baai/bge-reranker",
   "model_name": "bge-reranker",
   "display_name": "bge-reranker",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11416395"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11416395"
      }
     }
    }
   ],
   "released_at": "2025-04-23",
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114370748",
     "new": "0.11416395"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114370748",
     "new": "0.11416395"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114326597",
     "new": "0.114370748"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114326597",
     "new": "0.114370748"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114414143",
     "new": "0.114326597"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114414143",
     "new": "0.114326597"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114368084",
     "new": "0.114414143"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114368084",
     "new": "0.114414143"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114399787",
     "new": "0.114368084"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114399787",
     "new": "0.114368084"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.1138097",
     "new": "0.114399787"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.1138097",
     "new": "0.114399787"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bge-reranker"
    }
   ]
  },
  {
   "slug": "baai/bge-reranker-base",
   "model_name": "bge-reranker-base",
   "display_name": "BGE Reranker Base",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11416395"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11416395"
      }
     },
     "provider_model_id": "BAAI/bge-reranker-base"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0031"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/baai/bge-reranker-base"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0031"
      }
     },
     "provider_model_id": "@cf/baai/bge-reranker-base"
    }
   ],
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2025-04-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "bge",
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/baai/bge-reranker-base",
    "BAAI/bge-reranker-base",
    "workers-ai/@cf/baai/bge-reranker-base"
   ],
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114370748",
     "new": "0.11416395"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114370748",
     "new": "0.11416395"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114326597",
     "new": "0.114370748"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114326597",
     "new": "0.114370748"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114414143",
     "new": "0.114326597"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114414143",
     "new": "0.114326597"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114368084",
     "new": "0.114414143"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114368084",
     "new": "0.114414143"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114399787",
     "new": "0.114368084"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114399787",
     "new": "0.114368084"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.1138097",
     "new": "0.114399787"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.1138097",
     "new": "0.114399787"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BGE Reranker Base"
    }
   ]
  },
  {
   "slug": "baai/bge-reranker-v2-m3",
   "model_name": "bge-reranker-v2-m3",
   "display_name": "BGE Reranker v2 M3",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.034"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.034"
      }
     },
     "provider_model_id": "BAAI/bge-reranker-v2-m3"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "BAAI/bge-reranker-v2-m3"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2024-03-12",
   "max_input_tokens": 8192,
   "max_output_tokens": 1,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "bge",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2025-04",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "BAAI/bge-reranker-v2-m3"
   ],
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BGE Reranker v2 M3"
    }
   ]
  },
  {
   "slug": "baai/databricks-bge-large-en",
   "model_name": "databricks-bge-large-en",
   "display_name": "databricks-bge-large-en",
   "vendor": "baai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.10003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 512,
   "model_type": "text_embedding",
   "capabilities": {},
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-bge-large-en"
    }
   ]
  },
  {
   "slug": "baichuan/Baichuan-M2",
   "model_name": "Baichuan-M2",
   "display_name": "Baichuan M2",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "baichuan",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.9"
      }
     },
     "provider_model_id": "baichuan-m2"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15.73"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.73"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-08-19",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baichuan-m2"
   ],
   "intro_i18n": {
    "zh-CN": "我们推出 Baichuan-M2，这是一款面向真实世界医学推理任务的医学增强型推理模型。我们从真实医学问题出发，并基于大规模验证器系统进行强化学习训练。在保持模型通用能力的同时，Baichuan-M2 在医学有效性上取得了突破性提升。Baichuan-M2 是迄今为止全球最强的开源医疗大模型，性能超越包括 gpt-oss-120b 在内的所有开源模型，并在 HealthBench 基准上领先众多前沿闭源模型。在医学能力上，它是最接近 GPT-5 的开源模型。我们的实践表明，强健的验证器对于将模型能力与现实世界连接至关重要，而端到端的强化学习范式能够从根本上提升模型的医学推理能力。Baichuan-M2 的发布推动了医疗人工智能技术的前沿发展。",
    "zh-TW": "我們推出 Baichuan-M2，一款經過醫學增強的推理模型，專為真實世界的醫療推理任務設計。我們從真實醫療問題出發，基於大規模驗證器系統進行強化學習訓練。在保持模型通用能力的同時，Baichuan-M2 在醫療效果上取得突破性提升。Baichuan-M2 是目前全球最強的開源醫療模型，全面超越所有開源模型（包含 gpt-oss-120b）以及多款頂尖閉源模型，在 HealthBench 基準測試上名列前茅。它是醫療能力最接近 GPT-5 的開源模型。我們的實踐證明，強大的驗證器對於將模型能力連結到真實世界至關重要，而端到端強化學習方法能從根本提升模型的醫療推理能力。Baichuan-M2 的發布推動了醫療人工智慧領域的技術前沿。",
    "ja-JP": "Baichuan-M2は、医療分野に特化した推論モデルであり、実世界の医療推論タスクに対応するために設計されています。実際の医療質問を出発点とし、大規模な検証システムに基づく強化学習トレーニングを実施しました。モデルの一般的な能力を維持しつつ、Baichuan-M2の医療効果は画期的な向上を遂げました。Baichuan-M2は、現在世界で最も優れたオープンソースの医療モデルであり、gpt-oss-120bを含むすべてのオープンソースモデルや、最先端のクローズドソースモデルをHealthBenchベンチマークで上回ります。医療能力においてGPT-5に最も近いオープンソースモデルです。我々の実践は、堅牢な検証システムがモデル能力を実世界に結びつける上で重要であり、エンドツーエンドの強化学習アプローチがモデルの医療推論能力を根本的に向上させることを示しています。Baichuan-M2のリリースは、医療人工知能分野の技術の最前線をさらに進化させます。",
    "ru-RU": "Мы представляем Baichuan-M2 — модель медицинского рассуждения с расширенными возможностями, созданную для решения реальных медицинских задач. Мы начинаем с вопросов, основанных на реальной клинической практике, и проводим обучение с подкреплением на базе крупномасштабной системы верификации. Сохраняя общие способности модели, Baichuan-M2 демонстрирует значительный прорыв в медицинской эффективности. На сегодняшний день это лучшая открытая медицинская модель в мире. Она превосходит все открытые модели, включая gpt-oss-120b, а также многие передовые закрытые модели в бенчмарке HealthBench. По медицинским возможностям это самая близкая к GPT-5 открытая модель. Наша практика показывает, что надежный верификатор имеет решающее значение для связи возможностей модели с реальным миром, а подход обучения с подкреплением от начала до конца принципиально усиливает способность модели к медицинским рассуждениям. Выпуск Baichuan-M2 продвигает передовой уровень технологий в области медицинского искусственного интеллекта."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baichuan M2"
    }
   ]
  },
  {
   "slug": "baichuan/baichuan-m2-32b",
   "model_name": "baichuan-m2-32b",
   "display_name": "baichuan-m2-32b",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.426471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.705882"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "baichuan/baichuan-m2-32b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "baichuan/baichuan-m2-32b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "novita/baichuan/baichuan-m2-32b"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-08-13",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "baichuan",
   "capabilities": {
    "reasoning": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baichuan/baichuan-m2-32b",
    "novita/baichuan/baichuan-m2-32b"
   ],
   "intro_i18n": {
    "zh-CN": "Baichuan M2 32B 是百川智能推出的 MoE 模型，具备强大的推理能力。",
    "zh-TW": "Baichuan M2 32B 是百川智能推出的 MoE 模型，具備強大的推理能力。",
    "ja-JP": "Baichuan M2 32Bは、Baichuan IntelligenceによるMoEモデルで、優れた推論能力を備えています。",
    "ru-RU": "Baichuan M2 32B — это модель MoE от Baichuan Intelligence с сильными способностями к рассуждению."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "baichuan-m2-32b"
    }
   ]
  },
  {
   "slug": "baichuan/Baichuan-M2-Plus",
   "model_name": "Baichuan-M2-Plus",
   "display_name": "Baichuan M2 Plus",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "baichuan",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.411765"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.29"
      }
     },
     "provider_model_id": "baichuan-m2-plus"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true
   },
   "released_at": "2025-10-25",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baichuan-m2-plus"
   ],
   "intro_i18n": {
    "zh-CN": "我们推出 Baichuan-M2，这是一款面向真实世界医学推理任务的医学增强型推理模型。我们从真实医学问题出发，并基于大规模验证器系统进行强化学习训练。在保持模型通用能力的同时，Baichuan-M2 在医学有效性上取得了突破性提升。Baichuan-M2 是迄今为止全球最强的开源医疗大模型，性能超越包括 gpt-oss-120b 在内的所有开源模型，并在 HealthBench 基准上领先众多前沿闭源模型。在医学能力上，它是最接近 GPT-5 的开源模型。我们的实践表明，强健的验证器对于将模型能力与现实世界连接至关重要，而端到端的强化学习范式能够从根本上提升模型的医学推理能力。Baichuan-M2 的发布推动了医疗人工智能技术的前沿发展。",
    "zh-TW": "我們推出 Baichuan-M2，一款經過醫學增強的推理模型，專為真實世界的醫療推理任務設計。我們從真實醫療問題出發，基於大規模驗證器系統進行強化學習訓練。在保持模型通用能力的同時，Baichuan-M2 在醫療效果上取得突破性提升。Baichuan-M2 是目前全球最強的開源醫療模型，全面超越所有開源模型（包含 gpt-oss-120b）以及多款頂尖閉源模型，在 HealthBench 基準測試上名列前茅。它是醫療能力最接近 GPT-5 的開源模型。我們的實踐證明，強大的驗證器對於將模型能力連結到真實世界至關重要，而端到端強化學習方法能從根本提升模型的醫療推理能力。Baichuan-M2 的發布推動了醫療人工智慧領域的技術前沿。",
    "ja-JP": "Baichuan-M2は、医療分野に特化した推論モデルであり、実世界の医療推論タスクに対応するために設計されています。実際の医療質問を出発点とし、大規模な検証システムに基づく強化学習トレーニングを実施しました。モデルの一般的な能力を維持しつつ、Baichuan-M2の医療効果は画期的な向上を遂げました。Baichuan-M2は、現在世界で最も優れたオープンソースの医療モデルであり、gpt-oss-120bを含むすべてのオープンソースモデルや、最先端のクローズドソースモデルをHealthBenchベンチマークで上回ります。医療能力においてGPT-5に最も近いオープンソースモデルです。我々の実践は、堅牢な検証システムがモデル能力を実世界に結びつける上で重要であり、エンドツーエンドの強化学習アプローチがモデルの医療推論能力を根本的に向上させることを示しています。Baichuan-M2のリリースは、医療人工知能分野の技術の最前線をさらに進化させます。",
    "ru-RU": "Мы представляем Baichuan-M2 — модель медицинского рассуждения с расширенными возможностями, созданную для решения реальных медицинских задач. Мы начинаем с вопросов, основанных на реальной клинической практике, и проводим обучение с подкреплением на базе крупномасштабной системы верификации. Сохраняя общие способности модели, Baichuan-M2 демонстрирует значительный прорыв в медицинской эффективности. На сегодняшний день это лучшая открытая медицинская модель в мире. Она превосходит все открытые модели, включая gpt-oss-120b, а также многие передовые закрытые модели в бенчмарке HealthBench. По медицинским возможностям это самая близкая к GPT-5 открытая модель. Наша практика показывает, что надежный верификатор имеет решающее значение для связи возможностей модели с реальным миром, а подход обучения с подкреплением от начала до конца принципиально усиливает способность модели к медицинским рассуждениям. Выпуск Baichuan-M2 продвигает передовой уровень технологий в области медицинского искусственного интеллекта."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baichuan M2 Plus"
    }
   ]
  },
  {
   "slug": "baichuan/Baichuan-M3",
   "model_name": "Baichuan-M3",
   "display_name": "Baichuan M3",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "baichuan",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.411765"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.29"
      }
     },
     "provider_model_id": "baichuan-m3"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true
   },
   "released_at": "2026-01-21",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baichuan-m3"
   ],
   "intro_i18n": {
    "zh-CN": "我们推出 Baichuan-M3，这是一款新一代医学增强型大型语言模型，旨在支持临床级医疗辅助。不同于以往仅专注静态问答或浅层角色扮演的方法，Baichuan-M3 通过显式建模临床决策流程来提升真实医疗场景下的可用性与可靠性。它不再只是生成听起来合理的答案、流畅的“医生式提问”或诸如“请尽快就医”之类含糊但高频的建议，而是经过专门训练，能够主动获取关键临床信息、构建连贯的医学推理链，并在整个决策过程中系统性地抑制幻觉式输出。这一设计使模型具备与真实临床流程一致的医学增强能力。在临床问诊、医学幻觉鲁棒性、HealthBench 与 HealthBench-Hard 的评估中，Baichuan-M3 全面超越 OpenAI 最新旗舰模型 GPT-5.2，树立医学增强语言模型的新标杆。",
    "zh-TW": "我們推出 Baichuan-M3，新一代醫療增強大型語言模型，旨在支援臨床級的醫療輔助。不同於以往僅專注於靜態問答或表層角色扮演的方法，Baichuan-M3 被訓練為能明確建模臨床決策流程，以提升其在真實醫療場景中的可用性與可靠性。它不再僅生成似是而非的答案、流暢的醫生式提問，或高頻但模糊的建議（如「請儘速就醫」），而是經過特別訓練，能主動獲取關鍵臨床資訊、構建連貫的醫療推理路徑，並在整個決策過程中系統性抑制容易產生幻覺的行為。這樣的設計使其具備與臨床工作流程高度契合的內建醫療增強能力。在臨床問診、醫療幻覺穩健性、HealthBench 與 HealthBench-Hard 的評測中，Baichuan-M3 均超越 OpenAI 最新旗艦模型 GPT-5.2，樹立醫療增強語言模型的新標竿。",
    "ja-JP": "Baichuan-M3は、臨床レベルの医療支援を提供するために設計された新世代の医療強化型大規模言語モデルです。従来の静的な質問応答や表面的なロールプレイングに重点を置いたアプローチとは異なり、Baichuan-M3は臨床的意思決定プロセスを明示的にモデル化するように訓練され、実世界の医療実践における使いやすさと信頼性の向上を目指しています。単に説得力のある回答や流暢な医師のような質問、または「できるだけ早く医療機関を受診してください」といった曖昧な推奨を生成するのではなく、Baichuan-M3は重要な臨床情報を積極的に取得し、一貫した医療推論経路を構築し、意思決定プロセス全体で幻覚を起こしやすい行動を体系的に制約するように訓練されています。この設計により、モデルは実際の臨床ワークフローに一致した医療強化型能力を備えることができます。臨床的な問い合わせ、医療幻覚の耐性、HealthBench、およびHealthBench-Hardの評価において、Baichuan-M3はOpenAIがリリースした最新のフラッグシップモデルGPT-5.2を上回り、医療強化型言語モデルの新たな最先端を確立しました。",
    "ru-RU": "Мы представляем Baichuan-M3 — модель нового поколения с усиленными медицинскими возможностями, созданную для поддержки клинического уровня медицинской помощи. В отличие от предыдущих подходов, ориентированных в основном на статическое ответы на вопросы или поверхностное ролевое взаимодействие, Baichuan-M3 обучена явному моделированию процесса клинического принятия решений, что повышает ее практическую ценность и надежность в реальных медицинских условиях. Вместо того чтобы просто выдавать правдоподобные ответы, имитировать врачебные вопросы или давать частые, но расплывчатые рекомендации вроде «вам следует как можно скорее обратиться к врачу», Baichuan-M3 обучена активно собирать ключевую клиническую информацию, выстраивать последовательные логические цепочки рассуждений и систематически снижать вероятность галлюцинаций на протяжении всего процесса принятия решений. Такой подход наделяет модель встроенными медицинскими возможностями, согласованными с реальными клиническими рабочими процессами. В оценках по клиническим опросам, устойчивости к медицинским галлюцинациям, HealthBench и HealthBench-Hard, Baichuan-M3 превосходит последнюю флагманскую модель OpenAI — GPT-5.2, устанавливая новый стандарт для языковых моделей с медицинскими улучшениями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baichuan M3"
    }
   ]
  },
  {
   "slug": "baichuan/Baichuan-M3-Plus",
   "model_name": "Baichuan-M3-Plus",
   "display_name": "Baichuan M3 Plus",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "baichuan",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "我们推出 Baichuan-M3，这是一款新一代医学增强型大型语言模型，旨在支持临床级医疗辅助。不同于以往仅专注静态问答或浅层角色扮演的方法，Baichuan-M3 通过显式建模临床决策流程来提升真实医疗场景下的可用性与可靠性。它不再只是生成听起来合理的答案、流畅的“医生式提问”或诸如“请尽快就医”之类含糊但高频的建议，而是经过专门训练，能够主动获取关键临床信息、构建连贯的医学推理链，并在整个决策过程中系统性地抑制幻觉式输出。这一设计使模型具备与真实临床流程一致的医学增强能力。在临床问诊、医学幻觉鲁棒性、HealthBench 与 HealthBench-Hard 的评估中，Baichuan-M3 全面超越 OpenAI 最新旗舰模型 GPT-5.2，树立医学增强语言模型的新标杆。",
    "zh-TW": "我們推出 Baichuan-M3，新一代醫療增強大型語言模型，旨在支援臨床級的醫療輔助。不同於以往僅專注於靜態問答或表層角色扮演的方法，Baichuan-M3 被訓練為能明確建模臨床決策流程，以提升其在真實醫療場景中的可用性與可靠性。它不再僅生成似是而非的答案、流暢的醫生式提問，或高頻但模糊的建議（如「請儘速就醫」），而是經過特別訓練，能主動獲取關鍵臨床資訊、構建連貫的醫療推理路徑，並在整個決策過程中系統性抑制容易產生幻覺的行為。這樣的設計使其具備與臨床工作流程高度契合的內建醫療增強能力。在臨床問診、醫療幻覺穩健性、HealthBench 與 HealthBench-Hard 的評測中，Baichuan-M3 均超越 OpenAI 最新旗艦模型 GPT-5.2，樹立醫療增強語言模型的新標竿。",
    "ja-JP": "Baichuan-M3は、臨床レベルの医療支援を提供するために設計された新世代の医療強化型大規模言語モデルです。従来の静的な質問応答や表面的なロールプレイングに重点を置いたアプローチとは異なり、Baichuan-M3は臨床的意思決定プロセスを明示的にモデル化するように訓練され、実世界の医療実践における使いやすさと信頼性の向上を目指しています。単に説得力のある回答や流暢な医師のような質問、または「できるだけ早く医療機関を受診してください」といった曖昧な推奨を生成するのではなく、Baichuan-M3は重要な臨床情報を積極的に取得し、一貫した医療推論経路を構築し、意思決定プロセス全体で幻覚を起こしやすい行動を体系的に制約するように訓練されています。この設計により、モデルは実際の臨床ワークフローに一致した医療強化型能力を備えることができます。臨床的な問い合わせ、医療幻覚の耐性、HealthBench、およびHealthBench-Hardの評価において、Baichuan-M3はOpenAIがリリースした最新のフラッグシップモデルGPT-5.2を上回り、医療強化型言語モデルの新たな最先端を確立しました。",
    "ru-RU": "Мы представляем Baichuan-M3 — модель нового поколения с усиленными медицинскими возможностями, созданную для поддержки клинического уровня медицинской помощи. В отличие от предыдущих подходов, ориентированных в основном на статическое ответы на вопросы или поверхностное ролевое взаимодействие, Baichuan-M3 обучена явному моделированию процесса клинического принятия решений, что повышает ее практическую ценность и надежность в реальных медицинских условиях. Вместо того чтобы просто выдавать правдоподобные ответы, имитировать врачебные вопросы или давать частые, но расплывчатые рекомендации вроде «вам следует как можно скорее обратиться к врачу», Baichuan-M3 обучена активно собирать ключевую клиническую информацию, выстраивать последовательные логические цепочки рассуждений и систематически снижать вероятность галлюцинаций на протяжении всего процесса принятия решений. Такой подход наделяет модель встроенными медицинскими возможностями, согласованными с реальными клиническими рабочими процессами. В оценках по клиническим опросам, устойчивости к медицинским галлюцинациям, HealthBench и HealthBench-Hard, Baichuan-M3 превосходит последнюю флагманскую модель OpenAI — GPT-5.2, устанавливая новый стандарт для языковых моделей с медицинскими улучшениями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baichuan M3 Plus"
    }
   ]
  },
  {
   "slug": "baichuan/baichuan2-13b-chat",
   "model_name": "baichuan2-13b-chat",
   "display_name": "baichuan/baichuan2-13b-chat",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.257353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.257353"
      }
     },
     "provider_model_id": "baichuan/baichuan2-13b-chat"
    }
   ],
   "max_input_tokens": 14336,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baichuan/baichuan2-13b-chat"
   ],
   "intro_i18n": {
    "zh-CN": "Baichuan-13B 是百川推出的开源、可商用的 130 亿参数大语言模型，在权威中英文基准测试中取得同类模型中的最佳表现。",
    "zh-TW": "Baichuan-13B 是百川推出的開源、可商用的 130 億參數大型語言模型，在中文與英文權威基準測試中表現同級最佳。",
    "ja-JP": "Baichuan-13Bは、Baichuanが開発したオープンソースかつ商用利用可能な13BパラメータのLLMで、中国語および英語の権威あるベンチマークにおいて、同規模モデル中で最高クラスの性能を達成しています。",
    "ru-RU": "Baichuan-13B — это открытая, коммерчески пригодная LLM с 13 миллиардами параметров от Baichuan, демонстрирующая лучшие в своем классе результаты на авторитетных китайских и английских бенчмарках."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "baichuan/baichuan2-13b-chat"
    }
   ]
  },
  {
   "slug": "baichuan/Baichuan2-Turbo",
   "model_name": "Baichuan2-Turbo",
   "display_name": "Baichuan 2 Turbo",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "baichuan",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "通过搜索增强技术将模型与领域知识和网页知识连接，支持 PDF/Word 上传和 URL 输入，实现及时、全面的检索与专业、准确的输出。",
    "zh-TW": "透過搜尋增強技術，將模型與領域知識與網路資訊連結。支援 PDF/Word 上傳與網址輸入，實現即時、全面的檢索與專業、準確的輸出。",
    "ja-JP": "検索拡張を活用して、モデルをドメイン知識やウェブ知識と接続。PDF/WordのアップロードやURL入力に対応し、タイムリーで包括的な情報取得と専門的で正確な出力を実現します。",
    "ru-RU": "Использует расширение поиска для подключения модели к отраслевым и веб-знаниям. Поддерживает загрузку PDF/Word и ввод URL для своевременного, всестороннего поиска и профессионального, точного вывода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baichuan 2 Turbo"
    }
   ]
  },
  {
   "slug": "baichuan/Baichuan3-Turbo",
   "model_name": "Baichuan3-Turbo",
   "display_name": "Baichuan 3 Turbo",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "baichuan",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "provider_model_id": "baichuan3-turbo"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "released_at": "2024-02-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baichuan3-turbo"
   ],
   "intro_i18n": {
    "zh-CN": "专为高频企业场景优化，带来显著提升与高价值。相比 Baichuan2，内容创作提升 20%，知识问答提升 17%，角色扮演提升 40%。整体性能优于 GPT-3.5。",
    "zh-TW": "針對高頻企業場景進行優化，帶來顯著效能提升。相較於 Baichuan2，內容創作提升 20%，知識問答提升 17%，角色扮演提升 40%。整體表現優於 GPT-3.5。",
    "ja-JP": "頻度の高い企業シナリオに最適化され、大幅な性能向上と高い価値を提供します。Baichuan2と比較して、コンテンツ生成は20%、知識QAは17%、ロールプレイは40%向上。全体的な性能はGPT-3.5を上回ります。",
    "ru-RU": "Оптимизирована для частых корпоративных сценариев с существенным приростом ценности. По сравнению с Baichuan2, генерация контента улучшена на 20%, ответы на вопросы — на 17%, ролевые сценарии — на 40%. Общая производительность выше, чем у GPT-3.5."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baichuan 3 Turbo"
    }
   ]
  },
  {
   "slug": "baichuan/Baichuan3-Turbo-128k",
   "model_name": "Baichuan3-Turbo-128k",
   "display_name": "Baichuan 3 Turbo 128k",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "baichuan",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.4"
      }
     },
     "provider_model_id": "baichuan3-turbo-128k"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.8"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2025-08-08",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baichuan3-turbo-128k"
   ],
   "intro_i18n": {
    "zh-CN": "拥有 128K 超长上下文窗口，专为高频企业场景优化，带来显著提升与高价值。相比 Baichuan2，内容创作提升 20%，知识问答提升 17%，角色扮演提升 40%。整体性能优于 GPT-3.5。",
    "zh-TW": "具備 128K 超長上下文視窗，針對高頻企業場景進行優化，帶來顯著效能提升。相較於 Baichuan2，內容創作提升 20%，知識問答提升 17%，角色扮演提升 40%。整體表現優於 GPT-3.5。",
    "ja-JP": "128Kの超長文コンテキストウィンドウを備え、頻度の高い企業シナリオに最適化され、大幅な性能向上と高い価値を提供します。Baichuan2と比較して、コンテンツ生成は20%、知識QAは17%、ロールプレイは40%向上。全体的な性能はGPT-3.5を上回ります。",
    "ru-RU": "С ультрадлинным контекстным окном на 128K, оптимизирована для частых корпоративных сценариев с существенным приростом ценности. По сравнению с Baichuan2, генерация контента улучшена на 20%, ответы на вопросы — на 17%, ролевые сценарии — на 40%. Общая производительность выше, чем у GPT-3.5."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baichuan 3 Turbo 128k"
    }
   ]
  },
  {
   "slug": "baichuan/Baichuan4",
   "model_name": "Baichuan4",
   "display_name": "Baichuan 4",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "baichuan",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.3"
      }
     },
     "provider_model_id": "baichuan4"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "released_at": "2024-02-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baichuan4"
   ],
   "intro_i18n": {
    "zh-CN": "国内顶尖性能，在中文任务如百科知识、长文本处理和创意生成方面超越海外主流模型。具备行业领先的多模态能力，在权威评测中表现出色。",
    "zh-TW": "國內頂尖表現，在百科知識、長文本處理與創意生成等中文任務上超越主流海外模型。亦具備業界領先的多模態能力與強勁的基準測試成績。",
    "ja-JP": "中国国内で最高レベルの性能を持ち、百科事典的知識、長文生成、創造的生成などの中国語タスクで海外の主要モデルを上回ります。業界最先端のマルチモーダル機能と優れたベンチマーク結果も提供します。",
    "ru-RU": "Лидер по производительности среди отечественных моделей, превосходит ведущие зарубежные модели в задачах на китайском языке, таких как энциклопедические знания, длинные тексты и творческая генерация. Также предлагает передовые мультимодальные возможности и высокие результаты на бенчмарках."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baichuan 4"
    }
   ]
  },
  {
   "slug": "baichuan/Baichuan4-Air",
   "model_name": "Baichuan4-Air",
   "display_name": "Baichuan 4 Air",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "baichuan",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.144118"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.157"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.157"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-08-19",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "国内领先模型，在中文任务如知识问答、长文本处理和创意生成方面超越海外主流模型。具备行业领先的多模态能力，在权威评测中表现优异。",
    "zh-TW": "中國表現最強的模型之一，在知識問答、長文本處理與創意生成等中文任務上超越多個海外主流模型。具備業界領先的多模態能力，在權威基準測試中表現優異。",
    "ja-JP": "中国国内でトップクラスの性能を誇り、知識、長文生成、創造的生成などの中国語タスクで海外の主要モデルを上回ります。業界最先端のマルチモーダル機能も備え、権威あるベンチマークで高評価を獲得しています。",
    "ru-RU": "Одна из лучших моделей в Китае, превосходит ведущие зарубежные модели в задачах на китайском языке, таких как энциклопедические знания, длинные тексты и творческая генерация. Также обладает передовыми мультимодальными возможностями с высокими результатами на авторитетных бенчмарках."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baichuan 4 Air"
    }
   ]
  },
  {
   "slug": "baichuan/Baichuan4-Turbo",
   "model_name": "Baichuan4-Turbo",
   "display_name": "Baichuan 4 Turbo",
   "vendor": "baichuan",
   "pricing": [
    {
     "provider": "baichuan",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.42"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-08-19",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "国内领先模型，在中文任务如知识问答、长文本处理和创意生成方面超越海外主流模型。具备行业领先的多模态能力，在权威评测中表现优异。",
    "zh-TW": "中國表現最強的模型之一，在知識問答、長文本處理與創意生成等中文任務上超越多個海外主流模型。具備業界領先的多模態能力，在權威基準測試中表現優異。",
    "ja-JP": "中国国内でトップクラスの性能を誇り、知識、長文生成、創造的生成などの中国語タスクで海外の主要モデルを上回ります。業界最先端のマルチモーダル機能も備え、権威あるベンチマークで高評価を獲得しています。",
    "ru-RU": "Одна из лучших моделей в Китае, превосходит ведущие зарубежные модели в задачах на китайском языке, таких как энциклопедические знания, длинные тексты и творческая генерация. Также обладает передовыми мультимодальными возможностями с высокими результатами на авторитетных бенчмарках."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baichuan 4 Turbo"
    }
   ]
  },
  {
   "slug": "baidu/baidu-ernie-4-5-8k-preview",
   "model_name": "baidu-ernie-4-5-8k-preview",
   "display_name": "ernie-4.5-8k-preview",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-03-25",
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-4.5-8k-preview"
    }
   ]
  },
  {
   "slug": "baidu/baidu-ernie-4-5-turbo-128k",
   "model_name": "baidu-ernie-4-5-turbo-128k",
   "display_name": "ernie-4.5-turbo-128k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-4.5-turbo-128k"
    }
   ]
  },
  {
   "slug": "baidu/baidu-ernie-4-5-turbo-vl-32k",
   "model_name": "baidu-ernie-4-5-turbo-vl-32k",
   "display_name": "ernie-4.5-turbo-vl-32k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     }
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-4.5-turbo-vl-32k"
    }
   ]
  },
  {
   "slug": "baidu/baidu-ernie-4-8k",
   "model_name": "baidu-ernie-4-8k",
   "display_name": "ernie-4.0-8k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      }
     }
    }
   ],
   "released_at": "2024-02-01",
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-4.0-8k"
    }
   ]
  },
  {
   "slug": "baidu/baidu-ernie-4-turbo-128k",
   "model_name": "baidu-ernie-4-turbo-128k",
   "display_name": "ernie-4.0-turbo-128k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.6"
      }
     }
    }
   ],
   "released_at": "2025-08-08",
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-4.0-turbo-128k"
    }
   ]
  },
  {
   "slug": "baidu/baidu-ernie-4-turbo-8k",
   "model_name": "baidu-ernie-4-turbo-8k",
   "display_name": "ernie-4.0-turbo-8k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.6"
      }
     }
    }
   ],
   "released_at": "2024-06-28",
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-4.0-turbo-8k"
    }
   ]
  },
  {
   "slug": "baidu/baidu-ernie-5-0-thinking-latest",
   "model_name": "baidu-ernie-5-0-thinking-latest",
   "display_name": "ernie-5.0-thinking-latest",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.43"
      }
     }
    }
   ],
   "released_at": "2025-11-18",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-5.0-thinking-latest"
    }
   ]
  },
  {
   "slug": "baidu/baidu-ernie-5-0-thinking-preview",
   "model_name": "baidu-ernie-5-0-thinking-preview",
   "display_name": "ernie-5.0-thinking-preview",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.43"
      }
     }
    }
   ],
   "released_at": "2025-11-18",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-5.0-thinking-preview"
    }
   ]
  },
  {
   "slug": "baidu/baidu-ernie-x1-1-preview",
   "model_name": "baidu-ernie-x1-1-preview",
   "display_name": "ernie-x1.1-preview",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.142"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     }
    }
   ],
   "released_at": "2025-11-18",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-x1.1-preview"
    }
   ]
  },
  {
   "slug": "baidu/baidu-ernie-x1-turbo-32k",
   "model_name": "baidu-ernie-x1-turbo-32k",
   "display_name": "ernie-x1-turbo-32k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-x1-turbo-32k"
    }
   ]
  },
  {
   "slug": "baidu/cc-ernie-4.5-300b-a47b",
   "model_name": "cc-ernie-4.5-300b-a47b",
   "display_name": "cc-ernie-4.5-300b-a47b",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.28"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-ernie-4.5-300b-a47b"
    }
   ]
  },
  {
   "slug": "baidu/cobuddy",
   "model_name": "cobuddy",
   "display_name": "Baidu: CoBuddy (free)",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "baidu/cobuddy:free"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.13"
      }
     },
     "provider_model_id": "baidu/cobuddy"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "baidu/cobuddy:free"
    }
   ],
   "intro": "Free provider route for experiments, demos, and cost-sensitive chat workloads",
   "released_at": "2026-05-06",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/cobuddy",
    "baidu/cobuddy:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baidu: CoBuddy (free)"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-3.5-128K",
   "model_name": "ERNIE-3.5-128K",
   "display_name": "ERNIE 3.5 128K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "百度旗舰级大模型，基于海量中英文语料训练，具备强大的通用对话、创作和插件使用能力；支持自动集成百度搜索插件，提供最新答案。",
    "zh-TW": "百度旗艦級大模型，訓練於大規模中英文語料，具備強大通用能力，支援對話、創作與插件使用；可自動整合百度搜尋插件以提供即時答案。",
    "ja-JP": "Baidu のフラッグシップ大規模言語モデルで、中国語・英語の大規模コーパスで訓練され、チャット、創作、プラグイン利用において高い汎用性を発揮します。最新情報の取得に対応した Baidu 検索プラグインの自動統合をサポートします。",
    "ru-RU": "Флагманская LLM-модель от Baidu, обученная на обширных корпусах китайского и английского языков, обладающая высокой универсальностью для чата, создания контента и использования плагинов. Поддерживает автоматическую интеграцию плагина Baidu Search для получения актуальных ответов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 3.5 128K"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-3.5-8K",
   "model_name": "ERNIE-3.5-8K",
   "display_name": "ERNIE 3.5 8K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "百度旗舰级大模型，基于海量中英文语料训练，具备强大的通用对话、创作和插件使用能力；支持自动集成百度搜索插件，提供最新答案。",
    "zh-TW": "百度旗艦級大模型，訓練於大規模中英文語料，具備強大通用能力，支援對話、創作與插件使用；可自動整合百度搜尋插件以提供即時答案。",
    "ja-JP": "Baidu のフラッグシップ大規模言語モデルで、中国語・英語の大規模コーパスで訓練され、チャット、創作、プラグイン利用において高い汎用性を発揮します。最新情報の取得に対応した Baidu 検索プラグインの自動統合をサポートします。",
    "ru-RU": "Флагманская LLM-модель от Baidu, обученная на обширных корпусах китайского и английского языков, обладающая высокой универсальностью для чата, создания контента и использования плагинов. Поддерживает автоматическую интеграцию плагина Baidu Search для получения актуальных ответов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 3.5 8K"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-3.5-8K-Preview",
   "model_name": "ERNIE-3.5-8K-Preview",
   "display_name": "ERNIE 3.5 8K Preview",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "百度旗舰级大模型，基于海量中英文语料训练，具备强大的通用对话、创作和插件使用能力；支持自动集成百度搜索插件，提供最新答案。",
    "zh-TW": "百度旗艦級大模型，訓練於大規模中英文語料，具備強大通用能力，支援對話、創作與插件使用；可自動整合百度搜尋插件以提供即時答案。",
    "ja-JP": "Baidu のフラッグシップ大規模言語モデルで、中国語・英語の大規模コーパスで訓練され、チャット、創作、プラグイン利用において高い汎用性を発揮します。最新情報の取得に対応した Baidu 検索プラグインの自動統合をサポートします。",
    "ru-RU": "Флагманская LLM-модель от Baidu, обученная на обширных корпусах китайского и английского языков, обладающая высокой универсальностью для чата, создания контента и использования плагинов. Поддерживает автоматическую интеграцию плагина Baidu Search для получения актуальных ответов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 3.5 8K Preview"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4-5-vl-424b-a47b",
   "model_name": "ernie-4-5-vl-424b-a47b",
   "display_name": "ERNIE 4.5 VL 424B A47B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-424b-a47b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-424b-a47b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "ernie-4.5-vl-424b-a47b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-424b-a47b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-424b-a47b"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-06-30",
   "max_input_tokens": 123000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-03",
   "family": "ernie",
   "model_type": "vision_understanding",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ernie-4.5-vl-424b-a47b",
    "ernie-4.5-vl-424b-a47b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.5 VL 424B A47B"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-4.0-8K-Latest",
   "model_name": "ERNIE-4.0-8K-Latest",
   "display_name": "ERNIE 4.0 8K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.411765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.235294"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "百度旗舰级超大模型，全面升级自 ERNIE 3.5，适用于各领域复杂任务；支持百度搜索插件集成，提供实时答案。",
    "zh-TW": "百度旗艦級超大模型，全面升級自 ERNIE 3.5，適用於跨領域複雜任務；支援百度搜尋插件整合以提供即時答案。",
    "ja-JP": "ERNIE 3.5 を全面的にアップグレードした Baidu の超大規模フラッグシップモデルで、分野横断的な複雑なタスクに対応可能です。Baidu 検索プラグインの統合により、最新情報の取得が可能です。",
    "ru-RU": "Флагманская сверхмощная LLM-модель от Baidu с комплексными улучшениями по сравнению с ERNIE 3.5, подходящая для сложных задач в различных областях. Поддерживает интеграцию плагина Baidu Search для получения актуальных ответов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.0 8K"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-4.0-8K-Preview",
   "model_name": "ERNIE-4.0-8K-Preview",
   "display_name": "ERNIE 4.0 8K Preview",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.411765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.235294"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "百度旗舰级超大模型，全面升级自 ERNIE 3.5，适用于各领域复杂任务；支持百度搜索插件集成，提供实时答案。",
    "zh-TW": "百度旗艦級超大模型，全面升級自 ERNIE 3.5，適用於跨領域複雜任務；支援百度搜尋插件整合以提供即時答案。",
    "ja-JP": "ERNIE 3.5 を全面的にアップグレードした Baidu の超大規模フラッグシップモデルで、分野横断的な複雑なタスクに対応可能です。Baidu 検索プラグインの統合により、最新情報の取得が可能です。",
    "ru-RU": "Флагманская сверхмощная LLM-модель от Baidu с комплексными улучшениями по сравнению с ERNIE 3.5, подходящая для сложных задач в различных областях. Поддерживает интеграцию плагина Baidu Search для получения актуальных ответов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.0 8K Preview"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-4.0-Turbo-8K-Latest",
   "model_name": "ERNIE-4.0-Turbo-8K-Latest",
   "display_name": "ERNIE 4.0 Turbo 8K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.823529"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "百度旗舰级超大模型，综合性能强劲，适用于复杂任务，集成百度搜索插件，提供实时答案。性能优于 ERNIE 4.0。",
    "zh-TW": "百度旗艦級超大模型，整體表現強勁，適用於複雜任務，支援百度搜尋插件整合以提供即時答案。表現優於 ERNIE 4.0。",
    "ja-JP": "ERNIE 4.0 を上回る性能を持つ、Baidu の超大規模フラッグシップモデルで、複雑なタスクにおいて高い総合性能を発揮します。Baidu 検索プラグインの統合により、最新情報の取得が可能です。",
    "ru-RU": "Флагманская сверхмощная LLM-модель от Baidu с высокой общей производительностью для сложных задач. Поддерживает интеграцию плагина Baidu Search для получения актуальных ответов. Превосходит ERNIE 4.0."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.0 Turbo 8K"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-4.0-Turbo-8K-Preview",
   "model_name": "ERNIE-4.0-Turbo-8K-Preview",
   "display_name": "ERNIE 4.0 Turbo 8K Preview",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.823529"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "百度旗舰级超大模型，综合性能强劲，适用于复杂任务，集成百度搜索插件，提供实时答案。性能优于 ERNIE 4.0。",
    "zh-TW": "百度旗艦級超大模型，整體表現強勁，適用於複雜任務，支援百度搜尋插件整合以提供即時答案。表現優於 ERNIE 4.0。",
    "ja-JP": "ERNIE 4.0 を上回る性能を持つ、Baidu の超大規模フラッグシップモデルで、複雑なタスクにおいて高い総合性能を発揮します。Baidu 検索プラグインの統合により、最新情報の取得が可能です。",
    "ru-RU": "Флагманская сверхмощная LLM-модель от Baidu с высокой общей производительностью для сложных задач. Поддерживает интеграцию плагина Baidu Search для получения актуальных ответов. Превосходит ERNIE 4.0."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.0 Turbo 8K Preview"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5",
   "model_name": "ernie-4.5",
   "display_name": "ernie-4.5",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.272"
      }
     }
    }
   ],
   "max_input_tokens": 160000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-4.5"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-0.3b",
   "model_name": "ernie-4.5-0.3b",
   "display_name": "ERNIE 4.5 0.3B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0136"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0544"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.014706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE 4.5 0.3B 是一款开源轻量级模型，适用于本地和定制化部署。",
    "zh-TW": "ERNIE 4.5 0.3B 是一款開源輕量級模型，適合本地與客製化部署。",
    "ja-JP": "ERNIE 4.5 0.3B は、ローカルおよびカスタマイズ展開に適した軽量なオープンソースモデルです。",
    "ru-RU": "ERNIE 4.5 0.3B — легковесная модель с открытым исходным кодом для локального и кастомизированного развертывания."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.5 0.3B"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-21B-a3b",
   "model_name": "ernie-4.5-21B-a3b",
   "display_name": "ERNIE 4.5 21B A3B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-21b-a3b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-21B-a3b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-21B-a3b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-21b-a3b"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-06-30",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 120000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ernie",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ernie-4.5-21B-a3b",
    "baidu/ernie-4.5-21b-a3b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.5 21B A3B"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-21B-a3b-thingking",
   "model_name": "ernie-4.5-21B-a3b-thingking",
   "display_name": "ERNIE 4.5 21B A3B Thinking",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-21B-a3b-thingking"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ernie-4.5-21B-a3b-thingking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.5 21B A3B Thinking"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-21B-A3B-Thinking",
   "model_name": "ernie-4.5-21B-A3B-Thinking",
   "display_name": "ERNIE-4.5-21B-A3B-Thinking",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "ernie-4.5-21b-a3b-thinking"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-21b-a3b-thinking"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "ernie-4.5-21B-a3b-thinking"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-21B-a3b-thinking"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-21b-a3b-thinking"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-09-19",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ernie",
   "capabilities": {
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ernie-4.5-21B-A3B-Thinking",
    "baidu/ernie-4.5-21B-a3b-thinking",
    "baidu/ernie-4.5-21b-a3b-thinking",
    "ernie-4.5-21B-a3b-thinking",
    "ernie-4.5-21b-a3b-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE-4.5-21B-A3B-Thinking"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-4.5-300B-A47B",
   "model_name": "ERNIE-4.5-300B-A47B",
   "display_name": "baidu/ERNIE-4.5-300B-A47B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.28"
      }
     },
     "provider_model_id": "baidu/ERNIE-4.5-300B-A47B"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-300b-a47b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-300b-a47b"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "baidu/ERNIE-4.5-300B-A47B"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "baidu/ERNIE-4.5-300B-A47B"
    }
   ],
   "intro": "Tool-capable chat model for instruction following and agentic application workflows",
   "released_at": "2025-07-02",
   "max_input_tokens": 131000,
   "max_output_tokens": 131000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ernie",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ERNIE-4.5-300B-A47B",
    "baidu/ernie-4.5-300b-a47b",
    "ernie-4.5-300b-a47b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "baidu/ERNIE-4.5-300B-A47B"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-300b-a47b-paddle",
   "model_name": "ernie-4.5-300b-a47b-paddle",
   "display_name": "ERNIE 4.5 300B A47B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-300b-a47b-paddle"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-300b-a47b-paddle"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-300b-a47b-paddle"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "novita/baidu/ernie-4.5-300b-a47b-paddle"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-06-30",
   "max_input_tokens": 123000,
   "max_output_tokens": 12000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "family": "ernie",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ernie-4.5-300b-a47b-paddle",
    "novita/baidu/ernie-4.5-300b-a47b-paddle"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.5 300B A47B"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-8k-preview",
   "model_name": "ernie-4.5-8k-preview",
   "display_name": "Ernie 4.5 8k Preview",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-03-25",
   "max_input_tokens": 8000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE 4.5 8K Preview 是一款用于评估 ERNIE 4.5 的 8K 上下文预览模型。",
    "zh-TW": "ERNIE 4.5 8K Preview 是一款 8K 上下文預覽模型，用於評估 ERNIE 4.5。",
    "ja-JP": "ERNIE 4.5 8K Preview は、ERNIE 4.5 の評価用に設計された 8K コンテキストプレビューモデルです。",
    "ru-RU": "ERNIE 4.5 8K Preview — модель с контекстом 8K для предварительной оценки возможностей ERNIE 4.5."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ernie 4.5 8k Preview"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-turbo-128k",
   "model_name": "ernie-4.5-turbo-128k",
   "display_name": "Ernie 4.5 Turbo 128k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE 4.5 Turbo 128K 是一款高性能通用模型，支持搜索增强与工具调用，适用于问答、编程与代理场景。",
    "zh-TW": "ERNIE 4.5 Turbo 128K 是一款高效能通用模型，支援搜尋增強與工具調用，適用於問答、程式設計與代理場景。",
    "ja-JP": "ERNIE 4.5 Turbo 128K は、検索補強とツール呼び出しを備えた高性能な汎用モデルであり、質問応答、コーディング、エージェントシナリオに適しています。",
    "ru-RU": "ERNIE 4.5 Turbo 128K — высокопроизводительная универсальная модель с поддержкой поиска и вызова инструментов для задач Вопрос-Ответ, программирования и агентов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ernie 4.5 Turbo 128k"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-turbo-128k-preview",
   "model_name": "ernie-4.5-turbo-128k-preview",
   "display_name": "ernie-4.5-turbo-128k-preview",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.108"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.432"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-4.5-turbo-128k-preview"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-turbo-20260402",
   "model_name": "ernie-4.5-turbo-20260402",
   "display_name": "ERNIE 4.5 Turbo 20260402",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117705056"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.470820224"
      }
     },
     "provider_model_id": "ERNIE-4.5-Turbo"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 12288,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "released_at": "2025-06-17",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ERNIE-4.5-Turbo"
   ],
   "intro_i18n": {
    "zh-CN": "ERNIE 4.5 Turbo 20260402 是一款高性能通用模型，支持搜索增强和工具调用，适用于问答、编程和代理场景。",
    "zh-TW": "ERNIE 4.5 Turbo 20260402 是一款高性能通用模型，支持搜索增強和工具調用，用於問答、編程和代理場景。",
    "ja-JP": "ERNIE 4.5 Turbo 20260402は、QA、コーディング、エージェントシナリオ向けの検索拡張とツール呼び出しを備えた高性能な汎用モデルです。",
    "ru-RU": "ERNIE 4.5 Turbo 20260402 — это высокопроизводительная универсальная модель с дополнением поиска и вызовом инструментов для QA, программирования и агентных сценариев."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471045376",
     "new": "0.470820224"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.117761344",
     "new": "0.117705056"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471372608",
     "new": "0.471045376"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.117843152",
     "new": "0.117761344"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471869504",
     "new": "0.471372608"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.117967376",
     "new": "0.117843152"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471965856",
     "new": "0.471869504"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.117991464",
     "new": "0.117967376"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471798784",
     "new": "0.471965856"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.117949696",
     "new": "0.117991464"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.47097264",
     "new": "0.471798784"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.11774316",
     "new": "0.117949696"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.5 Turbo 20260402"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-turbo-32k",
   "model_name": "ernie-4.5-turbo-32k",
   "display_name": "ERNIE 4.5 Turbo 32K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 12288,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE 4.5 Turbo 32K 是一款中等长度上下文版本，适用于问答、知识库检索与多轮对话。",
    "zh-TW": "ERNIE 4.5 Turbo 32K 是中長上下文版本，適用於問答、知識庫檢索與多輪對話。",
    "ja-JP": "ERNIE 4.5 Turbo 32K は、中程度の長さのコンテキストに対応し、質問応答、ナレッジベース検索、マルチターン対話に適しています。",
    "ru-RU": "ERNIE 4.5 Turbo 32K — версия со средним контекстом для Вопрос-Ответ, поиска в базе знаний и многотурового диалога."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.5 Turbo 32K"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-turbo-latest",
   "model_name": "ernie-4.5-turbo-latest",
   "display_name": "ERNIE 4.5 Turbo Latest",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 12288,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "最新 ERNIE 4.5 Turbo，整体性能优化，适合作为主力生产模型。",
    "zh-TW": "最新 ERNIE 4.5 Turbo，整體效能優化，適合作為主要生產模型。",
    "ja-JP": "最新の ERNIE 4.5 Turbo は、全体的な性能が最適化されており、主要な本番モデルとして理想的です。",
    "ru-RU": "Актуальная версия ERNIE 4.5 Turbo с оптимизированной общей производительностью, идеально подходит в качестве основной модели для продакшена."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.5 Turbo Latest"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-4.5-Turbo-VL",
   "model_name": "ERNIE-4.5-Turbo-VL",
   "display_name": "ERNIE 4.5 Turbo VL",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "ernie-4.5-turbo-vl"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.44139396"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32418188"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      }
     },
     "provider_model_id": "ernie-4.5-turbo-vl"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "released_at": "2025-06-17",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ernie-4.5-turbo-vl"
   ],
   "intro_i18n": {
    "zh-CN": "ERNIE 4.5 Turbo VL 是一款成熟的多模态模型，适用于生产级图文理解与识别。",
    "zh-TW": "ERNIE 4.5 Turbo VL 是一款成熟的多模態模型，適用於生產級圖文理解與識別。",
    "ja-JP": "ERNIE 4.5 Turbo VL は、本番環境での画像とテキストの理解および認識に適した成熟したマルチモーダルモデルです。",
    "ru-RU": "ERNIE 4.5 Turbo VL — зрелая мультимодальная модель для промышленного понимания и распознавания изображений и текста."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.32481512",
     "new": "1.32418188"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.44160504",
     "new": "0.44139396"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.32573546",
     "new": "1.32481512"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.44191182",
     "new": "0.44160504"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.32713298",
     "new": "1.32573546"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.44237766",
     "new": "0.44191182"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.32740397",
     "new": "1.32713298"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.44246799",
     "new": "0.44237766"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.32693408",
     "new": "1.32740397"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.44231136",
     "new": "0.44246799"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.32461055",
     "new": "1.32693408"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.44153685",
     "new": "0.44231136"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.5 Turbo VL"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-turbo-vl-32k",
   "model_name": "ernie-4.5-turbo-vl-32k",
   "display_name": "Ernie 4.5 Turbo VL 32k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.495"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.43"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-08",
   "max_input_tokens": 32000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE 4.5 Turbo VL 32K 是一款中长上下文多模态模型，适用于长文档与图像联合理解。",
    "zh-TW": "ERNIE 4.5 Turbo VL 32K 是中長上下文多模態版本，適用於長文檔與圖像理解。",
    "ja-JP": "ERNIE 4.5 Turbo VL 32K は、長文と画像の理解を組み合わせた中長距離マルチモーダルモデルです。",
    "ru-RU": "ERNIE 4.5 Turbo VL 32K — мультимодальная модель со средне-длинным контекстом для понимания длинных документов и изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ernie 4.5 Turbo VL 32k"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-turbo-vl-latest",
   "model_name": "ernie-4.5-turbo-vl-latest",
   "display_name": "ERNIE 4.5 Turbo VL Latest",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.110294"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE 4.5 Turbo VL 最新版，图文理解与推理能力进一步提升。",
    "zh-TW": "ERNIE 4.5 Turbo VL 最新版，圖文理解與推理能力提升。",
    "ja-JP": "ERNIE 4.5 Turbo VL Latest は、画像とテキストの理解および推論を強化した最新のマルチモーダルモデルです。",
    "ru-RU": "ERNIE 4.5 Turbo VL Latest — новейшая мультимодальная модель с улучшенным пониманием изображений и текста, а также рассуждением."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 4.5 Turbo VL Latest"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-vl-28b-a3b",
   "model_name": "ernie-4.5-vl-28b-a3b",
   "display_name": "ERNIE 4.5 VL 28B A3B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-28b-a3b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13999999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5599999999999999"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-28b-a3b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-28b-a3b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-28b-a3b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-28b-a3b"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-06-30",
   "max_input_tokens": 30000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "family": "ernie",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ernie-4.5-vl-28b-a3b"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "ERNIE 4.5 VL 28B A3B"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4.5-vl-28b-a3b-thinking",
   "model_name": "ernie-4.5-vl-28b-a3b-thinking",
   "display_name": "ERNIE-4.5-VL-28B-A3B-Thinking",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-28b-a3b-thinking"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     },
     "provider_model_id": "baidu/ernie-4.5-vl-28b-a3b-thinking"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-11-26",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ernie-4.5-vl-28b-a3b-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE-4.5-VL-28B-A3B-Thinking"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-4.5-VL-424B-A47B-Base-PT",
   "model_name": "ERNIE-4.5-VL-424B-A47B-Base-PT",
   "display_name": "baidu/ERNIE-4.5-VL-424B-A47B-Base-PT",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "baidu/ERNIE-4.5-VL-424B-A47B-Base-PT"
    }
   ],
   "released_at": "2025-06-28",
   "max_input_tokens": 123000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ERNIE-4.5-VL-424B-A47B-Base-PT"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "baidu/ERNIE-4.5-VL-424B-A47B-Base-PT"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4p5-21b-a3b-pt",
   "model_name": "ernie-4p5-21b-a3b-pt",
   "display_name": "ERNIE-4.5-21B-A3B-PT",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/ernie-4p5-21b-a3b-pt"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/ernie-4p5-21b-a3b-pt"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE-4.5-21B-A3B-PT"
    }
   ]
  },
  {
   "slug": "baidu/ernie-4p5-300b-a47b-pt",
   "model_name": "ernie-4p5-300b-a47b-pt",
   "display_name": "ERNIE-4.5-300B-A47B-PT",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/ernie-4p5-300b-a47b-pt"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/ernie-4p5-300b-a47b-pt"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE-4.5-300B-A47B-PT"
    }
   ]
  },
  {
   "slug": "baidu/ernie-5.0",
   "model_name": "ernie-5.0",
   "display_name": "ERNIE 5.0",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.82192"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.28768"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "5.882353"
      }
     }
    }
   ],
   "released_at": "2026-03-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE 5.0 是 ERNIE 系列的新一代原生多模态大模型。通过统一多模态建模方法，对文本、图像、音频和视频进行联合建模，提供全面的多模态能力。其基础能力全面升级，在多项基准测试中取得强劲表现，尤其在多模态理解、指令跟随、创意写作、事实准确性、Agent 规划和工具调用方面表现突出。",
    "zh-TW": "ERNIE 5.0 是 ERNIE 系列新世代模型，屬於原生多模態大型模型。採用統一多模態建模方法，可同時建模文本、圖片、音訊與影片，具備全面的多模態能力。基礎能力大幅升級，在基準測試中表現亮眼，特別擅長多模態理解、指令遵循、創作寫作、事實準確性、代理規劃與工具使用。",
    "ja-JP": "ERNIE 5.0は、ERNIEシリーズの新世代モデルで、ネイティブにマルチモーダルな大規模モデルです。統一されたマルチモーダルモデリングアプローチを採用し、テキスト、画像、音声、動画を共同でモデリングして包括的なマルチモーダル能力を提供します。その基盤能力は大幅に向上し、ベンチマーク評価で優れた性能を達成しています。特にマルチモーダル理解、指示の追従、創造的な執筆、事実の正確性、エージェント計画、ツール利用において優れています。",
    "ru-RU": "ERNIE 5.0 — модель нового поколения в серии ERNIE, являющаяся изначально мультимодальной. Она использует унифицированный подход к моделированию текста, изображений, аудио и видео, обеспечивая комплексные мультимодальные возможности. Базовые способности значительно улучшены, модель демонстрирует высокие результаты в бенчмарках. Особенно сильна в мультимодальном понимании, следовании инструкциям, творческом письме, фактической точности, планировании и использовании инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 5.0"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-5.0-Thinking",
   "model_name": "ERNIE-5.0-Thinking",
   "display_name": "ERNIE-5.0-Thinking",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.35410112"
      }
     }
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35522688",
     "new": "2.35410112"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35686304",
     "new": "2.35522688"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35934752",
     "new": "2.35686304"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35982928",
     "new": "2.35934752"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35899392",
     "new": "2.35982928"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.3548632",
     "new": "2.35899392"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE-5.0-Thinking"
    }
   ]
  },
  {
   "slug": "baidu/ernie-5.0-thinking-exp",
   "model_name": "ernie-5.0-thinking-exp",
   "display_name": "ernie-5.0-thinking-exp",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.82192"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.28768"
      }
     }
    }
   ],
   "max_input_tokens": 119000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-5.0-thinking-exp"
    }
   ]
  },
  {
   "slug": "baidu/ernie-5.0-thinking-latest",
   "model_name": "ernie-5.0-thinking-latest",
   "display_name": "ERNIE 5.0 Thinking",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "5.882353"
      }
     }
    }
   ],
   "released_at": "2025-11-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "文心 5.0 Thinking 是一款原生全模态旗舰模型，统一建模文本、图像、音频与视频，在复杂问答、创作与智能体场景中实现全面能力升级。",
    "zh-TW": "文心 5.0 思考版是一款原生全模態旗艦模型，整合文字、圖像、音訊與影片建模，全面升級複雜問答、創作與智能體場景的能力。",
    "ja-JP": "文心 5.0 Thinking は、テキスト、画像、音声、動画を統合的に扱うネイティブなフルモーダルフラッグシップモデルであり、複雑な質問応答、創作、エージェントシナリオにおいて大幅な能力向上を実現します。",
    "ru-RU": "Wenxin 5.0 Thinking — флагманская модель с нативной полной мультимодальностью, объединяющая текст, изображение, аудио и видео. Обеспечивает широкие улучшения для сложных задач Вопрос-Ответ, творчества и агентов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 5.0 Thinking"
    }
   ]
  },
  {
   "slug": "baidu/ernie-5.0-thinking-preview",
   "model_name": "ernie-5.0-thinking-preview",
   "display_name": "ERNIE 5.0",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.822"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.288"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "5.882353"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.84"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.37"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "0.6"
      }
     },
     "provider_model_id": "baidu/ernie-5.0-thinking-preview",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.667656",
        "prompt": "1.678571"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-01-22",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ernie-5.0-thinking-preview"
   ],
   "intro_i18n": {
    "zh-CN": "ERNIE 5.0 思维预览版是百度下一代原生多模态 ERNIE 模型，擅长多模态理解、指令跟随、创作、事实问答和工具调用。",
    "zh-TW": "ERNIE 5.0 Thinking Preview 是百度新一代原生多模態 ERNIE 模型，擅長多模態理解、指令遵循、創作、事實問答與工具調用。",
    "ja-JP": "ERNIE 5.0 Thinking Previewは、Baiduの次世代ネイティブマルチモーダルERNIEモデルで、マルチモーダル理解、指示追従、創造、事実に基づくQ&A、ツール呼び出しに優れています。",
    "ru-RU": "ERNIE 5.0 Thinking Preview — это модель нового поколения от Baidu с нативной мультимодальностью, обладающая сильными возможностями в понимании мультимодальных данных, следовании инструкциям, создании контента, фактическом вопросо-ответе и использовании инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 5.0"
    }
   ]
  },
  {
   "slug": "baidu/ernie-5.1:thinking",
   "model_name": "ernie-5.1:thinking",
   "display_name": "ERNIE 5.1",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5634"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5353"
      }
     },
     "provider_model_id": "ernie-5.1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "ernie-5.1"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      }
     },
     "provider_model_id": "ernie-5.1"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.910668662"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.424593036"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "0.4332582"
      }
     },
     "provider_model_id": "baidu/ernie-5.1",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.2226",
        "prompt": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-10",
   "max_input_tokens": 119000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ernie-5.1",
    "ernie-5.1"
   ],
   "intro_i18n": {
    "zh-CN": "ERNIE 5.1 是 ERNIE 系列的最新模型，其基础能力全面升级。在代理、知识处理、推理和深度搜索等领域表现出显著改进。本次发布采用了解耦的全异步强化学习架构，专为解决大模型向自主代理决策演进中的关键挑战而设计，包括训练与推理数值差异、异构计算资源利用率低以及长尾效应引发的全局问题。此外，还采用了大规模代理后训练技术，进一步增强了模型的能力和泛化性能。通过环境、专家和融合过程的三阶段协作框架，这种方法不仅确保了训练效率，还显著提升了模型在复杂任务中的稳定性和表现。",
    "zh-TW": "ERNIE 5.1 是 ERNIE 系列的最新模型，基礎能力全面升級。在代理、知識處理、推理和深度搜索等領域展現了顯著的改進。本次版本採用了解耦的全異步強化學習架構，專門針對大型模型向自主代理決策演進過程中的關鍵挑戰進行設計，包括訓練與推理數值差異、異構計算資源利用率低以及由長尾效應引發的全局問題。此外，還採用了大規模代理後訓練技術，進一步提升模型的能力和泛化性能。通過環境、專家和融合三階段協作框架，此方法不僅確保了訓練效率，還顯著提升了模型在複雜任務中的穩定性和表現。",
    "ja-JP": "ERNIE 5.1は、ERNIEシリーズの最新モデルで、基盤能力に大幅なアップグレードが施されています。エージェント、知識処理、推論、深層検索などの分野で顕著な改善を示しています。このリリースでは、完全非同期型の強化学習アーキテクチャを採用し、大規模モデルの自律エージェント意思決定への進化における主要な課題（トレーニングと推論の数値的不一致、異種計算リソースの低利用率、ロングテール効果によるグローバルな問題）に対応しています。さらに、大規模エージェントのポストトレーニング技術を活用し、モデルの能力と一般化性能をさらに向上させています。環境、専門家、融合プロセスを含む三段階の協調フレームワークを通じて、このアプローチはトレーニング効率を確保するだけでなく、複雑なタスクにおけるモデルの安定性とパフォーマンスを大幅に向上させます。",
    "ru-RU": "ERNIE 5.1 — последняя модель серии ERNIE, с комплексными улучшениями базовых возможностей. Она демонстрирует значительные улучшения в таких областях, как агенты, обработка знаний, рассуждение и глубокий поиск. В этом выпуске используется раздельная полностью асинхронная архитектура обучения с подкреплением, специально разработанная для решения ключевых задач в эволюции больших моделей к автономному принятию решений агентами, включая числовые несоответствия между обучением и выводом, низкую эффективность использования гетерогенных вычислительных ресурсов и глобальные проблемы, вызванные эффектами длинного хвоста. Кроме того, применяются методы крупномасштабного пост-обучения агентов для дальнейшего повышения возможностей модели и её способности к обобщению. Благодаря трехэтапной совместной структуре, включающей процессы окружающей среды, экспертов и слияния, подход не только обеспечивает эффективность обучения, но и значительно улучшает стабильность и производительность модели при выполнении сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE 5.1"
    }
   ]
  },
  {
   "slug": "baidu/ernie-char-fiction-8k",
   "model_name": "ernie-char-fiction-8k",
   "display_name": "ERNIE Character Fiction 8K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE Character Fiction 8K 是一款面向小说与情节创作的角色模型，适合长篇故事生成。",
    "zh-TW": "ERNIE 角色小說 8K 是一款面向小說與情節創作的角色模型，適合長篇故事生成。",
    "ja-JP": "ERNIE Character Fiction 8K は、小説やプロット創作に適した人格モデルであり、長編ストーリー生成に最適です。",
    "ru-RU": "ERNIE Character Fiction 8K — модель персонажа для написания романов и создания сюжетов, подходит для генерации длинных историй."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE Character Fiction 8K"
    }
   ]
  },
  {
   "slug": "baidu/ernie-char-fiction-8k-preview",
   "model_name": "ernie-char-fiction-8k-preview",
   "display_name": "ERNIE Character Fiction 8K Preview",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE Character Fiction 8K 预览版是一款用于角色与情节创作的模型预览，适用于功能评估与测试。",
    "zh-TW": "ERNIE 角色小說 8K 預覽版是一款面向角色與情節創作的模型預覽，用於功能評估與測試。",
    "ja-JP": "ERNIE Character Fiction 8K Preview は、キャラクターとプロットの創作に対応したモデルのプレビュー版であり、機能評価とテストに適しています。",
    "ru-RU": "ERNIE Character Fiction 8K Preview — предварительная модель для создания персонажей и сюжетов, предназначенная для оценки и тестирования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE Character Fiction 8K Preview"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-Character-8K",
   "model_name": "ERNIE-Character-8K",
   "display_name": "ERNIE Character 8K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "百度面向游戏 NPC、客服和角色扮演的垂直领域大模型，具备更清晰的人设一致性、更强的指令理解能力和更优的推理能力。",
    "zh-TW": "百度面向遊戲 NPC、客服與角色扮演的垂直領域大模型，具備更清晰的人設一致性、更強的指令遵循能力與推理能力。",
    "ja-JP": "ゲームNPC、カスタマーサービス、ロールプレイ向けに最適化された Baidu のドメイン特化型 LLM で、キャラクターの一貫性、指示の理解、推論能力が強化されています。",
    "ru-RU": "Отраслевая LLM-модель от Baidu для игровых NPC, клиентской поддержки и ролевых сценариев. Обеспечивает более четкое соответствие персонажу, лучшее следование инструкциям и улучшенное логическое мышление."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE Character 8K"
    }
   ]
  },
  {
   "slug": "baidu/ernie-image-turbo",
   "model_name": "ernie-image-turbo",
   "display_name": "ERNIE Image Turbo",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.016176"
      }
     }
    }
   ],
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE-Image 是百度推出的 80 亿参数文生图模型，在多项评测中名列前茅，在中国 SuperCLUE 上并列第一，并在开源赛道保持领先。",
    "zh-TW": "ERNIE-Image 是百度推出的 80 億參數文生圖模型，在多項基準測試中名列前茅，在中國 SuperCLUE 中獲得並列第一，並在開源賽道領先。",
    "ja-JP": "ERNIE-Imageは、Baiduが開発した8Bパラメータのテキストから画像への生成モデルです。複数のベンチマークでトップにランクインしており、中国のSuperCLUEで同率1位を達成し、オープンソーストラックでリードしています。",
    "ru-RU": "ERNIE-Image — 8-миллиардная текст‑в‑изображение модель, разработанная Baidu. Она входит в число лучших по многим бенчмаркам, занимая первое место в SuperCLUE в Китае и лидируя в категории открытых моделей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE Image Turbo"
    }
   ]
  },
  {
   "slug": "baidu/ernie-irag-edit",
   "model_name": "ernie-irag-edit",
   "display_name": "ERNIE iRAG Edit",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.020588"
      }
     }
    }
   ],
   "released_at": "2025-04-17",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE iRAG Edit 是一款图像编辑模型，支持擦除、重绘与变体生成。",
    "zh-TW": "ERNIE iRAG Edit 是一款支援擦除、重繪與變體生成的圖像編輯模型。",
    "ja-JP": "ERNIE iRAG Edit は、消去、再描画、バリエーション生成に対応した画像編集モデルです。",
    "ru-RU": "ERNIE iRAG Edit — модель редактирования изображений с поддержкой стирания, перерисовки и генерации вариантов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE iRAG Edit"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-Lite-Pro-128K",
   "model_name": "ERNIE-Lite-Pro-128K",
   "display_name": "ERNIE Lite Pro 128K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      }
     },
     "provider_model_id": "ernie-lite-pro-128k"
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "max_output_tokens": 4096,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ernie-lite-pro-128k"
   ],
   "intro_i18n": {
    "zh-CN": "百度轻量级大模型，在质量与推理性能之间取得平衡，优于 ERNIE Lite，适用于低算力加速器。",
    "zh-TW": "百度輕量級大模型，在品質與推理效能間取得平衡，優於 ERNIE Lite，適用於低算力加速器。",
    "ja-JP": "Baidu の軽量 LLM で、品質と推論性能のバランスに優れ、ERNIE Lite よりも高性能で、低計算リソース環境に適しています。",
    "ru-RU": "Легковесная LLM-модель от Baidu, сочетающая качество и производительность вывода. Превосходит ERNIE Lite и подходит для ускорителей с низким уровнем вычислений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE Lite Pro 128K"
    }
   ]
  },
  {
   "slug": "baidu/ernie-novel-8k",
   "model_name": "ernie-novel-8k",
   "display_name": "ERNIE Novel 8K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.882353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17.647059"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE Novel 8K 专为长篇小说与 IP 剧情创作打造，支持多角色叙事。",
    "zh-TW": "ERNIE 小說 8K 專為長篇小說與 IP 情節創作打造，支援多角色敘事。",
    "ja-JP": "ERNIE Novel 8K は、複数キャラクターによる長編小説や IP プロットの生成に特化しています。",
    "ru-RU": "ERNIE Novel 8K предназначена для написания длинных романов и IP-сюжетов с участием нескольких персонажей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE Novel 8K"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-Speed-128K",
   "model_name": "ERNIE-Speed-128K",
   "display_name": "ERNIE Speed 128K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "百度最新高性能大模型（2024），具备强大的通用能力，适合作为微调基础模型，适应特定场景，推理能力出色。",
    "zh-TW": "百度最新高效能大模型（2024），具備強大通用能力，適合作為微調基礎模型，推理表現優異。",
    "ja-JP": "Baidu の最新高性能 LLM（2024年版）で、汎用性が高く、特定シナリオに対応するファインチューニングのベースとして最適です。優れた推論性能を備えています。",
    "ru-RU": "Последняя высокопроизводительная LLM-модель от Baidu (2024), обладающая сильными универсальными способностями. Подходит в качестве основы для дообучения под конкретные сценарии, с отличной логикой рассуждений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE Speed 128K"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-Speed-Pro-128K",
   "model_name": "ERNIE-Speed-Pro-128K",
   "display_name": "ERNIE Speed Pro 128K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      }
     },
     "provider_model_id": "ernie-speed-pro-128k"
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {},
   "max_output_tokens": 4096,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ernie-speed-pro-128k"
   ],
   "intro_i18n": {
    "zh-CN": "百度最新高性能大模型（2024），具备强大的通用能力，优于 ERNIE Speed，适合作为微调基础模型，推理能力出色。",
    "zh-TW": "百度最新高效能大模型（2024），具備強大通用能力，優於 ERNIE Speed，適合作為微調基礎模型，推理表現優異。",
    "ja-JP": "Baidu の最新高性能 LLM（2024年版）で、汎用性が高く、ERNIE Speed よりも高性能です。特定シナリオに対応するファインチューニングのベースとして最適で、優れた推論性能を備えています。",
    "ru-RU": "Последняя высокопроизводительная LLM-модель от Baidu (2024), обладающая сильными универсальными способностями. Превосходит ERNIE Speed и подходит в качестве основы для дообучения с отличной логикой рассуждений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE Speed Pro 128K"
    }
   ]
  },
  {
   "slug": "baidu/ernie-x1-32k",
   "model_name": "ernie-x1-32k",
   "display_name": "Ernie X1 32k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-08",
   "max_input_tokens": 32000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ernie X1 32k"
    }
   ]
  },
  {
   "slug": "baidu/ernie-x1-32k-preview",
   "model_name": "ernie-x1-32k-preview",
   "display_name": "Ernie X1 32k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-04-03",
   "max_input_tokens": 32000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ernie X1 32k"
    }
   ]
  },
  {
   "slug": "baidu/ERNIE-X1-Turbo",
   "model_name": "ERNIE-X1-Turbo",
   "display_name": "ernie-x1-turbo",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.136"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.544"
      }
     },
     "provider_model_id": "ernie-x1-turbo"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14713132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      }
     }
    }
   ],
   "max_input_tokens": 50500,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "released_at": "2025-06-17",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ernie-x1-turbo"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14720168",
     "new": "0.14713132"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14730394",
     "new": "0.14720168"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14745922",
     "new": "0.14730394"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14748933",
     "new": "0.14745922"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14743712",
     "new": "0.14748933"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14717895",
     "new": "0.14743712"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ernie-x1-turbo"
    }
   ]
  },
  {
   "slug": "baidu/ernie-x1-turbo-32k",
   "model_name": "ernie-x1-turbo-32k",
   "display_name": "Ernie X1 Turbo 32k",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.165"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-08",
   "max_input_tokens": 32000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE X1 Turbo 32K 是一款快速思考模型，具备 32K 上下文能力，适合复杂推理与多轮对话。",
    "zh-TW": "ERNIE X1 Turbo 32K 是一款快速思考模型，具備 32K 上下文，適合複雜推理與多輪對話。",
    "ja-JP": "ERNIE X1 Turbo 32K は、複雑な推論やマルチターン対話に対応した 32K コンテキストの高速思考モデルです。",
    "ru-RU": "ERNIE X1 Turbo 32K — быстрая модель мышления с контекстом 32K для сложного рассуждения и многотурового общения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ernie X1 Turbo 32k"
    }
   ]
  },
  {
   "slug": "baidu/ernie-x1-turbo-32k-preview",
   "model_name": "ernie-x1-turbo-32k-preview",
   "display_name": "ERNIE X1 Turbo 32K Preview",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 28160,
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE X1 Turbo 32K Preview是一个快速思维模型，支持32K上下文，用于复杂推理和多轮对话。",
    "zh-TW": "ERNIE X1 Turbo 32K Preview 是一個快速思考模型，支持 32K 上下文，用於複雜推理和多輪對話。",
    "ja-JP": "ERNIE X1 Turbo 32K Previewは、複雑な推論とマルチターンチャットに対応する高速思考モデルです。",
    "ru-RU": "ERNIE X1 Turbo 32K Preview — это модель быстрого мышления с контекстом 32K для сложных рассуждений и многократных диалогов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE X1 Turbo 32K Preview"
    }
   ]
  },
  {
   "slug": "baidu/ernie-x1.1",
   "model_name": "ernie-x1.1",
   "display_name": "ERNIE X1.1",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     }
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE X1.1是一个用于评估和测试的思维模型预览版。",
    "zh-TW": "ERNIE X1.1 是一個用於評估和測試的思考模型預覽版。",
    "ja-JP": "ERNIE X1.1は評価とテスト用の思考モデルプレビューです。",
    "ru-RU": "ERNIE X1.1 — это предварительная версия модели мышления для оценки и тестирования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE X1.1"
    }
   ]
  },
  {
   "slug": "baidu/ernie-x1.1-preview",
   "model_name": "ernie-x1.1-preview",
   "display_name": "ERNIE X1.1",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.136"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.544"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "0.6"
      }
     },
     "provider_model_id": "baidu/ernie-x1.1-preview"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-09-10",
   "max_input_tokens": 64000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/ernie-x1.1-preview"
   ],
   "intro_i18n": {
    "zh-CN": "ERNIE X1.1 Preview 是一款用于评估与测试的思考模型预览版。",
    "zh-TW": "ERNIE X1.1 預覽版是一款思考模型預覽，用於評估與測試。",
    "ja-JP": "ERNIE X1.1 Preview は、評価およびテスト用の思考モデルプレビューです。",
    "ru-RU": "ERNIE X1.1 Preview — предварительная версия модели мышления для оценки и тестирования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE X1.1"
    }
   ]
  },
  {
   "slug": "baidu/ppio-baidu-ernie-4-5-21B-a3b",
   "model_name": "ppio-baidu-ernie-4-5-21B-a3b",
   "display_name": "baidu/ernie-4.5-21B-a3b",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    }
   ],
   "released_at": "2025-08-04",
   "max_input_tokens": 120000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "baidu/ernie-4.5-21B-a3b"
    }
   ]
  },
  {
   "slug": "baidu/ppio-baidu-ernie-4-5-300b-a47b-paddle",
   "model_name": "ppio-baidu-ernie-4-5-300b-a47b-paddle",
   "display_name": "baidu/ernie-4.5-300b-a47b-paddle",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28600000000000003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "released_at": "2025-09-29",
   "max_input_tokens": 123000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "baidu/ernie-4.5-300b-a47b-paddle"
    }
   ]
  },
  {
   "slug": "baidu/ppio-baidu-ernie-4-5-vl-424b-a47b",
   "model_name": "ppio-baidu-ernie-4-5-vl-424b-a47b",
   "display_name": "baidu/ernie-4-5-vl-424b-a47b",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.429"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.29"
      }
     }
    }
   ],
   "released_at": "2025-08-04",
   "max_input_tokens": 123000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "baidu/ernie-4-5-vl-424b-a47b"
    }
   ]
  },
  {
   "slug": "baidu/ppio-baidu-ernie-4.5-21b-a3b-thinking",
   "model_name": "ppio-baidu-ernie-4.5-21b-a3b-thinking",
   "display_name": "baidu/ernie-4.5-21b-a3b-thinking",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "baidu/ernie-4.5-21b-a3b-thinking"
    }
   ]
  },
  {
   "slug": "baidu/ppio-baidu-ernie-4.5-vl-28b-a3b",
   "model_name": "ppio-baidu-ernie-4.5-vl-28b-a3b",
   "display_name": "baidu/ernie-4.5-vl-28b-a3b",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.572"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 30000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "baidu/ernie-4.5-vl-28b-a3b"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-70b",
   "model_name": "qianfan-70b",
   "display_name": "Qianfan 70B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 70B 是一款中文大模型，适用于高质量生成和复杂推理任务。",
    "zh-TW": "千帆 70B 是一款大型中文模型，具備高品質生成與複雜推理能力。",
    "ja-JP": "Qianfan 70Bは、高品質な生成と複雑な推論に対応する大規模な中国語モデルです。",
    "ru-RU": "Qianfan 70B — это крупная китайская модель для высококачественной генерации текста и сложного рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan 70B"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-8b",
   "model_name": "qianfan-8b",
   "display_name": "Qianfan 8B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 8B 是一款中等规模通用模型，在生成质量与成本之间取得平衡，适用于文本生成和问答任务。",
    "zh-TW": "千帆 8B 是一款中型通用模型，在生成文本與問答任務中兼顧成本與品質。",
    "ja-JP": "Qianfan 8Bは、コストと品質のバランスに優れた中規模の汎用モデルで、テキスト生成やQAに対応します。",
    "ru-RU": "Qianfan 8B — это универсальная модель среднего размера, обеспечивающая баланс между стоимостью и качеством генерации текста и ответов на вопросы."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan 8B"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-agent-intent-32k",
   "model_name": "qianfan-agent-intent-32k",
   "display_name": "Qianfan Agent Intent 32K",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 Agent Intent 32K 专注于意图识别和智能体编排，支持长上下文。",
    "zh-TW": "千帆 Agent Intent 32K 專注於意圖識別與智能代理協作，支援長上下文處理。",
    "ja-JP": "Qianfan Agent Intent 32Kは、長文コンテキストに対応した意図認識とエージェントのオーケストレーションに特化しています。",
    "ru-RU": "Qianfan Agent Intent 32K предназначена для распознавания намерений и координации агентов с поддержкой длинного контекста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan Agent Intent 32K"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-check-vl",
   "model_name": "qianfan-check-vl",
   "display_name": "Qianfan Check VL",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.183824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.551471"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 Check VL 是一款多模态内容审核模型，适用于图文合规性识别与审核任务。",
    "zh-TW": "千帆 Check VL 是一款多模態內容審核模型，支援圖文合規與識別任務。",
    "ja-JP": "Qianfan Check VLは、画像とテキストのコンプライアンス確認や認識タスクに対応するマルチモーダルコンテンツ審査モデルです。",
    "ru-RU": "Qianfan Check VL — это мультимодальная модель для проверки соответствия контента изображений и текста, а также задач распознавания."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan Check VL"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-chinese-llama-2-13b",
   "model_name": "qianfan-chinese-llama-2-13b",
   "display_name": "qianfan-chinese-llama-2-13b",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.822"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.822"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qianfan-chinese-llama-2-13b"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-composition",
   "model_name": "qianfan-composition",
   "display_name": "Qianfan Composition",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.102941"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 Composition 是一款多模态创作模型，支持图文混合理解与生成。",
    "zh-TW": "千帆 Composition 是一款多模態創作模型，支援圖文混合理解與生成。",
    "ja-JP": "Qianfan Compositionは、画像とテキストの混合理解・生成に対応するマルチモーダル創作モデルです。",
    "ru-RU": "Qianfan Composition — это мультимодальная модель для создания и понимания смешанного контента изображение-текст."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan Composition"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-engcard-vl",
   "model_name": "qianfan-engcard-vl",
   "display_name": "Qianfan EngCard VL",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 EngCard VL 是一款专注于英文场景的多模态识别模型。",
    "zh-TW": "千帆 EngCard VL 是一款聚焦英語場景的多模態識別模型。",
    "ja-JP": "Qianfan EngCard VLは、英語シナリオに特化したマルチモーダル認識モデルです。",
    "ru-RU": "Qianfan EngCard VL — это мультимодальная модель распознавания, ориентированная на англоязычные сценарии."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan EngCard VL"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-llama-vl-8b",
   "model_name": "qianfan-llama-vl-8b",
   "display_name": "qianfan-llama-vl-8b",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.274"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.685"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qianfan-llama-vl-8b"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-multipicocr",
   "model_name": "qianfan-multipicocr",
   "display_name": "Qianfan MultiPicOCR",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.102941"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 MultiPicOCR 是一款多图 OCR 模型，支持跨图像的文本检测与识别。",
    "zh-TW": "千帆 MultiPicOCR 是一款多圖像 OCR 模型，支援跨圖像的文字檢測與識別。",
    "ja-JP": "Qianfan MultiPicOCRは、複数画像に対応したOCRモデルで、画像間のテキスト検出と認識を行います。",
    "ru-RU": "Qianfan MultiPicOCR — это модель OCR для нескольких изображений, предназначенная для обнаружения и распознавания текста на изображениях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan MultiPicOCR"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-ocr",
   "model_name": "qianfan-ocr",
   "display_name": "qianfan-ocr",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.062"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.248"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "qianfan-ocr"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-ocr-fast",
   "model_name": "qianfan-ocr-fast",
   "display_name": "Baidu: Qianfan-OCR-Fast",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.664"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.738336"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.81"
      }
     },
     "provider_model_id": "baidu/qianfan-ocr-fast"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.81"
      }
     },
     "provider_model_id": "baidu/qianfan-ocr-fast"
    }
   ],
   "intro": "OCR model for extracting structured text from documents and screenshots",
   "released_at": "2026-04-20",
   "max_input_tokens": 65536,
   "max_output_tokens": 28672,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baidu/qianfan-ocr-fast",
    "baidu/qianfan-ocr-fast:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Baidu: Qianfan-OCR-Fast"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-qi-vl",
   "model_name": "qianfan-qi-vl",
   "display_name": "Qianfan QI VL",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.661765"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 QI VL 是一款多模态问答模型，适用于复杂图文场景下的精准检索与问答。",
    "zh-TW": "千帆 QI VL 是一款多模態問答模型，適用於複雜圖文場景中的精準檢索與問答。",
    "ja-JP": "Qianfan QI VLは、複雑な画像と言語のシナリオにおける高精度な検索と質問応答に対応するマルチモーダルQAモデルです。",
    "ru-RU": "Qianfan QI VL — мультимодальная модель для точного поиска и ответов на вопросы в сложных сценариях изображение-текст."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan QI VL"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-singlepicocr",
   "model_name": "qianfan-singlepicocr",
   "display_name": "Qianfan SinglePicOCR",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 SinglePicOCR 是一款单图 OCR 模型，具备高精度字符识别能力。",
    "zh-TW": "千帆 SinglePicOCR 是一款單張圖片的光學字元辨識（OCR）模型，具備高精度的文字識別能力。",
    "ja-JP": "Qianfan SinglePicOCRは、高精度な文字認識を実現する単一画像向けOCRモデルです。",
    "ru-RU": "Qianfan SinglePicOCR — это модель OCR для одного изображения с высокой точностью распознавания символов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan SinglePicOCR"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-vl-70b",
   "model_name": "qianfan-vl-70b",
   "display_name": "Qianfan VL 70B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 28672,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 VL 70B 是一款大型视觉语言模型，擅长复杂图文理解任务。",
    "zh-TW": "千帆 VL 70B 是一款大型視覺語言模型（VLM），專為複雜的圖文理解任務設計。",
    "ja-JP": "Qianfan VL 70Bは、複雑な画像と言語の理解に対応する大規模ビジョン・ランゲージモデルです。",
    "ru-RU": "Qianfan VL 70B — это крупная мультимодальная модель для сложного понимания изображений и текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan VL 70B"
    }
   ]
  },
  {
   "slug": "baidu/qianfan-vl-8b",
   "model_name": "qianfan-vl-8b",
   "display_name": "Qianfan VL 8B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 28672,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "千帆 VL 8B 是一款轻量级视觉语言模型，适用于日常图文问答与分析。",
    "zh-TW": "千帆 VL 8B 是一款輕量級視覺語言模型，適用於日常圖文問答與分析。",
    "ja-JP": "Qianfan VL 8Bは、日常的な画像と言語のQAや分析に適した軽量なビジョン・ランゲージモデルです。",
    "ru-RU": "Qianfan VL 8B — это легковесная мультимодальная модель для повседневного анализа изображений и текстов и ответов на вопросы."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qianfan VL 8B"
    }
   ]
  },
  {
   "slug": "baidu/siliconflow-baidu-ernie-4-5-300B-a47b",
   "model_name": "siliconflow-baidu-ernie-4-5-300B-a47b",
   "display_name": "baidu/ERNIE-4.5-300B-A47B",
   "vendor": "baidu",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14"
      }
     }
    }
   ],
   "released_at": "2025-07-02",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "baidu/ERNIE-4.5-300B-A47B"
    }
   ]
  },
  {
   "slug": "bfl/flux",
   "model_name": "flux",
   "display_name": "flux",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.2"
      }
     },
     "provider_model_id": "ClarityAI/flux"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00012833333333333333"
      }
     },
     "provider_model_id": "deepgram/flux"
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ClarityAI/flux",
    "deepgram/flux"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "flux"
    }
   ]
  },
  {
   "slug": "bfl/flux_1-kontext-dev",
   "model_name": "flux_1-kontext-dev",
   "display_name": "FLUX.1-Kontext-dev",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "black-forest-labs/flux_1-kontext-dev"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-08-12",
   "max_input_tokens": 40960,
   "max_output_tokens": 40960,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/flux_1-kontext-dev"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1-Kontext-dev"
    }
   ]
  },
  {
   "slug": "bfl/flux_1-schnell",
   "model_name": "flux_1-schnell",
   "display_name": "FLUX.1-schnell",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "black-forest-labs/flux_1-schnell"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-08-01",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 77,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/flux_1-schnell"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1-schnell"
    }
   ]
  },
  {
   "slug": "bfl/flux_2-klein-4b",
   "model_name": "flux_2-klein-4b",
   "display_name": "FLUX.2 Klein 4B",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "black-forest-labs/flux_2-klein-4b"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-01-14",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 40960,
   "max_output_tokens": 40960,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/flux_2-klein-4b"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.2 Klein 4B"
    }
   ]
  },
  {
   "slug": "bfl/FLUX-1-dev",
   "model_name": "FLUX-1-dev",
   "display_name": "FLUX.1-dev",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.009"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX-1-dev"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "flux-1-dev"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "black-forest-labs/flux.1-dev"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-08-01",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 4096,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/FLUX-1-dev",
    "black-forest-labs/flux.1-dev",
    "flux-1-dev"
   ],
   "intro_i18n": {
    "zh-CN": "FLUX.1-dev 是 Black Forest Labs 推出的开源多模态语言模型（MLLM），优化用于图文任务，融合图像/文本理解与生成能力。基于先进的大语言模型（如 Mistral-7B），采用精心设计的视觉编码器和多阶段指令微调，实现多模态协同与复杂任务推理。",
    "zh-TW": "FLUX.1-dev 是來自 Black Forest Labs 的開源多模態語言模型（MLLM），針對圖文任務進行優化，結合圖像與文字的理解與生成能力。該模型基於先進的大型語言模型（如 Mistral-7B），搭配精心設計的視覺編碼器與多階段指令微調，實現多模態協同與複雜任務推理。",
    "ja-JP": "FLUX.1-dev は、Black Forest Labs によるオープンソースのマルチモーダル言語モデル（MLLM）で、画像とテキストの理解・生成を統合しています。高度な LLM（例：Mistral-7B）をベースに、精密に設計されたビジョンエンコーダと多段階の指示チューニングを用いて、マルチモーダルの連携と複雑なタスクの推論を可能にします。",
    "ru-RU": "FLUX.1-dev — это мультимодальная языковая модель с открытым исходным кодом (MLLM) от Black Forest Labs, оптимизированная для задач, связанных с изображениями и текстом. Она объединяет понимание и генерацию изображений/текста. Построена на базе передовых LLM (например, Mistral-7B), использует тщательно разработанный визуальный энкодер и многоступенчатую настройку инструкций для обеспечения мультимодальной координации и сложного логического вывода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1-dev"
    }
   ]
  },
  {
   "slug": "bfl/flux-1-dev-controlnet-union",
   "model_name": "flux-1-dev-controlnet-union",
   "display_name": "flux-1-dev-controlnet-union",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.001"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.001"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "flux-1-dev-controlnet-union"
    }
   ]
  },
  {
   "slug": "bfl/flux-1-dev-fp8",
   "model_name": "flux-1-dev-fp8",
   "display_name": "flux-1-dev-fp8",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0005"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "flux-1-dev-fp8"
    }
   ]
  },
  {
   "slug": "bfl/FLUX-1-Redux-dev",
   "model_name": "FLUX-1-Redux-dev",
   "display_name": "FLUX-1-Redux-dev",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.012"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX-1-Redux-dev"
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/FLUX-1-Redux-dev"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX-1-Redux-dev"
    }
   ]
  },
  {
   "slug": "bfl/FLUX-1-schnell",
   "model_name": "FLUX-1-schnell",
   "display_name": "FLUX.1-schnell",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0005"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX-1-schnell"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "flux-1-schnell"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0027"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.1-schnell"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.000294"
      }
     },
     "provider_model_id": "flux.1-schnell"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "image_generation",
   "capabilities": {
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "released_at": "2025-03-27",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/flux-1-schnell",
    "black-forest-labs/FLUX-1-schnell",
    "black-forest-labs/FLUX.1-schnell",
    "flux-1-schnell",
    "flux.1-schnell"
   ],
   "intro_i18n": {
    "zh-CN": "来自 Black Forest Labs 的 120 亿参数文本转图像模型，采用潜在对抗扩散蒸馏技术，可在 1-4 步内生成高质量图像。性能媲美闭源模型，采用 Apache-2.0 许可，适用于个人、研究与商业用途。",
    "zh-TW": "來自黑森林實驗室的 12B 參數文字轉圖像模型，透過潛在對抗擴散蒸餾技術，在 1 至 4 步內生成高品質圖像。其表現媲美封閉式替代方案，並以 Apache-2.0 授權釋出，供個人、研究與商業用途。",
    "ja-JP": "Black Forest Labs による 120 億パラメータのテキストから画像への変換モデルで、潜在敵対的拡散蒸留を用いて 1～4 ステップで高品質な画像を生成します。クローズドな代替モデルに匹敵し、Apache-2.0 ライセンスのもと、個人・研究・商用利用が可能です。",
    "ru-RU": "Модель преобразования текста в изображение с 12 миллиардами параметров от Black Forest Labs, использующая латентную диффузию с дистилляцией для генерации качественных изображений за 1–4 шага. Конкурирует с закрытыми аналогами и распространяется по лицензии Apache-2.0 для личного, исследовательского и коммерческого использования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1-schnell"
    }
   ]
  },
  {
   "slug": "bfl/flux-1-schnell-fp8",
   "model_name": "flux-1-schnell-fp8",
   "display_name": "flux-1-schnell-fp8",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.00035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.00035"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "flux-1-schnell-fp8"
    }
   ]
  },
  {
   "slug": "bfl/FLUX-2-dev",
   "model_name": "FLUX-2-dev",
   "display_name": "FLUX-2-dev",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.01"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX-2-dev"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0154"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.2-dev"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/FLUX-2-dev",
    "black-forest-labs/FLUX.2-dev"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX-2-dev"
    }
   ]
  },
  {
   "slug": "bfl/flux-2-flex",
   "model_name": "flux-2-flex",
   "display_name": "FLUX.2 [flex]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.2-flex"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-11-25",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bfl/flux-2-flex",
    "black-forest-labs/FLUX.2-flex"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.2 [flex]"
    }
   ]
  },
  {
   "slug": "bfl/FLUX-2-klein-4b",
   "model_name": "FLUX-2-klein-4b",
   "display_name": "FLUX.2 [klein] 4B",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.014"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX-2-klein-4b"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.2-klein-4B"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-01-15",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "open_weights": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bfl/flux-2-klein-4b",
    "black-forest-labs/FLUX-2-klein-4b",
    "black-forest-labs/FLUX.2-klein-4B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.2 [klein] 4B"
    }
   ]
  },
  {
   "slug": "bfl/FLUX-2-klein-9b",
   "model_name": "FLUX-2-klein-9b",
   "display_name": "FLUX.2 [klein] 9B",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.015"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX-2-klein-9b"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-01-15",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bfl/flux-2-klein-9b",
    "black-forest-labs/FLUX-2-klein-9b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.2 [klein] 9B"
    }
   ]
  },
  {
   "slug": "bfl/FLUX-2-max",
   "model_name": "FLUX-2-max",
   "display_name": "FLUX.2 [max]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.03"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.07"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX-2-max"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.07"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.2-max"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-12-16",
   "max_input_tokens": 67300,
   "max_output_tokens": 67300,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bfl/flux-2-max",
    "black-forest-labs/FLUX-2-max",
    "black-forest-labs/FLUX.2-max"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.2 [max]"
    }
   ]
  },
  {
   "slug": "bfl/FLUX-2-pro",
   "model_name": "FLUX-2-pro",
   "display_name": "FLUX.2 [pro]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "flux.2-pro"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.015"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX-2-pro"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.2-pro"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-11-25",
   "max_input_tokens": 67300,
   "max_output_tokens": 67300,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "docs_url": "https://ai.azure.com/explore/models/flux.2-pro/version/1/registry/azureml-blackforestlabs",
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bfl/flux-2-pro",
    "black-forest-labs/FLUX-2-pro",
    "black-forest-labs/FLUX.2-pro",
    "flux.2-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.2 [pro]"
    }
   ]
  },
  {
   "slug": "bfl/flux-dev",
   "model_name": "flux-dev",
   "display_name": "FLUX.1 [dev]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "bfl",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "replicate",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.025"
      }
     },
     "provider_model_id": "black-forest-labs/flux-dev"
    }
   ],
   "released_at": "2024-08-01",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/flux-dev"
   ],
   "intro_i18n": {
    "zh-CN": "FLUX Dev 是 FLUX 的开发版本，仅供非商业用途使用。",
    "zh-TW": "FLUX Dev 是 FLUX 的開發版本，僅供非商業用途。",
    "ja-JP": "FLUX Devは、非商用利用向けのFLUX開発バージョンです。",
    "ru-RU": "FLUX Dev — это версия FLUX для разработки, предназначенная для некоммерческого использования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1 [dev]"
    }
   ]
  },
  {
   "slug": "bfl/flux-fast-schnell",
   "model_name": "flux-fast-schnell",
   "display_name": "Flux Schnell",
   "vendor": "bfl",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-08-02",
   "max_input_tokens": 512,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "prodia/flux-fast-schnell"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Flux Schnell"
    }
   ]
  },
  {
   "slug": "bfl/flux-kontext-max",
   "model_name": "flux-kontext-max",
   "display_name": "FLUX.1 Kontext [max]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "bfl",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.08"
      }
     },
     "provider_model_id": "bfl/flux-kontext-max"
    }
   ],
   "released_at": "2025-05-29",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 512,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bfl/flux-kontext-max"
   ],
   "intro_i18n": {
    "zh-CN": "最先进的上下文图像生成与编辑模型，结合文本与图像输入，实现精准一致的结果。",
    "zh-TW": "最先進的語境圖像生成與編輯技術，結合文字與圖像輸入，實現精準且一致的結果。",
    "ja-JP": "最先端のコンテキスト画像生成・編集モデルで、テキストと画像を組み合わせて精密かつ一貫性のある結果を生成します。",
    "ru-RU": "Передовая генерация и редактирование изображений с учётом контекста, объединяющая текст и изображения для точных и согласованных результатов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1 Kontext [max]"
    }
   ]
  },
  {
   "slug": "bfl/flux-kontext-pro",
   "model_name": "flux-kontext-pro",
   "display_name": "FLUX.1 Kontext [pro]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "bfl",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "bfl/flux-kontext-pro"
    }
   ],
   "released_at": "2025-05-29",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 512,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bfl/flux-kontext-pro"
   ],
   "intro_i18n": {
    "zh-CN": "最先进的上下文图像生成与编辑模型，结合文本与图像输入，实现精准一致的结果。",
    "zh-TW": "最先進的語境圖像生成與編輯技術，結合文字與圖像輸入，實現精準且一致的結果。",
    "ja-JP": "最先端のコンテキスト画像生成・編集モデルで、テキストと画像を組み合わせて精密かつ一貫性のある結果を生成します。",
    "ru-RU": "Передовая генерация и редактирование изображений с учётом контекста, объединяющая текст и изображения для точных и согласованных результатов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1 Kontext [pro]"
    }
   ]
  },
  {
   "slug": "bfl/flux-kontext/dev",
   "model_name": "flux-kontext/dev",
   "display_name": "FLUX.1 Kontext [dev]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "fal",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output_per_megapixel": {
       "unit": "per_image",
       "price": "0.025"
      }
     },
     "provider_model_id": "fal-ai/flux-kontext/dev"
    }
   ],
   "released_at": "2025-06-28",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fal-ai/flux-kontext/dev"
   ],
   "intro_i18n": {
    "zh-CN": "FLUX.1 模型专注于图像编辑，支持文本与图像输入。",
    "zh-TW": "FLUX.1 模型專注於圖像編輯，支援文字與圖像輸入。",
    "ja-JP": "FLUX.1 モデルは画像編集に特化しており、テキストと画像の入力に対応しています。",
    "ru-RU": "Модель FLUX.1, ориентированная на редактирование изображений, поддерживает ввод текста и изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1 Kontext [dev]"
    }
   ]
  },
  {
   "slug": "bfl/FLUX-pro",
   "model_name": "FLUX-pro",
   "display_name": "FLUX.1 [pro]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "bfl",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.025"
      }
     },
     "provider_model_id": "flux-pro"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.05"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX-pro"
    },
    {
     "provider": "replicate",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.05"
      }
     },
     "provider_model_id": "black-forest-labs/flux-pro"
    }
   ],
   "released_at": "2024-08-01",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/FLUX-pro",
    "black-forest-labs/flux-pro",
    "flux-pro"
   ],
   "intro_i18n": {
    "zh-CN": "FLUX Pro 是专业级图像生成模型，输出高质量图像。",
    "zh-TW": "FLUX Pro 是專業級 FLUX 模型，專為高品質圖像輸出設計。",
    "ja-JP": "FLUX Proは、高品質な画像出力を実現するプロフェッショナル向けFLUXモデルです。",
    "ru-RU": "FLUX Pro — профессиональная модель FLUX для генерации изображений высокого качества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1 [pro]"
    }
   ]
  },
  {
   "slug": "bfl/flux-pro-1.0-fill",
   "model_name": "flux-pro-1.0-fill",
   "display_name": "FLUX.1 Fill [pro]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.05"
      }
     },
     "provider_model_id": "bfl/flux-pro-1.0-fill"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-10-01",
   "max_input_tokens": 512,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bfl/flux-pro-1.0-fill"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1 Fill [pro]"
    }
   ]
  },
  {
   "slug": "bfl/flux-pro-1.1",
   "model_name": "flux-pro-1.1",
   "display_name": "FLUX1.1 [pro] ",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "bfl",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "bfl/flux-pro-1.1"
    }
   ],
   "released_at": "2024-10-02",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 512,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bfl/flux-pro-1.1"
   ],
   "intro_i18n": {
    "zh-CN": "升级版专业图像生成模型，图像质量卓越，提示词遵循精准。",
    "zh-TW": "升級版專業級圖像生成模型，具備卓越圖像品質與精準提示遵循能力。",
    "ja-JP": "画像品質とプロンプトの精度に優れた、アップグレードされたプロフェッショナル画像生成モデルです。",
    "ru-RU": "Обновлённая профессиональная модель генерации изображений с отличным качеством и точным следованием подсказкам."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX1.1 [pro] "
    }
   ]
  },
  {
   "slug": "bfl/flux-pro-1.1-ultra",
   "model_name": "flux-pro-1.1-ultra",
   "display_name": "FLUX1.1 [pro] Ultra",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "bfl",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "provider_model_id": "bfl/flux-pro-1.1-ultra"
    }
   ],
   "released_at": "2024-11-06",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 512,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bfl/flux-pro-1.1-ultra"
   ],
   "intro_i18n": {
    "zh-CN": "超高分辨率图像生成，支持 4MP 输出，10 秒内生成清晰图像。",
    "zh-TW": "支援 4MP 輸出的超高解析度圖像生成，10 秒內產出清晰圖像。",
    "ja-JP": "400 万画素の超高解像度画像を 10 秒で生成するモデルです。",
    "ru-RU": "Генерация изображений сверхвысокого разрешения с выходом 4 МП, создаёт чёткие изображения за 10 секунд."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX1.1 [pro] Ultra"
    }
   ]
  },
  {
   "slug": "bfl/flux-pro/kontext",
   "model_name": "flux-pro/kontext",
   "display_name": "FLUX.1 Kontext [pro]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "fal",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "fal-ai/flux-pro/kontext"
    }
   ],
   "released_at": "2025-05-01",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fal-ai/flux-pro/kontext"
   ],
   "intro_i18n": {
    "zh-CN": "FLUX.1 Kontext [pro] 接受文本与参考图像输入，支持局部精准编辑与复杂全局场景变换。",
    "zh-TW": "FLUX.1 Kontext [pro] 接受文字與參考圖像輸入，實現目標區域編輯與複雜場景轉換。",
    "ja-JP": "FLUX.1 Kontext [pro] は、テキストと参照画像を入力として受け取り、局所的な編集や複雑なシーン全体の変換を可能にします。",
    "ru-RU": "FLUX.1 Kontext [pro] принимает текст и эталонные изображения, позволяя выполнять локальные правки и сложные глобальные трансформации сцены."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1 Kontext [pro]"
    }
   ]
  },
  {
   "slug": "bfl/flux-schnell",
   "model_name": "flux-schnell",
   "display_name": "FLUX Schnell",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "replicate",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.003"
      }
     },
     "provider_model_id": "black-forest-labs/flux-schnell"
    }
   ],
   "released_at": "2024-08-01",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/flux-schnell"
   ],
   "intro_i18n": {
    "zh-CN": "FLUX Schnell 是一款专为速度优化的快速图像生成模型。",
    "zh-TW": "FLUX Schnell 是一款針對速度優化的快速圖像生成模型。",
    "ja-JP": "FLUX Schnellは、速度に最適化された高速画像生成モデルです。",
    "ru-RU": "FLUX Schnell — это модель генерации изображений, оптимизированная для высокой скорости."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX Schnell"
    }
   ]
  },
  {
   "slug": "bfl/FLUX.1-Kontext-dev",
   "model_name": "FLUX.1-Kontext-dev",
   "display_name": "FLUX.1-Kontext-dev",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.01"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.1-Kontext-dev"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/FLUX.1-Kontext-dev"
   ],
   "intro_i18n": {
    "zh-CN": "FLUX.1-Kontext-dev 是 Black Forest Labs 推出的多模态图像生成与编辑模型，基于 Rectified Flow Transformer 架构，拥有 120 亿参数。专注于在给定上下文条件下生成、重建、增强或编辑图像。结合扩散模型的可控生成能力与 Transformer 的上下文建模，支持图像修复、扩图和视觉场景重建等高质量任务。",
    "zh-TW": "FLUX.1-Kontext-dev 是來自 Black Forest Labs 的多模態圖像生成與編輯模型，基於 Rectified Flow Transformer 架構，擁有 120 億參數。該模型專注於在特定語境條件下生成、重建、增強或編輯圖像。它結合了擴散模型的可控生成能力與 Transformer 的語境建模能力，支援高品質的圖像修補、擴圖與視覺場景重建等任務。",
    "ja-JP": "FLUX.1-Kontext-dev は、Black Forest Labs によるマルチモーダル画像生成・編集モデルで、12Bパラメータの Rectified Flow Transformer アーキテクチャに基づいています。与えられたコンテキスト条件下での画像生成、再構築、強化、編集に特化しており、拡散モデルの制御可能な生成能力と Transformer のコンテキストモデリングを組み合わせ、インペインティング、アウトペインティング、視覚シーン再構築などの高品質な出力を実現します。",
    "ru-RU": "FLUX.1-Kontext-dev — это мультимодальная модель генерации и редактирования изображений от Black Forest Labs, основанная на архитектуре Rectified Flow Transformer с 12 миллиардами параметров. Она предназначена для генерации, реконструкции, улучшения и редактирования изображений в заданных контекстных условиях. Модель сочетает управляемую генерацию диффузионных моделей с контекстным моделированием Transformer, обеспечивая высококачественные результаты для задач, таких как дорисовка, расширение изображения и реконструкция визуальных сцен."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1-Kontext-dev"
    }
   ]
  },
  {
   "slug": "bfl/FLUX.1-kontext-max",
   "model_name": "FLUX.1-kontext-max",
   "display_name": "FLUX.1-kontext-max",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.08"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.1-kontext-max"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/FLUX.1-kontext-max"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1-kontext-max"
    }
   ]
  },
  {
   "slug": "bfl/FLUX.1-Kontext-pro",
   "model_name": "FLUX.1-Kontext-pro",
   "display_name": "FLUX.1-Kontext-pro",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.1-kontext-pro"
    }
   ],
   "docs_url": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/FLUX.1-kontext-pro"
   ],
   "intro_i18n": {
    "zh-CN": "FLUX.1 Kontext [pro]",
    "zh-TW": "FLUX.1 Kontext [專業版]",
    "ja-JP": "FLUX.1 Kontext [pro]",
    "ru-RU": "FLUX.1 Kontext [pro]"
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1-Kontext-pro"
    }
   ]
  },
  {
   "slug": "bfl/FLUX.1-krea-dev",
   "model_name": "FLUX.1-krea-dev",
   "display_name": "FLUX.1-krea-dev",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.025"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.1-krea-dev"
    }
   ],
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/FLUX.1-krea-dev"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1-krea-dev"
    }
   ]
  },
  {
   "slug": "bfl/FLUX.1-pro",
   "model_name": "FLUX.1-pro",
   "display_name": "FLUX.1-pro",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.1-pro"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "black-forest-labs/FLUX.1-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1-pro"
    }
   ]
  },
  {
   "slug": "bfl/FLUX.1.1-pro",
   "model_name": "FLUX.1.1-pro",
   "display_name": "FLUX 1.1 Pro",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "FLUX-1.1-pro"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX-1.1-pro"
    },
    {
     "provider": "replicate",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "black-forest-labs/flux-1.1-pro"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "black-forest-labs/FLUX.1.1-pro"
    }
   ],
   "docs_url": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/black-forest-labs-flux-1-kontext-pro-and-flux1-1-pro-now-available-in-azure-ai-f/4434659",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "released_at": "2024-10-02",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "FLUX-1.1-pro",
    "black-forest-labs/FLUX-1.1-pro",
    "black-forest-labs/FLUX.1.1-pro",
    "black-forest-labs/flux-1.1-pro"
   ],
   "intro_i18n": {
    "zh-CN": "FLUX.1.1 Pro",
    "zh-TW": "FLUX.1.1 Pro",
    "ja-JP": "FLUX.1.1 Pro",
    "ru-RU": "FLUX.1.1 Pro"
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX 1.1 Pro"
    }
   ]
  },
  {
   "slug": "bfl/flux/krea",
   "model_name": "flux/krea",
   "display_name": "FLUX.1 Krea [dev]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "fal",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output_per_megapixel": {
       "unit": "per_image",
       "price": "0.025"
      }
     },
     "provider_model_id": "fal-ai/flux/krea"
    }
   ],
   "released_at": "2025-07-31",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fal-ai/flux/krea"
   ],
   "intro_i18n": {
    "zh-CN": "Flux Krea [dev] 是一款图像生成模型，偏好更真实自然的美学风格。",
    "zh-TW": "Flux Krea [dev] 是一款圖像生成模型，偏好更真實自然的美學風格。",
    "ja-JP": "Flux Krea [dev] は、よりリアルで自然な画像を生成する美的バイアスを持つ画像生成モデルです。",
    "ru-RU": "Flux Krea [dev] — модель генерации изображений с эстетическим уклоном в сторону более реалистичных и естественных изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1 Krea [dev]"
    }
   ]
  },
  {
   "slug": "bfl/flux/schnell",
   "model_name": "flux/schnell",
   "display_name": "FLUX.1 [schnell]",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "fal",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output_per_megapixel": {
       "unit": "per_image",
       "price": "0.003"
      }
     },
     "provider_model_id": "fal-ai/flux/schnell"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-08-01",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "flux",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fal-ai/flux/schnell"
   ],
   "intro_i18n": {
    "zh-CN": "FLUX.1 [schnell] 是一款拥有 120 亿参数的图像生成模型，专为快速高质量输出而设计。",
    "zh-TW": "FLUX.1 [schnell] 是一款具備 120 億參數的圖像生成模型，專為快速高品質輸出打造。",
    "ja-JP": "FLUX.1 [schnell] は、迅速かつ高品質な出力を目的として構築された 120 億パラメータの画像生成モデルです。",
    "ru-RU": "FLUX.1 [schnell] — модель генерации изображений с 12 миллиардами параметров, созданная для быстрой и качественной генерации."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FLUX.1 [schnell]"
    }
   ]
  },
  {
   "slug": "bfl/Juggernaut-Lightning-Flux",
   "model_name": "Juggernaut-Lightning-Flux",
   "display_name": "Juggernaut-Lightning-Flux",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0017"
      }
     },
     "provider_model_id": "Rundiffusion/Juggernaut-Lightning-Flux"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Rundiffusion/Juggernaut-Lightning-Flux"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Juggernaut-Lightning-Flux"
    }
   ]
  },
  {
   "slug": "bfl/Juggernaut-pro-flux",
   "model_name": "Juggernaut-pro-flux",
   "display_name": "Juggernaut-pro-flux",
   "vendor": "bfl",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.0049"
      }
     },
     "provider_model_id": "RunDiffusion/Juggernaut-pro-flux"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "RunDiffusion/Juggernaut-pro-flux"
   ],
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Juggernaut-pro-flux"
    }
   ]
  },
  {
   "slug": "bytedance/bytedance/seedream/v4",
   "model_name": "bytedance/seedream/v4",
   "display_name": "Seedream 4.0",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "fal",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "fal-ai/bytedance/seedream/v4"
    }
   ],
   "released_at": "2025-09-09",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fal-ai/bytedance/seedream/v4"
   ],
   "intro_i18n": {
    "zh-CN": "Seedream 4.0 是字节跳动 Seed 的图像生成模型，支持文本和图像输入，能够生成高度可控、高质量的图像。它可以根据文本提示生成图像。",
    "zh-TW": "Seedream 4.0 是來自字節跳動 Seed 的圖像生成模型，支持文本和圖像輸入，能夠生成高度可控且高品質的圖像。它可以根據文本提示生成圖像。",
    "ja-JP": "Seedream 4.0は、ByteDance Seedが提供する画像生成モデルで、テキストと画像入力をサポートし、高度に制御可能で高品質な画像生成を実現します。テキストプロンプトから画像を生成します。",
    "ru-RU": "Seedream 4.0 — модель генерации изображений от ByteDance Seed, поддерживающая ввод текста и изображений с высококонтролируемой, качественной генерацией изображений. Она создает изображения на основе текстовых запросов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedream 4.0"
    }
   ]
  },
  {
   "slug": "bytedance/cc-doubao-seed-code-preview-latest",
   "model_name": "cc-doubao-seed-code-preview-latest",
   "display_name": "cc-doubao-seed-code-preview-latest",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-doubao-seed-code-preview-latest"
    }
   ]
  },
  {
   "slug": "bytedance/deepseek-v3-2-251201",
   "model_name": "deepseek-v3-2-251201",
   "display_name": "deepseek-v3-2-251201",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "volcengine",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 98304,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "assistant_prefill": true
   },
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-12-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-v3.2-251201"
   ]
  },
  {
   "slug": "bytedance/doubao-1-5-lite-32k",
   "model_name": "doubao-1-5-lite-32k",
   "display_name": "Doubao 1.5 Lite 32k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      }
     },
     "provider_model_id": "doubao-1.5-lite-32k"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Doubao-1.5-lite-32k"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 12288,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "released_at": "2025-01-22",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Doubao-1.5-lite-32k",
    "doubao-1.5-lite-32k"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-1.5-lite 是一款全新轻量级模型，响应速度极快，兼具卓越质量与低延迟。",
    "zh-TW": "Doubao-1.5-lite 是一款全新輕量級模型，具備極速回應能力，提供頂級品質與低延遲表現。",
    "ja-JP": "Doubao-1.5-lite は、超高速応答を実現する新しい軽量モデルで、最高水準の品質と低遅延を提供します。",
    "ru-RU": "Doubao-1.5-lite — новая облегчённая модель с ультрабыстрым откликом, обеспечивающая высокое качество и низкую задержку."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao 1.5 Lite 32k"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1-5-pro-256k",
   "model_name": "doubao-1-5-pro-256k",
   "display_name": "Doubao 1.5 Pro 256k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      }
     },
     "provider_model_id": "doubao-1.5-pro-256k"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "Doubao-1.5-pro-256k"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.799"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.445"
      }
     },
     "provider_model_id": "doubao-1.5-pro-256k"
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 12288,
   "model_type": "text_generation",
   "capabilities": {},
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-03-12",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Doubao-1.5-pro-256k",
    "doubao-1.5-pro-256k"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-1.5-pro-256k 是 Doubao-1.5-Pro 的全面升级版，整体性能提升 10%。支持 256k 上下文窗口和最多 12k 输出 token，性能更强、窗口更大，适用于更广泛的场景。",
    "zh-TW": "Doubao-1.5-pro-256k 是 Doubao-1.5-Pro 的全面升級版，整體效能提升 10%。支援 256k 上下文視窗與最多 12k 輸出字元，提供更高效能、更大視窗與更廣泛應用價值。",
    "ja-JP": "Doubao-1.5-pro-256k は Doubao-1.5-Pro の包括的なアップグレード版で、全体的な性能が10%向上しています。256kのコンテキストウィンドウと最大12kの出力トークンに対応し、より高性能で広範なユースケースに対応する価値の高いモデルです。",
    "ru-RU": "Doubao-1.5-pro-256k — комплексное обновление модели Doubao-1.5-Pro, повышающее общую производительность на 10%. Поддерживает контекстное окно 256k и до 12k токенов вывода, обеспечивая высокую производительность, расширенное окно и отличную ценность для широкого спектра задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao 1.5 Pro 256k"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1-5-pro-256k-250115",
   "model_name": "doubao-1-5-pro-256k-250115",
   "display_name": "doubao-1-5-pro-256k-250115",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.684"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2312"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-1-5-pro-256k-250115"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1-5-pro-32k",
   "model_name": "doubao-1-5-pro-32k",
   "display_name": "Doubao 1.5 Pro 32k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "doubao-1.5-pro-32k"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.134"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.335"
      }
     },
     "provider_model_id": "Doubao-1.5-pro-32k"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1343"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3349"
      }
     },
     "provider_model_id": "doubao-1.5-pro-32k"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2025-08-05",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Doubao-1.5-pro-32k",
    "doubao-1.5-pro-32k"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-1.5-pro 是新一代旗舰模型，全面升级，在知识、编程和推理方面表现出色。",
    "zh-TW": "Doubao-1.5-pro 是新一代旗艦模型，全面升級，在知識、程式設計與推理方面表現出色。",
    "ja-JP": "Doubao-1.5-pro は次世代のフラッグシップモデルで、知識、コーディング、推論の各分野で優れた性能を発揮します。",
    "ru-RU": "Doubao-1.5-pro — флагманская модель нового поколения с улучшениями по всем направлениям, превосходящая в знаниях, программировании и рассуждении."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao 1.5 Pro 32k"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1-5-pro-32k-250115",
   "model_name": "doubao-1-5-pro-32k-250115",
   "display_name": "doubao-1-5-pro-32k-250115",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.108"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     }
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "released_at": "2025-11-07",
   "max_input_tokens": 128000,
   "max_output_tokens": 12000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-1-5-pro-32k-250115"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1-5-thinking-pro-250415",
   "model_name": "doubao-1-5-thinking-pro-250415",
   "display_name": "Doubao 1.5 Thinking Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-04-17",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao 1.5 Thinking Pro"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1-5-thinking-pro-vision-250415",
   "model_name": "doubao-1-5-thinking-pro-vision-250415",
   "display_name": "Doubao 1.5 Thinking Pro Vision",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-04-15",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao 1.5 Thinking Pro Vision"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1-5-thinking-vision-pro-250428",
   "model_name": "doubao-1-5-thinking-vision-pro-250428",
   "display_name": "Doubao 1.5 Thinking Vision Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.43"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-15",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao 1.5 Thinking Vision Pro"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1-5-ui-tars-250328",
   "model_name": "doubao-1-5-ui-tars-250328",
   "display_name": "doubao-1.5-ui-tars-250328",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     }
    }
   ],
   "released_at": "2025-05-06",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-1.5-ui-tars-250328"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1-5-vision-pro-32k",
   "model_name": "doubao-1-5-vision-pro-32k",
   "display_name": "Doubao 1.5 Vision Pro 32k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.323529"
      }
     },
     "provider_model_id": "doubao-1.5-vision-pro-32k"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.46"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.38"
      }
     },
     "provider_model_id": "Doubao-1.5-vision-pro-32k"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.459"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.377"
      }
     },
     "provider_model_id": "doubao-1.5-vision-pro-32k"
    }
   ],
   "released_at": "2025-01-15",
   "max_input_tokens": 32768,
   "max_output_tokens": 12288,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true,
    "image_output": true,
    "video_input": true,
    "pdf_input": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Doubao-1.5-vision-pro-32k",
    "doubao-1.5-vision-pro-32k"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-1.5-vision-pro 是升级版多模态模型，支持任意分辨率和极端长宽比图像，提升视觉推理、文档识别、细节理解与指令遵循能力。",
    "zh-TW": "Doubao-1.5-vision-pro 是升級版多模態模型，支援任意解析度與極端長寬比的圖像，強化視覺推理、文件識別、細節理解與指令遵循。",
    "ja-JP": "Doubao-1.5-vision-pro はアップグレードされたマルチモーダルモデルで、あらゆる解像度や極端なアスペクト比の画像に対応し、視覚的推論、文書認識、細部理解、指示の追従性を強化します。",
    "ru-RU": "Doubao-1.5-vision-pro — обновлённая мультимодальная модель, поддерживающая изображения любого разрешения и экстремальных соотношений сторон, улучшая визуальное рассуждение, распознавание документов, понимание деталей и следование инструкциям."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao 1.5 Vision Pro 32k"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1.5-pro-32k-character-250715",
   "model_name": "doubao-1.5-pro-32k-character-250715",
   "display_name": "doubao-1.5-pro-32k-character-250715",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     }
    }
   ],
   "released_at": "2025-10-30",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-1.5-pro-32k-character-250715"
    }
   ]
  },
  {
   "slug": "bytedance/Doubao-1.5-thinking-pro",
   "model_name": "Doubao-1.5-thinking-pro",
   "display_name": "Doubao 1.5 Thinking Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.48"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.31884"
      }
     },
     "provider_model_id": "doubao-1.5-thinking-pro"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2025-08-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubao-1.5-thinking-pro"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao 1.5 Thinking Pro"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1.5-vision-lite-250315",
   "model_name": "doubao-1.5-vision-lite-250315",
   "display_name": "doubao-1.5-vision-lite-250315",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.64"
      }
     }
    }
   ],
   "released_at": "2025-07-03",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-1.5-vision-lite-250315"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1.5-vision-pro",
   "model_name": "doubao-1.5-vision-pro",
   "display_name": "Doubao 1.5 Vision Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43478"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.30435"
      }
     }
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2025-08-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao 1.5 Vision Pro"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-1.5-vision-pro-250328",
   "model_name": "doubao-1.5-vision-pro-250328",
   "display_name": "doubao-1.5-vision-pro-250328",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.29"
      }
     }
    }
   ],
   "released_at": "2025-07-03",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-1.5-vision-pro-250328"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-embedding",
   "model_name": "doubao-embedding",
   "display_name": "doubao-embedding",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "volcengine",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "bytedance/doubao-embedding-large",
   "model_name": "doubao-embedding-large",
   "display_name": "doubao-embedding-large",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "volcengine",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "bytedance/doubao-embedding-large-text-240915",
   "model_name": "doubao-embedding-large-text-240915",
   "display_name": "doubao-embedding-large-text-240915",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "volcengine",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_embedding",
   "capabilities": {},
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "bytedance/doubao-embedding-large-text-250515",
   "model_name": "doubao-embedding-large-text-250515",
   "display_name": "doubao-embedding-large-text-250515",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "volcengine",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "bytedance/doubao-embedding-text-240715",
   "model_name": "doubao-embedding-text-240715",
   "display_name": "doubao-embedding-text-240715",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "volcengine",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_embedding",
   "capabilities": {},
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "bytedance/Doubao-lite-128k",
   "model_name": "Doubao-lite-128k",
   "display_name": "Doubao-lite-128k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "豆包-lite 提供超快响应和更高性价比，适用于多种场景，支持 128K 上下文推理与微调。",
    "zh-TW": "Doubao-lite 提供超快速回應與更高性價比，適用於多種場景，支援 128K 上下文推理與微調。",
    "ja-JP": "Doubao-lite は、超高速な応答と優れたコストパフォーマンスを提供し、さまざまなシナリオに柔軟に対応します。推論とファインチューニングに対応した128Kコンテキストをサポートします。",
    "ru-RU": "Doubao-lite обеспечивает сверхбыстрые ответы и отличное соотношение цены и качества, предлагая гибкие варианты для различных сценариев. Поддерживает контекст объемом 128K для вывода и дообучения."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao-lite-128k"
    }
   ]
  },
  {
   "slug": "bytedance/Doubao-lite-32k",
   "model_name": "Doubao-lite-32k",
   "display_name": "Doubao Lite 32k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      }
     },
     "provider_model_id": "doubao-lite-32k"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubao-lite-32k"
   ],
   "intro_i18n": {
    "zh-CN": "豆包-lite 提供超快响应和更高性价比，适用于多种场景，支持 32K 上下文推理与微调。",
    "zh-TW": "Doubao-lite 提供超快速回應與更高性價比，適用於多種場景，支援 32K 上下文推理與微調。",
    "ja-JP": "Doubao-lite は、超高速な応答と優れたコストパフォーマンスを提供し、さまざまなシナリオに柔軟に対応します。推論とファインチューニングに対応した32Kコンテキストをサポートします。",
    "ru-RU": "Doubao-lite обеспечивает сверхбыстрые ответы и отличное соотношение цены и качества, предлагая гибкие варианты для различных сценариев. Поддерживает контекст объемом 32K для вывода и дообучения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Lite 32k"
    }
   ]
  },
  {
   "slug": "bytedance/Doubao-lite-4k",
   "model_name": "Doubao-lite-4k",
   "display_name": "Doubao-lite-4k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "豆包-lite 提供超快响应和更高性价比，适用于多种场景，支持 4K 上下文推理与微调。",
    "zh-TW": "Doubao-lite 提供超快速回應與更高性價比，適用於多種場景，支援 4K 上下文推理與微調。",
    "ja-JP": "Doubao-lite は、超高速な応答と優れたコストパフォーマンスを提供し、さまざまなシナリオに柔軟に対応します。推論とファインチューニングに対応した4Kコンテキストをサポートします。",
    "ru-RU": "Doubao-lite обеспечивает сверхбыстрые ответы и отличное соотношение цены и качества, предлагая гибкие варианты для различных сценариев. Поддерживает контекст объемом 4K для вывода и дообучения."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao-lite-4k"
    }
   ]
  },
  {
   "slug": "bytedance/Doubao-pro-128k",
   "model_name": "Doubao-pro-128k",
   "display_name": "Doubao-pro-128k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "doubao-pro-128k"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     }
    }
   ],
   "released_at": "2025-08-08",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubao-pro-128k"
   ],
   "intro_i18n": {
    "zh-CN": "旗舰性能最强模型，擅长复杂任务，在参考问答、摘要、创作、分类和角色扮演方面表现出色。支持 128K 上下文推理与微调。",
    "zh-TW": "旗艦級最佳表現模型，擅長參考問答、摘要、創作、分類與角色扮演。支援 128K 上下文推理與微調。",
    "ja-JP": "複雑なタスクに最適な高性能フラッグシップモデルで、参照型QA、要約、創作、分類、ロールプレイに強みを持ちます。推論とファインチューニングに対応した128Kコンテキストをサポートします。",
    "ru-RU": "Флагманская модель с наилучшей производительностью для сложных задач, превосходно справляется с вопросно-ответными задачами, суммированием, созданием контента, классификацией и ролевыми сценариями. Поддерживает контекст объемом 128K для вывода и дообучения."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao-pro-128k"
    }
   ]
  },
  {
   "slug": "bytedance/Doubao-pro-256k",
   "model_name": "Doubao-pro-256k",
   "display_name": "Doubao-pro-256k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao-pro-256k"
    }
   ]
  },
  {
   "slug": "bytedance/Doubao-pro-32k",
   "model_name": "Doubao-pro-32k",
   "display_name": "Doubao Pro 32k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "doubao-pro-32k"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "doubao-pro-32k"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "released_at": "2024-06-06",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubao-pro-32k"
   ],
   "intro_i18n": {
    "zh-CN": "旗舰性能最强模型，擅长复杂任务，在参考问答、摘要、创作、分类和角色扮演方面表现出色。支持 32K 上下文推理与微调。",
    "zh-TW": "旗艦級最佳表現模型，擅長參考問答、摘要、創作、分類與角色扮演。支援 32K 上下文推理與微調。",
    "ja-JP": "複雑なタスクに最適な高性能フラッグシップモデルで、参照型QA、要約、創作、分類、ロールプレイに強みを持ちます。推論とファインチューニングに対応した32Kコンテキストをサポートします。",
    "ru-RU": "Флагманская модель с наилучшей производительностью для сложных задач, превосходно справляется с вопросно-ответными задачами, суммированием, созданием контента, классификацией и ролевыми сценариями. Поддерживает контекст объемом 32K для вывода и дообучения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Pro 32k"
    }
   ]
  },
  {
   "slug": "bytedance/Doubao-pro-4k",
   "model_name": "Doubao-pro-4k",
   "display_name": "Doubao-pro-4k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "旗舰性能最强模型，擅长复杂任务，在参考问答、摘要、创作、分类和角色扮演方面表现出色。支持 4K 上下文推理与微调。",
    "zh-TW": "旗艦級最佳表現模型，擅長參考問答、摘要、創作、分類與角色扮演。支援 4K 上下文推理與微調。",
    "ja-JP": "複雑なタスクに最適な高性能フラッグシップモデルで、参照型QA、要約、創作、分類、ロールプレイに強みを持ちます。推論とファインチューニングに対応した4Kコンテキストをサポートします。",
    "ru-RU": "Флагманская модель с наилучшей производительностью для сложных задач, превосходно справляется с вопросно-ответными задачами, суммированием, созданием контента, классификацией и ролевыми сценариями. Поддерживает контекст объемом 4K для вывода и дообучения."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao-pro-4k"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-6",
   "model_name": "doubao-seed-1-6",
   "display_name": "Doubao Seed 1.6",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.352941"
      },
      "completion_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_032_0_128_0_infinity": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "completion_0_128_infinity_0_infinity": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.023529"
      }
     },
     "provider_model_id": "doubao-seed-1.6"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11594"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      }
     },
     "provider_model_id": "doubao-seed-1.6"
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-08-15",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubao-seed-1.6"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-Seed-1.6 是一款全新多模态深度推理模型，支持自动、思考与非思考模式。在非思考模式下，其性能显著优于 Doubao-1.5-pro/250115。支持 256k 上下文窗口和最多 16k 输出 token。",
    "zh-TW": "Doubao-Seed-1.6 是一款全新多模態深度推理模型，具備自動、思考與非思考模式。在非思考模式下，效能顯著超越 Doubao-1.5-pro/250115。支援 256k 上下文視窗與最多 16k 輸出字元。",
    "ja-JP": "Doubao-Seed-1.6 は、自動、思考、非思考モードを備えた新しいマルチモーダル深層推論モデルです。非思考モードでは、Doubao-1.5-pro/250115 を大きく上回る性能を発揮します。256kのコンテキストウィンドウと最大16kの出力トークンに対応します。",
    "ru-RU": "Doubao-Seed-1.6 — новая мультимодальная модель глубокого рассуждения с режимами авто, мышления и без мышления. В режиме без мышления значительно превосходит Doubao-1.5-pro/250115. Поддерживает контекст до 256k и до 16k токенов вывода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 1.6"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-6-250615",
   "model_name": "doubao-seed-1-6-250615",
   "display_name": "Doubao Seed 1.6",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.52"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.204"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.51"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-06-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 1.6"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-6-flash",
   "model_name": "doubao-seed-1-6-flash",
   "display_name": "Doubao Seed 1.6 Flash",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.022059"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.004412"
      }
     },
     "provider_model_id": "doubao-seed-1.6-flash"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02174"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21739"
      }
     },
     "provider_model_id": "doubao-seed-1.6-flash"
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-08-15",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubao-seed-1.6-flash"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-Seed-1.6-flash 是一款超快多模态深度推理模型，TPOT 低至 10ms，支持文本与图像输入，在文本理解上超越前代 lite 模型，在视觉方面媲美主流 pro 模型。支持 256k 上下文窗口和最多 16k 输出 token。",
    "zh-TW": "Doubao-Seed-1.6-flash 是一款極速多模態深度推理模型，TPOT 低至 10ms。支援文字與圖像，文字理解超越前代 lite 模型，視覺能力媲美競品 pro 模型。支援 256k 上下文視窗與最多 16k 輸出字元。",
    "ja-JP": "Doubao-Seed-1.6-flash は、TPOTが10msと非常に低い超高速マルチモーダル深層推論モデルです。テキストと画像の両方に対応し、テキスト理解では従来のliteモデルを上回り、視覚では競合のproモデルに匹敵します。256kのコンテキストウィンドウと最大16kの出力トークンに対応します。",
    "ru-RU": "Doubao-Seed-1.6-flash — ультрабыстрая мультимодальная модель глубокого рассуждения с TPOT до 10 мс. Поддерживает текст и изображения, превосходит предыдущую lite-модель в понимании текста и сопоставима с pro-моделями в области зрения. Поддерживает контекстное окно 256k и до 16k токенов вывода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 1.6 Flash"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-6-flash-250615",
   "model_name": "doubao-seed-1-6-flash-250615",
   "display_name": "Doubao Seed 1.6 Flash",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.021"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0374"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.374"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-06-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 1.6 Flash"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-6-lite",
   "model_name": "doubao-seed-1-6-lite",
   "display_name": "doubao-seed-1-6-lite",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.082"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.656"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-seed-1-6-lite"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-6-thinking",
   "model_name": "doubao-seed-1-6-thinking",
   "display_name": "Doubao-Seed 1.6 Thinking",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11594"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15942"
      }
     },
     "provider_model_id": "doubao-seed-1.6-thinking"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-08-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubao-seed-1.6-thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao-Seed 1.6 Thinking"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-6-thinking-250615",
   "model_name": "doubao-seed-1-6-thinking-250615",
   "display_name": "Doubao Seed 1.6 Thinking",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.52"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.204"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.04"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-06-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 1.6 Thinking"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-6-thinking-250715",
   "model_name": "doubao-seed-1-6-thinking-250715",
   "display_name": "doubao-seed-1-6-thinking-250715",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.121"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.21"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-07-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-seed-1-6-thinking-250715"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-6-vision-250815",
   "model_name": "doubao-seed-1-6-vision-250815",
   "display_name": "doubao-seed-1-6-vision-250815",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.114"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.143"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.10959"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.0959"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.021918"
      }
     }
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2025-09-30",
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-seed-1-6-vision-250815"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-8",
   "model_name": "doubao-seed-1-8",
   "display_name": "Doubao Seed 1.8",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.352941"
      },
      "completion_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_032_0_128_0_infinity": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "completion_0_128_0_256_0_infinity": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.023529"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "doubao-seed-1.8"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.10959"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.273975"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.021918"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0024"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0024"
      }
     },
     "provider_model_id": "volcengine/doubao-seed-1.8",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "completion": "12.178571"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "released_at": "2025-12-18",
   "max_input_tokens": 256000,
   "max_output_tokens": 64000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "knowledge_cutoff": "2025-01",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/doubao-seed-1.8",
    "doubao-seed-1.8",
    "volcengine/doubao-seed-1.8"
   ],
   "intro_i18n": {
    "zh-CN": "豆包 Seed-1.8 拥有更强的多模态理解与智能体能力，支持文本/图像/视频输入与上下文缓存，在复杂任务中表现出色。",
    "zh-TW": "豆包 Seed-1.8 擁有更強的多模態理解與智能體能力，支援文字／圖片／影片輸入與上下文快取，在複雜任務中展現優異表現。",
    "ja-JP": "Doubao-Seed-1.8は、マルチモーダル理解とエージェント機能が強化されており、テキスト・画像・動画の入力とコンテキストキャッシュをサポートします。複雑なタスクにおいても優れたパフォーマンスを発揮します。",
    "ru-RU": "Doubao-Seed-1.8 обладает улучшенным мультимодальным пониманием и агентными возможностями, поддерживает ввод текста, изображений и видео, а также кэширование контекста, обеспечивая высокую эффективность при выполнении сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 1.8"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-8-251215",
   "model_name": "doubao-seed-1-8-251215",
   "display_name": "doubao-seed-1-8-251215",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.114"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.612"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.12"
      }
     }
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2025-12-18",
   "max_input_tokens": 224000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-seed-1-8-251215"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1-8-251228",
   "model_name": "doubao-seed-1-8-251228",
   "display_name": "doubao-seed-1-8-251228",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1103"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1034"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "video_input": true
   },
   "max_input_tokens": 256000,
   "max_output_tokens": 64000,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-seed-1-8-251228"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-1.6-vision",
   "model_name": "doubao-seed-1.6-vision",
   "display_name": "Doubao Seed 1.6 Vision",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.352941"
      },
      "prompt_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "0.705882"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "completion_0_128_infinity": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.023529"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Doubao-Seed-1.6-vision 是一款视觉深度推理模型，具备更强的多模态理解与推理能力，适用于教育、图像审核、安检和 AI 搜索问答等场景。支持 256k 上下文窗口和最多 64k 输出 token。",
    "zh-TW": "Doubao-Seed-1.6-vision 是一款視覺深度推理模型，針對教育、圖像審查、檢測/安防與 AI 搜尋問答等場景提供更強的多模態理解與推理能力。支援 256k 上下文視窗與最多 64k 輸出字元。",
    "ja-JP": "Doubao-Seed-1.6-vision は、教育、画像レビュー、検査・セキュリティ、AI検索QAなどにおいて、より強力なマルチモーダル理解と推論を提供する視覚的深層推論モデルです。256kのコンテキストウィンドウと最大64kの出力トークンに対応します。",
    "ru-RU": "Doubao-Seed-1.6-vision — визуальная модель глубокого рассуждения с улучшенным мультимодальным пониманием и логикой для образования, анализа изображений, инспекции/безопасности и визуального поиска с вопросами и ответами. Поддерживает контекст до 256k и до 64k токенов вывода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 1.6 Vision"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-code",
   "model_name": "doubao-seed-2-0-code",
   "display_name": "Doubao Seed 2.0 Code",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.705882"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "1.411765"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "7.058824"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.094118"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "doubao-seed-2.0-code"
    },
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     },
     "provider_model_id": "volcengine/doubao-seed-2-0-code"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.46377"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.31884"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09275"
      }
     },
     "provider_model_id": "doubao-seed-2.0-code"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0024"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0024"
      }
     },
     "provider_model_id": "volcengine/doubao-seed-2.0-code",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.497768",
        "cache_read": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "0.75"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "released_at": "2026-02-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2025-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/doubao-seed-2.0-code",
    "doubao-seed-2.0-code",
    "volcengine/doubao-seed-2-0-code",
    "volcengine/doubao-seed-2.0-code"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-Seed-2.0-code 针对代理编程进行了深度优化，支持多模态输入和 256k 上下文窗口，适用于编程、视觉理解和代理工作流。",
    "zh-TW": "Doubao-Seed-2.0-code 深度優化於代理編程，支持多模態輸入和 256k 上下文窗口，適合編程、視覺理解和代理工作流程。",
    "ja-JP": "Doubao-Seed-2.0-codeはエージェントコーディングに深く最適化されており、マルチモーダル入力と256kのコンテキストウィンドウをサポートし、コーディング、ビジョン理解、エージェントワークフローに適しています。",
    "ru-RU": "Doubao-Seed-2.0-code глубоко оптимизирован для агентного кодирования, поддерживает мультимодальные входные данные и контекстное окно до 256k, подходящее для кодирования, понимания визуальной информации и рабочих процессов агентов."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Code"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-code-260215",
   "model_name": "doubao-seed-2-0-code-260215",
   "display_name": "doubao-seed-2.0-code",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.46"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     }
    }
   ],
   "released_at": "2026-02-14",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-seed-2.0-code"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-code-preview",
   "model_name": "doubao-seed-2-0-code-preview",
   "display_name": "Doubao Seed 2.0 Code Preview",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.41"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09644"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3.020833",
        "completion": "3",
        "cache_read": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.5",
        "completion": "1.502075",
        "cache_read": "1.499959"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2026-02-14",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Code Preview"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-code-preview-260215",
   "model_name": "doubao-seed-2-0-code-preview-260215",
   "display_name": "Doubao Seed 2.0 Code Preview",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.96"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.782"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.893"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-02-14",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Code Preview"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-lite",
   "model_name": "doubao-seed-2-0-lite",
   "display_name": "Doubao Seed 2.0 Lite",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.132353"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.529412"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.794118"
      },
      "completion_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "1.588235"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.017647"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "doubao-seed-2.0-lite"
    },
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.529412"
      }
     },
     "provider_model_id": "volcengine/doubao-seed-2-0-lite"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08696"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52174"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.017390000000000003"
      }
     },
     "provider_model_id": "doubao-seed-2.0-lite"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.51"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0024"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0024"
      }
     },
     "provider_model_id": "volcengine/doubao-seed-2.0-lite",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "completion": "2.960784",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.490196"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "released_at": "2026-02-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2026-02",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/doubao-seed-2.0-lite",
    "doubao-seed-2.0-lite",
    "volcengine/doubao-seed-2-0-lite",
    "volcengine/doubao-seed-2.0-lite"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-Seed-2.0-lite 是一款全新的多模态深度推理模型，性价比更高，是常见任务的强力选择，支持高达 256k 的上下文窗口。",
    "zh-TW": "Doubao-Seed-2.0-lite 是一款全新的多模態深度推理模型，提供更高的性價比，是常見任務的強力選擇，支持高達 256k 的上下文窗口。",
    "ja-JP": "Doubao-Seed-2.0-liteは新しいマルチモーダル深層推論モデルで、優れた価値を提供し、一般的なタスクに適した強力な選択肢で、最大256kのコンテキストウィンドウを備えています。",
    "ru-RU": "Doubao-Seed-2.0-lite — это новая мультимодальная модель глубокого рассуждения, обеспечивающая лучшую ценность и отличный выбор для общих задач, с контекстным окном до 256k."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Lite"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-lite-260215",
   "model_name": "doubao-seed-2-0-lite-260215",
   "display_name": "Doubao Seed 2.0 Lite",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.128"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.514"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09041"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.54246"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018082"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.56"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1462"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8738"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-02-14",
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Lite"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-lite-260428",
   "model_name": "doubao-seed-2-0-lite-260428",
   "display_name": "Doubao Seed 2.0 Lite 260428",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.51"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01692"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.269"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3.125",
        "completion": "2.980392",
        "cache_read": "2.997636"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.625",
        "completion": "1.490196",
        "cache_read": "1.498818"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-04-28",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Lite 260428"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-mini",
   "model_name": "doubao-seed-2-0-mini",
   "display_name": "Doubao Seed 2.0 Mini",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005882"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "doubao-seed-2.0-mini"
    },
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "volcengine/doubao-seed-2-0-mini"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.030136"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.30136"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0060272"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02899"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0058000000000000005"
      }
     },
     "provider_model_id": "doubao-seed-2.0-mini"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0024"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0024"
      }
     },
     "provider_model_id": "volcengine/doubao-seed-2.0-mini",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "completion": "4",
        "cache_read": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "released_at": "2026-02-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2026-02",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/doubao-seed-2.0-mini",
    "doubao-seed-2.0-mini",
    "volcengine/doubao-seed-2-0-mini",
    "volcengine/doubao-seed-2.0-mini"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-Seed-2.0-mini 是一款轻量级模型，响应快速且性能优异，适合小型任务和高并发场景。",
    "zh-TW": "Doubao-Seed-2.0-mini 是一款輕量級模型，響應快速且性能卓越，適合小型任務和高併發場景。",
    "ja-JP": "Doubao-Seed-2.0-miniは軽量モデルで、高速応答と高性能を実現し、小規模タスクや高並列シナリオに適しています。",
    "ru-RU": "Doubao-Seed-2.0-mini — это легковесная модель с быстрым откликом и высокой производительностью, подходящая для небольших задач и сценариев с высокой конкуренцией."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Mini"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-mini-260215",
   "model_name": "doubao-seed-2-0-mini-260215",
   "display_name": "Doubao Seed 2.0 Mini",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0285"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.115"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0493"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4845"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-02-14",
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Mini"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-mini-260428",
   "model_name": "doubao-seed-2-0-mini-260428",
   "display_name": "Doubao Seed 2.0 Mini 260428",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.00564"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.423"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3.666667",
        "completion": "4.035714",
        "cache_read": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-04-28",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Mini 260428"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-pro",
   "model_name": "doubao-seed-2-0-pro",
   "display_name": "Doubao Seed 2.0 Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.705882"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "1.411765"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "7.058824"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.094118"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "doubao-seed-2.0-pro"
    },
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     },
     "provider_model_id": "volcengine/doubao-seed-2-0-pro"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.41"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09644"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3.020833",
        "completion": "3",
        "cache_read": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.5",
        "completion": "1.502075",
        "cache_read": "1.499959"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.46377"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.31884"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09275"
      }
     },
     "provider_model_id": "doubao-seed-2.0-pro"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0024"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0024"
      }
     },
     "provider_model_id": "volcengine/doubao-seed-2.0-pro",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "completion": "2.995536",
        "cache_read": "3"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "released_at": "2026-02-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2026-02",
   "family": "seed",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/doubao-seed-2.0-pro",
    "doubao-seed-2.0-pro",
    "volcengine/doubao-seed-2-0-pro",
    "volcengine/doubao-seed-2.0-pro"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-Seed-2.0-pro 是字节跳动的旗舰级 Agent 通用模型，在复杂任务规划和执行能力上实现了全方位飞跃。",
    "zh-TW": "Doubao-Seed-2.0-pro 是字節跳動的旗艦級 Agent 通用模型，在複雜任務規劃和執行能力上實現了全方位的飛躍。",
    "ja-JP": "Doubao-Seed-2.0-proはByteDanceのフラッグシップエージェント汎用モデルで、複雑なタスクの計画と実行能力において全方位的な飛躍を遂げています。",
    "ru-RU": "Doubao-Seed-2.0-pro — это флагманская универсальная модель агента от ByteDance, обеспечивающая всесторонние прорывы в планировании и выполнении сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Pro"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-0-pro-260215",
   "model_name": "doubao-seed-2-0-pro-260215",
   "display_name": "Doubao Seed 2.0 Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.46"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.28"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.96"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.782"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.876"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-02-14",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.0 Pro"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-1-pro",
   "model_name": "doubao-seed-2-1-pro",
   "display_name": "Doubao Seed 2.1 Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.411765"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "doubao-seed-2.1-pro"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9295"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.6475"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1859"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "bytedance/doubao-seed-2.1-pro"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.11285816"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08453343"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.001193975"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.422571632"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.001193975"
      }
     },
     "provider_model_id": "bytedance/doubao-seed-2.1-pro"
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/doubao-seed-2.1-pro",
    "doubao-seed-2.1-pro"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-Seed-2.1-pro 是字节跳动新一代旗舰级通用模型，针对编码、代理规划和长链任务执行进行了优化，并具备原生多模态理解能力。",
    "zh-TW": "Doubao-Seed-2.1-pro 是字節跳動新一代的旗艦代理通用模型，針對編碼、代理規劃和長鏈任務執行進行了優化，並具備原生多模態理解能力。",
    "ja-JP": "Doubao-Seed-2.1-proはByteDanceの次世代フラッグシップエージェント汎用モデルであり、コーディング、エージェント計画、長期タスクの実行に最適化され、ネイティブなマルチモーダル理解を備えています。",
    "ru-RU": "Doubao-Seed-2.1-pro — это флагманская универсальная модель нового поколения от ByteDance, оптимизированная для программирования, агентного планирования и выполнения задач с длинной цепочкой, с встроенным мультимодальным пониманием."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.1 Pro"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-1-pro-260628",
   "model_name": "doubao-seed-2-1-pro-260628",
   "display_name": "doubao-seed-2-1-pro-260628",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.28"
      }
     }
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-seed-2-1-pro-260628"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-1-turbo",
   "model_name": "doubao-seed-2-1-turbo",
   "display_name": "Doubao Seed 2.1 Turbo",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "doubao-seed-2.1-turbo"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.46475"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.32375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09295"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "bytedance/doubao-seed-2.1-turbo"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.11285816"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08453343"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.00238795"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.422571632"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.00238795"
      }
     },
     "provider_model_id": "bytedance/doubao-seed-2.1-turbo"
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/doubao-seed-2.1-turbo",
    "doubao-seed-2.1-turbo"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-Seed-2.1-turbo 在高并发生产场景中实现了效率与性能的平衡，具备强大的推理和代理能力。",
    "zh-TW": "Doubao-Seed-2.1-turbo 在高併發生產場景中平衡了效率與性能，具備強大的推理和代理能力。",
    "ja-JP": "Doubao-Seed-2.1-turboは効率と性能のバランスを取り、高い同時実行性が求められる生産シナリオにおいて強力な推論能力とエージェント機能を提供します。",
    "ru-RU": "Doubao-Seed-2.1-turbo сочетает эффективность и производительность для высококонкурентных производственных сценариев с мощными возможностями рассуждения и агентного взаимодействия."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed 2.1 Turbo"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-2-1-turbo-260628",
   "model_name": "doubao-seed-2-1-turbo-260628",
   "display_name": "doubao-seed-2-1-turbo-260628",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.14"
      }
     }
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-seed-2-1-turbo-260628"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-character",
   "model_name": "doubao-seed-character",
   "display_name": "Doubao-Seed-Character",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2947"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0236"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1179"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "bytedance/doubao-seed-character"
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 128000,
   "capabilities": {
    "reasoning": true,
    "vision": true,
    "video_input": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/doubao-seed-character"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao-Seed-Character"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-code",
   "model_name": "doubao-seed-code",
   "display_name": "Doubao Seed Code",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.205882"
      },
      "prompt_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "0.411765"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion_0_128_0_256": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035294"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5.6"
      }
     },
     "provider_model_id": "volcengine/doubao-seed-code",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "completion": "2.008929",
        "prompt": "2.294118"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.508929",
        "prompt": "1.176471"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2025-11-11",
   "knowledge_cutoff": "2025-01",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/doubao-seed-code",
    "volcengine/doubao-seed-code"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao-Seed-Code 针对代理式编程深度优化，支持多模态输入（文本/图像/视频）和 256k 上下文窗口，兼容 Anthropic API，适用于编程、视觉理解与代理工作流。",
    "zh-TW": "Doubao-Seed-Code 專為代理式程式設計深度優化，支援多模態輸入（文字/圖片/影片）與 256k 上下文視窗，兼容 Anthropic API，適用於程式設計、視覺理解與代理工作流程。",
    "ja-JP": "Doubao-Seed-Code は、エージェント型コーディングに最適化されたモデルで、マルチモーダル入力（テキスト／画像／動画）と256kのコンテキストウィンドウに対応し、Anthropic APIと互換性があります。コーディング、視覚理解、エージェントワークフローに適しています。",
    "ru-RU": "Doubao-Seed-Code глубоко оптимизирован для агентного программирования, поддерживает мультимодальный ввод (текст/изображение/видео) и контекстное окно 256k, совместим с API Anthropic и подходит для программирования, понимания изображений и рабочих процессов агентов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed Code"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-code-preview-251028",
   "model_name": "doubao-seed-code-preview-251028",
   "display_name": "doubao-seed-code-preview-251028",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14"
      }
     }
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2025-11-11",
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-seed-code-preview-251028"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-code-preview-latest",
   "model_name": "doubao-seed-code-preview-latest",
   "display_name": "doubao-seed-code-preview-latest",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1429"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "released_at": "2025-11-11",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubao-seed-code-preview-latest"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seed-evolving",
   "model_name": "doubao-seed-evolving",
   "display_name": "Doubao Seed Evolving",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.411765"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.11285816"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08453343"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.001193975"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.422571632"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.001193975"
      }
     },
     "provider_model_id": "bytedance/doubao-seed-evolving"
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/doubao-seed-evolving"
   ],
   "intro_i18n": {
    "zh-CN": "Doubao Seed Evolving 采用自我进化机制，每周持续更新，确保模型性能始终处于前沿水平。",
    "zh-TW": "Doubao Seed Evolving 採用自我進化機制，通過每週持續更新，保持模型性能處於最前沿。",
    "ja-JP": "Doubao Seed Evolvingは自己進化メカニズムを採用し、毎週の継続的なアップデートによってモデル性能を最先端に保ちます。",
    "ru-RU": "Doubao Seed Evolving использует механизм саморазвития с еженедельными обновлениями, чтобы поддерживать производительность модели на передовом уровне."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao Seed Evolving"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seedance-1-0-pro-250528",
   "model_name": "doubao-seedance-1-0-pro-250528",
   "display_name": "Seedance 1.0 Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      }
     }
    }
   ],
   "released_at": "2025-05-28",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Seedance 1.0 Pro 是一个支持多镜头叙事的视频生成基础模型，能够在多个维度上表现出色。该模型在语义理解和指令执行方面取得了突破，能够生成1080P高清视频，画面流畅、细节丰富、风格多样，并具有电影级视觉美感。",
    "zh-TW": "Seedance 1.0 Pro 是一款支持多鏡頭敘事的影片生成基礎模型，能在多個維度上展現強大性能。該模型在語義理解和指令執行方面實現突破，能生成1080P高清影片，具備流暢的動作、豐富的細節、多樣的風格以及電影級的視覺美感。",
    "ja-JP": "Seedance 1.0 Proは、マルチショットストーリーテリングをサポートする動画生成基盤モデルです。複数の次元で優れた性能を発揮します。このモデルは、意味理解と指示追従において画期的な進歩を遂げ、滑らかな動き、豊かなディテール、多様なスタイル、映画レベルの視覚美学を備えた1080P高解像度動画を生成することが可能です。",
    "ru-RU": "Seedance 1.0 Pro — это базовая модель генерации видео, поддерживающая многокадровое повествование. Она демонстрирует высокую производительность по нескольким параметрам. Модель достигает прорыва в семантическом понимании и следовании инструкциям, что позволяет ей создавать видео в формате 1080P с плавным движением, богатыми деталями, разнообразными стилями и визуальной эстетикой кинематографического уровня."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance 1.0 Pro"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seedance-1-0-pro-fast-251015",
   "model_name": "doubao-seedance-1-0-pro-fast-251015",
   "display_name": "Seedance 1.0 Pro Fast",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_M_tokens",
       "price": "0.617647"
      }
     }
    }
   ],
   "released_at": "2025-10-15",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Seedance 1.0 Pro Fast 是一个综合模型，旨在降低成本的同时最大化性能，在视频生成质量、速度和价格之间实现卓越平衡。它继承了 Seedance 1.0 Pro 的核心优势，同时提供更快的生成速度和更具竞争力的价格，为创作者带来效率与成本的双重优化。",
    "zh-TW": "Seedance 1.0 Pro Fast 是一款綜合模型，旨在降低成本的同時最大化性能，實現影片生成品質、速度與價格的卓越平衡。它繼承了 Seedance 1.0 Pro 的核心優勢，並提供更快的生成速度和更具競爭力的價格，為創作者帶來效率與成本的雙重優化。",
    "ja-JP": "Seedance 1.0 Pro Fastは、コストを最小化しながら性能を最大化することを目的とした包括的なモデルで、動画生成品質、速度、価格の優れたバランスを実現します。Seedance 1.0 Proの主要な強みを継承しつつ、より高速な生成速度と競争力のある価格を提供し、クリエイターに効率とコストの二重最適化をもたらします。",
    "ru-RU": "Seedance 1.0 Pro Fast — это универсальная модель, разработанная для минимизации затрат при максимизации производительности, достигая отличного баланса между качеством генерации видео, скоростью и ценой. Она наследует основные преимущества Seedance 1.0 Pro, предлагая при этом более высокую скорость генерации и более конкурентоспособные цены, обеспечивая создателям двойную оптимизацию эффективности и стоимости."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance 1.0 Pro Fast"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seedance-1-5-pro-251215",
   "model_name": "doubao-seedance-1-5-pro-251215",
   "display_name": "Seedance 1.5 Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output_false": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "video_output_true": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    }
   ],
   "released_at": "2025-12-15",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "字节跳动的 Seedance 1.5 Pro 支持文本生成视频、图像生成视频（首帧、首尾帧）以及与视觉同步的音频生成。",
    "zh-TW": "由字節跳動推出的 Seedance 1.5 Pro 支持文字轉影片、圖像轉影片（第一幀、首尾幀）以及與視覺同步的音頻生成。",
    "ja-JP": "ByteDanceのSeedance 1.5 Proは、テキストから動画、画像から動画（初期フレーム、初期+最終フレーム）、および視覚と同期した音声生成をサポートします。",
    "ru-RU": "Seedance 1.5 Pro от ByteDance поддерживает текст-видео, изображение-видео (первый кадр, первый+последний кадр) и генерацию аудио, синхронизированного с визуальными эффектами."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance 1.5 Pro"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seedance-2-0-260128",
   "model_name": "doubao-seedance-2-0-260128",
   "display_name": "Seedance 2.0",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_M_tokens",
       "price": "5.441176"
      }
     }
    }
   ],
   "released_at": "2026-01-28",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "字节跳动的Seedance 2.0是最强大的视频生成模型，支持多模态参考视频生成、视频编辑、视频扩展、文本转视频和图像转视频，并同步音频。",
    "zh-TW": "字節跳動的Seedance 2.0是最強大的影像生成模型，支持多模態參考影像生成、影像編輯、影像擴展、文字生成影像及影像生成影像，並同步音頻。",
    "ja-JP": "ByteDanceのSeedance 2.0は、最も強力なビデオ生成モデルで、マルチモーダル参照ビデオ生成、ビデオ編集、ビデオ拡張、テキストからビデオ、画像からビデオへの変換を同期音声付きでサポートします。",
    "ru-RU": "Seedance 2.0 от ByteDance — самая мощная модель генерации видео, поддерживающая мультимодальную генерацию видео по ссылке, редактирование видео, расширение видео, преобразование текста в видео и изображения в видео с синхронизированным звуком."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance 2.0"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seedance-2-0-fast-260128",
   "model_name": "doubao-seedance-2-0-fast-260128",
   "display_name": "Seedance 2.0 Fast",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_M_tokens",
       "price": "6.764706"
      }
     }
    }
   ],
   "released_at": "2026-01-28",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "字节跳动的Seedance 2.0 Fast提供与Seedance 2.0相同的功能，但生成速度更快，价格更具竞争力。",
    "zh-TW": "字節跳動的Seedance 2.0 Fast提供與Seedance 2.0相同的功能，但生成速度更快，價格更具競爭力。",
    "ja-JP": "ByteDanceのSeedance 2.0 Fastは、Seedance 2.0と同じ機能を提供しながら、より高速な生成速度と競争力のある価格を実現します。",
    "ru-RU": "Seedance 2.0 Fast от ByteDance предлагает те же возможности, что и Seedance 2.0, с более высокой скоростью генерации и более конкурентоспособной ценой."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance 2.0 Fast"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seedream-4-0-250828",
   "model_name": "doubao-seedream-4-0-250828",
   "display_name": "Seedream 4.0",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     }
    }
   ],
   "released_at": "2025-09-09",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Seedream 4.0 是字节跳动 Seed 推出的图像生成模型，支持文本与图像输入，具备高度可控的高质量图像生成能力。可根据文本提示生成图像。",
    "zh-TW": "Seedream 4.0 是字節跳動 Seed 團隊推出的圖像生成模型，支援文字與圖像輸入，實現高度可控、高品質的圖像生成。可根據文字提示生成圖像。",
    "ja-JP": "Seedream 4.0 は ByteDance Seed による画像生成モデルで、テキストと画像入力に対応し、高品質かつ制御性の高い画像生成を実現します。テキストプロンプトから画像を生成します。",
    "ru-RU": "Seedream 4.0 — модель генерации изображений от ByteDance Seed, поддерживающая ввод текста и изображений с высококачественной и управляемой генерацией. Генерирует изображения по текстовым подсказкам."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedream 4.0"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seedream-4-5-251128",
   "model_name": "doubao-seedream-4-5-251128",
   "display_name": "Seedream 4.5",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.036765"
      }
     }
    }
   ],
   "released_at": "2025-11-28",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Seedream 4.5是字节跳动最新的多模态图像模型，集成了文本生成图像、图像生成图像和批量图像生成功能，同时具备常识和推理能力。与之前的4.0版本相比，生成质量显著提升，编辑一致性和多图融合效果更好。它对视觉细节的控制更加精确，能够更自然地生成小文字和小面部，并实现更和谐的布局和色彩，提升整体美感。",
    "zh-TW": "Seedream 4.5 是字節跳動最新的多模態圖像模型，整合了文本生成圖像、圖像生成圖像和批量圖像生成功能，同時融入了常識和推理能力。與之前的 4.0 版本相比，生成質量顯著提升，編輯一致性和多圖融合效果更好。它對視覺細節的控制更加精確，能更自然地生成小字和小臉，並實現更和諧的佈局和色彩，提升整體美感。",
    "ja-JP": "Seedream 4.5はByteDanceの最新マルチモーダル画像モデルで、テキストから画像生成、画像間変換、バッチ画像生成機能を統合し、常識と推論能力を組み込んでいます。前バージョン4.0と比較して、生成品質が大幅に向上し、編集の一貫性や複数画像の融合が改善されています。視覚的な詳細の制御がより正確になり、小さなテキストや顔を自然に生成し、レイアウトや色彩の調和が向上し、全体的な美観が強化されています。",
    "ru-RU": "Seedream 4.5 — это последняя мультимодальная модель изображений от ByteDance, объединяющая возможности преобразования текста в изображение, изображения в изображение и пакетной генерации изображений, а также включающая здравый смысл и способности к рассуждению. По сравнению с предыдущей версией 4.0, она обеспечивает значительно улучшенное качество генерации, лучшую согласованность редактирования и слияние нескольких изображений. Модель предлагает более точный контроль над визуальными деталями, естественно воспроизводя мелкий текст и лица, а также достигает более гармоничного макета и цветовой палитры, улучшая общую эстетику."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedream 4.5"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-seedream-5-0-260128",
   "model_name": "doubao-seedream-5-0-260128",
   "display_name": "Seedream 5.0 Lite",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "bytedance",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.032353"
      }
     }
    }
   ],
   "released_at": "2026-01-28",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Doubao-Seedream-5.0-lite是字节跳动最新的图像生成模型。首次集成在线检索功能，能够结合实时网络信息，提升生成图像的时效性。模型智能性也得到升级，能够精确解析复杂指令和视觉内容。此外，它在专业场景中的全球知识覆盖、参考一致性和生成质量方面均有提升，更好地满足企业级视觉创作需求。",
    "zh-TW": "Doubao-Seedream-5.0-lite 是字節跳動最新的圖像生成模型。首次整合了在線檢索功能，能夠結合實時網絡信息，提升生成圖像的時效性。模型的智能性也得到了升級，能夠精確解讀複雜指令和視覺內容。此外，它在專業場景中的全球知識覆蓋、參考一致性和生成質量方面均有改進，更好地滿足企業級視覺創作需求。",
    "ja-JP": "Doubao-Seedream-5.0-liteはByteDanceの最新画像生成モデルです。初めてオンライン検索機能を統合し、リアルタイムのウェブ情報を取り入れることで生成画像のタイムリー性を向上させています。モデルの知能もアップグレードされ、複雑な指示や視覚コンテンツを正確に解釈できるようになりました。また、専門的なシナリオでのグローバルな知識カバレッジ、一貫性、生成品質が向上し、企業レベルの視覚制作ニーズにより適合しています。",
    "ru-RU": "Doubao-Seedream-5.0-lite — это последняя модель генерации изображений от ByteDance. Впервые она интегрирует возможности онлайн-поиска, что позволяет использовать информацию в реальном времени и улучшать актуальность создаваемых изображений. Интеллект модели также был обновлен, что позволяет точно интерпретировать сложные инструкции и визуальный контент. Кроме того, она предлагает улучшенное покрытие глобальных знаний, согласованность ссылок и качество генерации в профессиональных сценариях, лучше удовлетворяя потребности корпоративного визуального творчества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedream 5.0 Lite"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-Vision-Lite-32k",
   "model_name": "doubao-Vision-Lite-32k",
   "display_name": "Doubao-Vision-Lite-32k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "released_at": "2024-12-18",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao-Vision-Lite-32k"
    }
   ]
  },
  {
   "slug": "bytedance/doubao-vision-pro-32k",
   "model_name": "doubao-vision-pro-32k",
   "display_name": "Doubao-vision-pro-32k",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "released_at": "2024-12-13",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Doubao-vision-pro-32k"
    }
   ]
  },
  {
   "slug": "bytedance/dreamina-seedance-2-0-260128",
   "model_name": "dreamina-seedance-2-0-260128",
   "display_name": "dreamina-seedance-2-0-260128",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      }
     },
     "provider_model_id": "byteplus/dreamina-seedance-2-0-260128"
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "byteplus/dreamina-seedance-2-0-260128"
   ],
   "intro_i18n": {
    "zh-CN": "字节跳动推出的 Seedance 2.0 是最强大的视频生成模型，支持多模态参考视频生成、视频编辑、视频扩展、文本生成视频以及图像生成视频，并同步生成音频。",
    "zh-TW": "字節跳動的 Seedance 2.0 是最強大的視頻生成模型，支持多模態參考視頻生成、視頻編輯、視頻擴展、文本生成視頻以及圖像生成視頻，並同步音頻。",
    "ja-JP": "ByteDanceのSeedance 2.0は、マルチモーダル参照ビデオ生成、ビデオ編集、ビデオ拡張、テキストからビデオ、画像からビデオへの同期音声付き生成をサポートする最も強力なビデオ生成モデルです。",
    "ru-RU": "Seedance 2.0 от ByteDance — самая мощная модель генерации видео, поддерживающая мультимодальную генерацию видео по референсам, редактирование видео, расширение видео, преобразование текста в видео и изображений в видео с синхронизированным звуком."
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "prompt_caching: true→false"
    },
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "pdf_input: true→false"
    },
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "video_input: true→false"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "dreamina-seedance-2-0-260128"
    }
   ]
  },
  {
   "slug": "bytedance/dreamina-seedance-2-0-mini-hc",
   "model_name": "dreamina-seedance-2-0-mini-hc",
   "display_name": "dreamina-seedance-2-0-mini-hc",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "dreamina-seedance-2-0-mini-hc"
    }
   ]
  },
  {
   "slug": "bytedance/glm-4-7-251222",
   "model_name": "glm-4-7-251222",
   "display_name": "glm-4-7-251222",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "volcengine",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "bytedance/kimi-k2-thinking-251104",
   "model_name": "kimi-k2-thinking-251104",
   "display_name": "kimi-k2-thinking-251104",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "volcengine",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 229376,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "bytedance/seed-1-6",
   "model_name": "seed-1-6",
   "display_name": "Seed 1.6",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "bytedance-seed/seed-1.6"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "bytedance-seed/seed-1.6"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "bytedance/seed-1.6",
     "tracks": [
      {
       "label": ">128.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-09-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance-seed/seed-1.6",
    "bytedance/seed-1.6"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seed 1.6"
    }
   ]
  },
  {
   "slug": "bytedance/seed-1-6-250615",
   "model_name": "seed-1-6-250615",
   "display_name": "Seed 1.6 (250615)",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-06-25",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seed 1.6 (250615)"
    }
   ]
  },
  {
   "slug": "bytedance/seed-1-6-250915",
   "model_name": "seed-1-6-250915",
   "display_name": "Seed 1.6 (250915)",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-09-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seed 1.6 (250915)"
    }
   ]
  },
  {
   "slug": "bytedance/seed-1-6-flash",
   "model_name": "seed-1-6-flash",
   "display_name": "ByteDance Seed: Seed 1.6 Flash",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "bytedance-seed/seed-1.6-flash"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "bytedance-seed/seed-1.6-flash"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-12-23",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "family": "seed",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance-seed/seed-1.6-flash"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ByteDance Seed: Seed 1.6 Flash"
    }
   ]
  },
  {
   "slug": "bytedance/seed-1-6-flash-250715",
   "model_name": "seed-1-6-flash-250715",
   "display_name": "Seed 1.6 Flash (250715)",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-07-26",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seed 1.6 Flash (250715)"
    }
   ]
  },
  {
   "slug": "bytedance/seed-1-8-251228",
   "model_name": "seed-1-8-251228",
   "display_name": "Seed 1.8 (251228)",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-12-18",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seed 1.8 (251228)"
    }
   ]
  },
  {
   "slug": "bytedance/Seed-1.8",
   "model_name": "Seed-1.8",
   "display_name": "Seed 1.8",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "ByteDance/Seed-1.8"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "deepinfra/ByteDance/Seed-1.8"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "bytedance/seed-1.8",
     "tracks": [
      {
       "label": ">128.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-09-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 256000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance/Seed-1.8",
    "bytedance/seed-1.8",
    "deepinfra/ByteDance/Seed-1.8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seed 1.8"
    }
   ]
  },
  {
   "slug": "bytedance/seed-2-0-code-preview-260328",
   "model_name": "seed-2-0-code-preview-260328",
   "display_name": "seed-2-0-code-preview-260328",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.008333"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "seed-2-0-code-preview-260328"
    }
   ]
  },
  {
   "slug": "bytedance/seed-2-0-lite-260428",
   "model_name": "seed-2-0-lite-260428",
   "display_name": "seed-2-0-lite-260428",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.008333"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "seed-2-0-lite-260428"
    }
   ]
  },
  {
   "slug": "bytedance/seed-2-0-mini",
   "model_name": "seed-2-0-mini",
   "display_name": "ByteDance Seed: Seed-2.0-Mini",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "ByteDance/Seed-2.0-mini"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "bytedance-seed/seed-2.0-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "bytedance-seed/seed-2.0-mini"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1263"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5051"
      }
     },
     "provider_model_id": "seed-2.0-mini"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "deepinfra/ByteDance/Seed-2.0-mini"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-02-27",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "family": "seed",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance/Seed-2.0-mini",
    "bytedance-seed/seed-2.0-mini",
    "deepinfra/ByteDance/Seed-2.0-mini",
    "seed-2.0-mini"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ByteDance Seed: Seed-2.0-Mini"
    }
   ]
  },
  {
   "slug": "bytedance/seed-2-0-mini-260428",
   "model_name": "seed-2-0-mini-260428",
   "display_name": "seed-2-0-mini-260428",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.039999999999999994"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.00833"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.039999999999999994"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "seed-2-0-mini-260428"
    }
   ]
  },
  {
   "slug": "bytedance/seed-2-0-pro-260328",
   "model_name": "seed-2-0-pro-260328",
   "display_name": "seed-2-0-pro-260328",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.008333"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "seed-2-0-pro-260328"
    }
   ]
  },
  {
   "slug": "bytedance/Seed-2.0-code",
   "model_name": "Seed-2.0-code",
   "display_name": "ByteDance/Seed-2.0-code",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "ByteDance/Seed-2.0-code"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6313"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.7879"
      }
     },
     "provider_model_id": "seed-2.0-code"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepinfra/ByteDance/Seed-2.0-code"
    }
   ],
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "prompt_caching": true,
    "function_calling": true,
    "vision": true,
    "reasoning": true,
    "pdf_input": true,
    "video_input": true
   },
   "max_output_tokens": 256000,
   "released_at": "2026-04-22",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance/Seed-2.0-code",
    "deepinfra/ByteDance/Seed-2.0-code",
    "seed-2.0-code"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ByteDance/Seed-2.0-code"
    }
   ]
  },
  {
   "slug": "bytedance/seed-2.0-lite",
   "model_name": "seed-2.0-lite",
   "display_name": "ByteDance Seed: Seed-2.0-Lite",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "bytedance-seed/seed-2.0-lite"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "bytedance-seed/seed-2.0-lite"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "bytedance-seed/seed-2.0-lite"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3157"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5253"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-03-10",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "family": "seed",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance-seed/seed-2.0-lite"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ByteDance Seed: Seed-2.0-Lite"
    }
   ]
  },
  {
   "slug": "bytedance/Seed-2.0-pro",
   "model_name": "Seed-2.0-pro",
   "display_name": "ByteDance/Seed-2.0-pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "ByteDance/Seed-2.0-pro"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6313"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.7879"
      }
     },
     "provider_model_id": "seed-2.0-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepinfra/ByteDance/Seed-2.0-pro"
    }
   ],
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "max_output_tokens": 256000,
   "released_at": "2026-03-26",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance/Seed-2.0-pro",
    "deepinfra/ByteDance/Seed-2.0-pro",
    "seed-2.0-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ByteDance/Seed-2.0-pro"
    }
   ]
  },
  {
   "slug": "bytedance/Seed-OSS-36B-Instruct",
   "model_name": "Seed-OSS-36B-Instruct",
   "display_name": "ByteDance-Seed/Seed-OSS-36B-Instruct",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.534"
      }
     },
     "provider_model_id": "ByteDance-Seed/Seed-OSS-36B-Instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/seed-oss-36b-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "bytedance/seed-oss-36b-instruct"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     },
     "provider_model_id": "ByteDance-Seed/Seed-OSS-36B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "ByteDance-Seed/Seed-OSS-36B-Instruct"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "ByteDance-Seed/Seed-OSS-36B-Instruct"
    }
   ],
   "intro": "Tool-capable chat model for instruction following and agentic application workflows",
   "released_at": "2025-09-04",
   "max_input_tokens": 262000,
   "max_output_tokens": 262000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance-Seed/Seed-OSS-36B-Instruct",
    "accounts/fireworks/models/seed-oss-36b-instruct",
    "bytedance/seed-oss-36b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Seed-OSS 是字节跳动 Seed 团队推出的开源大模型系列，具备强大的长上下文处理、推理、智能体和通用能力。Seed-OSS-36B-Instruct 是一款 360 亿参数的指令微调模型，原生支持超长上下文，适用于处理大型文档或代码库。该模型在推理、代码生成和智能体任务（工具使用）方面表现出色，同时保留强大的通用能力。其核心特性“思维预算”可灵活控制推理长度，提升效率。",
    "zh-TW": "Seed-OSS 是字節跳動 Seed 團隊推出的開源 LLM 系列，具備強大的長上下文處理、推理、代理與通用能力。Seed-OSS-36B-Instruct 是一款 360 億參數的指令微調模型，原生支援超長上下文，適用於處理大型文件或程式碼庫。針對推理、程式碼生成與代理任務（工具使用）進行優化，同時保有強大的通用能力。其關鍵特性為「思考預算」，可靈活調整推理長度以提升效率。",
    "ja-JP": "Seed-OSSは、ByteDance Seedが開発したオープンソースのLLMファミリーで、長文処理、推論、エージェント、汎用能力に優れています。Seed-OSS-36B-Instructは、36Bの命令調整済みモデルで、超長文コンテキストにネイティブ対応し、大規模な文書やコードベースの処理に最適です。推論、コード生成、エージェントタスク（ツール使用）に最適化され、汎用能力も維持しています。特徴的な「Thinking Budget」機能により、柔軟な推論長を実現し、効率を向上させます。",
    "ru-RU": "Seed-OSS — семейство открытых LLM от ByteDance Seed, разработанных для обработки длинного контекста, логического мышления, агентных задач и общих способностей. Seed-OSS-36B-Instruct — это модель с 36 миллиардами параметров, адаптированная под инструкции, с нативной поддержкой ультрадлинного контекста для обработки больших документов или кодовых баз. Оптимизирована для логики, генерации кода и агентных задач (использование инструментов), сохраняя при этом общую универсальность. Ключевая особенность — \"Бюджет мышления\", позволяющий гибко управлять длиной рассуждений для повышения эффективности."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ByteDance-Seed/Seed-OSS-36B-Instruct"
    }
   ]
  },
  {
   "slug": "bytedance/seed-rp",
   "model_name": "seed-rp",
   "display_name": "seed-rp",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 524288,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "seed-rp"
    }
   ]
  },
  {
   "slug": "bytedance/Seedance-1.0-lite",
   "model_name": "Seedance-1.0-lite",
   "display_name": "Seedance-1.0-lite",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.14"
      }
     },
     "provider_model_id": "ByteDance/Seedance-1.0-lite"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance/Seedance-1.0-lite"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance-1.0-lite"
    }
   ]
  },
  {
   "slug": "bytedance/Seedance-1.0-pro",
   "model_name": "Seedance-1.0-pro",
   "display_name": "Seedance-1.0-pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.57"
      }
     },
     "provider_model_id": "ByteDance/Seedance-1.0-pro"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance/Seedance-1.0-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance-1.0-pro"
    }
   ]
  },
  {
   "slug": "bytedance/seedance-2",
   "model_name": "seedance-2",
   "display_name": "Seedance 2",
   "vendor": "bytedance",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-04-01",
   "max_input_tokens": 4096,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "seed",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/seedance-2"
   ],
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance 2"
    }
   ]
  },
  {
   "slug": "bytedance/Seedance-2.0",
   "model_name": "Seedance-2.0",
   "display_name": "Seedance 2.0",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.3"
      }
     },
     "provider_model_id": "ByteDance/Seedance-2.0"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_input": {
       "unit": "per_M_tokens",
       "price": "7"
      },
      "video_input_with_video": {
       "unit": "per_M_tokens",
       "price": "4.3"
      }
     },
     "provider_model_id": "bytedance/seedance-2.0"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-04-14",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance/Seedance-2.0",
    "bytedance/seedance-2.0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance 2.0"
    }
   ]
  },
  {
   "slug": "bytedance/seedance-2.0-fast",
   "model_name": "seedance-2.0-fast",
   "display_name": "Seedance 2.0 Fast",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_input": {
       "unit": "per_M_tokens",
       "price": "5.6"
      },
      "video_input_with_video": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     },
     "provider_model_id": "bytedance/seedance-2.0-fast"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-04-14",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/seedance-2.0-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance 2.0 Fast"
    }
   ]
  },
  {
   "slug": "bytedance/seedance-v1.0-pro",
   "model_name": "seedance-v1.0-pro",
   "display_name": "Seedance v1.0 Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_480p": {
       "unit": "per_second",
       "price": "0.0243"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.0515"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.1224"
      }
     },
     "provider_model_id": "bytedance/seedance-v1.0-pro"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-06-11",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "seed",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/seedance-v1.0-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance v1.0 Pro"
    }
   ]
  },
  {
   "slug": "bytedance/seedance-v1.0-pro-fast",
   "model_name": "seedance-v1.0-pro-fast",
   "display_name": "Seedance v1.0 Pro Fast",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_480p": {
       "unit": "per_second",
       "price": "0.0097"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.0206"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.049"
      }
     },
     "provider_model_id": "bytedance/seedance-v1.0-pro-fast"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-10-24",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "seed",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/seedance-v1.0-pro-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance v1.0 Pro Fast"
    }
   ]
  },
  {
   "slug": "bytedance/seedance-v1.5-pro",
   "model_name": "seedance-v1.5-pro",
   "display_name": "Seedance v1.5 Pro",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_480p": {
       "unit": "per_second",
       "price": "0.0121"
      },
      "video_output_480p_audio": {
       "unit": "per_second",
       "price": "0.0241"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.0259"
      },
      "video_output_720p_audio": {
       "unit": "per_second",
       "price": "0.0518"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.0583"
      },
      "video_output_1080p_audio": {
       "unit": "per_second",
       "price": "0.1166"
      }
     },
     "provider_model_id": "bytedance/seedance-v1.5-pro"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-12-16",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "seed",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/seedance-v1.5-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedance v1.5 Pro"
    }
   ]
  },
  {
   "slug": "bytedance/Seedream-3.0",
   "model_name": "Seedream-3.0",
   "display_name": "Seedream-3.0",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.018"
      }
     },
     "provider_model_id": "ByteDance-Seed/Seedream-3.0"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance-Seed/Seedream-3.0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedream-3.0"
    }
   ]
  },
  {
   "slug": "bytedance/Seedream-4",
   "model_name": "Seedream-4",
   "display_name": "Seedream-4",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "ByteDance/Seedream-4"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance/Seedream-4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedream-4"
    }
   ]
  },
  {
   "slug": "bytedance/Seedream-4.0",
   "model_name": "Seedream-4.0",
   "display_name": "Seedream 4.0",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "ByteDance-Seed/Seedream-4.0"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "bytedance/seedream-4.0"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-09-09",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance-Seed/Seedream-4.0",
    "bytedance/seedream-4.0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedream 4.0"
    }
   ]
  },
  {
   "slug": "bytedance/Seedream-4.5",
   "model_name": "Seedream-4.5",
   "display_name": "Seedream 4.5",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "ByteDance/Seedream-4.5"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "bytedance-seed/seedream-4.5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "bytedance/seedream-4.5"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-12-03",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance/Seedream-4.5",
    "bytedance-seed/seedream-4.5",
    "bytedance/seedream-4.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedream 4.5"
    }
   ]
  },
  {
   "slug": "bytedance/Seedream-5.0-lite",
   "model_name": "Seedream-5.0-lite",
   "display_name": "Seedream 5.0 Lite",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ByteDance-Seed/Seedream-5.0-lite"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.063"
      }
     },
     "provider_model_id": "bytedance-seed/seedream-5.0-lite"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.035"
      }
     },
     "provider_model_id": "bytedance/seedream-5.0-lite"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-02-13",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "seed",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ByteDance-Seed/Seedream-5.0-lite",
    "ByteDance/Seedream-5.0-lite",
    "bytedance-seed/seedream-5.0-lite",
    "bytedance/seedream-5.0-lite"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Seedream 5.0 Lite"
    }
   ]
  },
  {
   "slug": "bytedance/siliconflow-bytedance-seed-seed-oss-36b-Instruct",
   "model_name": "siliconflow-bytedance-seed-seed-oss-36b-Instruct",
   "display_name": "ByteDance-Seed/Seed-OSS-36B-Instruct",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5715"
      }
     }
    }
   ],
   "released_at": "2025-09-05",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ByteDance-Seed/Seed-OSS-36B-Instruct"
    }
   ]
  },
  {
   "slug": "bytedance/sophnet-seed-oss-36b-instruct",
   "model_name": "sophnet-seed-oss-36b-instruct",
   "display_name": "sophnet/Seed-OSS-36B-Instruct",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.172"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.715"
      }
     }
    }
   ],
   "released_at": "2025-09-09",
   "max_input_tokens": 512000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Seed-OSS-36B-Instruct"
    }
   ]
  },
  {
   "slug": "bytedance/ui-tars-1.5-7b",
   "model_name": "ui-tars-1.5-7b",
   "display_name": "ByteDance: UI-TARS 7B ",
   "vendor": "bytedance",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "bytedance/ui-tars-1.5-7b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "bytedance/ui-tars-1.5-7b"
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2025-07-23",
   "max_input_tokens": 128000,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2025-01",
   "docs_url": "https://openrouter.ai/api/v1/models/bytedance/ui-tars-1.5-7b",
   "model_type": "vision_understanding",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bytedance/ui-tars-1.5-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ByteDance: UI-TARS 7B "
    }
   ]
  },
  {
   "slug": "cohere/aihubmix-Cohere-command-r",
   "model_name": "aihubmix-Cohere-command-r",
   "display_name": "aihubmix-Cohere-command-r",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.92"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Cohere-command-r"
    }
   ]
  },
  {
   "slug": "cohere/aihubmix-command-r-08-2024",
   "model_name": "aihubmix-command-r-08-2024",
   "display_name": "aihubmix-command-r-08-2024",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-command-r-08-2024"
    }
   ]
  },
  {
   "slug": "cohere/aihubmix-command-r-plus",
   "model_name": "aihubmix-command-r-plus",
   "display_name": "aihubmix-command-r-plus",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.84"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.2"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-command-r-plus"
    }
   ]
  },
  {
   "slug": "cohere/aihubmix-command-r-plus-08-2024",
   "model_name": "aihubmix-command-r-plus-08-2024",
   "display_name": "aihubmix-command-r-plus-08-2024",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.2"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-command-r-plus-08-2024"
    }
   ]
  },
  {
   "slug": "cohere/c4ai-aya-expanse-32b",
   "model_name": "c4ai-aya-expanse-32b",
   "display_name": "Aya Expanse 32B",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "intro": "Cohere command model for multilingual enterprise agents, tools, and chat",
   "released_at": "2024-10-24",
   "max_input_tokens": 128000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Aya Expanse 是一款高性能的 320 亿参数多语言模型，结合指令微调、数据套利、偏好训练和模型融合，性能媲美单语模型，支持 23 种语言。",
    "zh-TW": "Aya Expanse 是一款高效能的 320 億參數多語言模型，透過指令微調、資料仲裁、偏好訓練與模型融合，達到媲美單語模型的表現。支援 23 種語言。",
    "ja-JP": "Aya Expanseは、32Bパラメータの高性能多言語モデルで、指示チューニング、データアービトラージ、好みの学習、モデル統合を活用し、単言語モデルに匹敵する性能を実現しています。23言語に対応しています。",
    "ru-RU": "Aya Expanse — это высокопроизводительная многоязычная модель с 32 миллиардами параметров, использующая настройку по инструкциям, арбитраж данных, обучение предпочтениям и объединение моделей, чтобы конкурировать с монолингвальными моделями. Поддерживает 23 языка."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "listed",
     "note": "Aya Expanse 32B"
    }
   ]
  },
  {
   "slug": "cohere/c4ai-aya-expanse-8b",
   "model_name": "c4ai-aya-expanse-8b",
   "display_name": "Aya Expanse 8B",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "intro": "Cohere command model for multilingual enterprise agents, tools, and chat",
   "released_at": "2024-10-24",
   "max_input_tokens": 8000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Aya Expanse 是一款高性能的 80 亿参数多语言模型，结合指令微调、数据套利、偏好训练和模型融合，性能媲美单语模型，支持 23 种语言。",
    "zh-TW": "Aya Expanse 是一款高效能的 80 億參數多語言模型，透過指令微調、資料仲裁、偏好訓練與模型融合，達到媲美單語模型的表現。支援 23 種語言。",
    "ja-JP": "Aya Expanseは、8Bパラメータの高性能多言語モデルで、指示チューニング、データアービトラージ、好みの学習、モデル統合を活用し、単言語モデルに匹敵する性能を実現しています。23言語に対応しています。",
    "ru-RU": "Aya Expanse — это высокопроизводительная многоязычная модель с 8 миллиардами параметров, использующая настройку по инструкциям, арбитраж данных, обучение предпочтениям и объединение моделей, чтобы конкурировать с монолингвальными моделями. Поддерживает 23 языка."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "listed",
     "note": "Aya Expanse 8B"
    }
   ]
  },
  {
   "slug": "cohere/c4ai-aya-vision-32b",
   "model_name": "c4ai-aya-vision-32b",
   "display_name": "Aya Vision 32B",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Cohere command model for multilingual enterprise agents, tools, and chat",
   "released_at": "2025-03-04",
   "max_input_tokens": 16000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Aya Vision 是一款先进的多模态模型，在语言、文本和视觉基准测试中表现出色。该 320 亿参数版本专注于顶级多语言性能，支持 23 种语言。",
    "zh-TW": "Aya Vision 是一款先進的多模態模型，在語言、文字與視覺基準測試中表現優異。此 320 億參數版本專注於頂級多語言效能，支援 23 種語言。",
    "ja-JP": "Aya Visionは、最先端のマルチモーダルモデルで、言語、テキスト、ビジョンの主要ベンチマークで高い性能を発揮します。23言語に対応しており、この32Bバージョンは多言語性能に特化しています。",
    "ru-RU": "Aya Vision — это передовая мультимодальная модель, демонстрирующая высокие результаты на ключевых языковых, текстовых и визуальных бенчмарках. Поддерживает 23 языка. Версия с 32 миллиардами параметров ориентирована на выдающуюся многоязычную производительность."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "listed",
     "note": "Aya Vision 32B"
    }
   ]
  },
  {
   "slug": "cohere/c4ai-aya-vision-8b",
   "model_name": "c4ai-aya-vision-8b",
   "display_name": "Aya Vision 8B",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "intro": "Cohere command model for multilingual enterprise agents, tools, and chat",
   "released_at": "2025-03-04",
   "max_input_tokens": 16000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Aya Vision 是一款先进的多模态模型，在语言、文本和视觉基准测试中表现出色。该 80 亿参数版本专注于低延迟和强大性能。",
    "zh-TW": "Aya Vision 是一款先進的多模態模型，在語言、文字與視覺基準測試中表現優異。此 80 億參數版本著重於低延遲與穩定效能。",
    "ja-JP": "Aya Visionは、最先端のマルチモーダルモデルで、言語、テキスト、ビジョンの主要ベンチマークで高い性能を発揮します。この8Bバージョンは低レイテンシと高性能を重視しています。",
    "ru-RU": "Aya Vision — это передовая мультимодальная модель, демонстрирующая высокие результаты на ключевых языковых, текстовых и визуальных бенчмарках. Версия с 8 миллиардами параметров ориентирована на низкую задержку и высокую производительность."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "listed",
     "note": "Aya Vision 8B"
    }
   ]
  },
  {
   "slug": "cohere/cohere-command-a",
   "model_name": "cohere-command-a",
   "display_name": "Cohere Command A",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere/cohere-command-a"
    }
   ],
   "intro": "Cohere command model for multilingual enterprise agents, tools, and chat",
   "released_at": "2024-11-01",
   "knowledge_cutoff": "2024-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-a",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/cohere-command-a"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Command A"
    }
   ]
  },
  {
   "slug": "cohere/cohere-command-r",
   "model_name": "cohere-command-r",
   "display_name": "Cohere Command R",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere/cohere-command-r"
    }
   ],
   "intro": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
   "released_at": "2024-03-11",
   "knowledge_cutoff": "2024-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-r",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/cohere-command-r"
   ],
   "intro_i18n": {
    "zh-CN": "Command R 是一款可扩展的生成模型，专为 RAG 和工具使用场景设计，支持生产级 AI 应用。",
    "zh-TW": "Command R 是一款可擴展的生成模型，設計用於 RAG 與工具使用，支援生產級 AI 應用。",
    "ja-JP": "Command Rは、RAGやツール使用に対応したスケーラブルな生成モデルであり、実運用レベルのAIを実現します。",
    "ru-RU": "Command R — масштабируемая генеративная модель, разработанная для RAG и использования инструментов, обеспечивающая промышленный уровень ИИ."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Command R"
    }
   ]
  },
  {
   "slug": "cohere/cohere-command-r-08-2024",
   "model_name": "cohere-command-r-08-2024",
   "display_name": "Cohere Command R 08-2024",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere/cohere-command-r-08-2024"
    }
   ],
   "intro": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
   "released_at": "2024-08-01",
   "knowledge_cutoff": "2024-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-r",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/cohere-command-r-08-2024"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Command R 08-2024"
    }
   ]
  },
  {
   "slug": "cohere/cohere-command-r-plus",
   "model_name": "cohere-command-r-plus",
   "display_name": "Cohere Command R+",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere/cohere-command-r-plus"
    }
   ],
   "intro": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
   "released_at": "2024-04-04",
   "knowledge_cutoff": "2024-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-r",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/cohere-command-r-plus"
   ],
   "intro_i18n": {
    "zh-CN": "Command R+ 是一款为企业级工作负载优化的先进 RAG 模型。",
    "zh-TW": "Command R+ 是一款針對企業工作負載優化的先進 RAG 模型。",
    "ja-JP": "Command R+は、エンタープライズ向けのワークロードに最適化された高度なRAG対応モデルです。",
    "ru-RU": "Command R+ — продвинутая модель, оптимизированная для RAG, предназначенная для корпоративных задач."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Command R+"
    }
   ]
  },
  {
   "slug": "cohere/cohere-command-r-plus-08-2024",
   "model_name": "cohere-command-r-plus-08-2024",
   "display_name": "Cohere Command R+ 08-2024",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere/cohere-command-r-plus-08-2024"
    }
   ],
   "intro": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
   "released_at": "2024-08-01",
   "knowledge_cutoff": "2024-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-r",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/cohere-command-r-plus-08-2024"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Command R+ 08-2024"
    }
   ]
  },
  {
   "slug": "cohere/cohere-embed-v-4-0",
   "model_name": "cohere-embed-v-4-0",
   "display_name": "Embed v4",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2025-04-15",
   "max_input_tokens": 128000,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "cohere-embed",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "multimodal_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Embed v4"
    }
   ]
  },
  {
   "slug": "cohere/Cohere-embed-v3-english",
   "model_name": "Cohere-embed-v3-english",
   "display_name": "Embed v3 English",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere-embed-v3-english"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere-embed-v3-english"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2023-11-07",
   "max_input_tokens": 512,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "cohere-embed",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "stream": true
   },
   "docs_url": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere-embed-v3-english"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Embed v3 English"
    }
   ]
  },
  {
   "slug": "cohere/Cohere-embed-v3-multilingual",
   "model_name": "Cohere-embed-v3-multilingual",
   "display_name": "Embed v3 Multilingual",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere-embed-v3-multilingual"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere-embed-v3-multilingual"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2023-11-07",
   "max_input_tokens": 512,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "cohere-embed",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "stream": true
   },
   "docs_url": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/cohere.cohere-embed-v3-english-offer?tab=PlansAndPrice",
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere-embed-v3-multilingual"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Embed v3 Multilingual"
    }
   ]
  },
  {
   "slug": "cohere/cohere-rerank-v3-english",
   "model_name": "cohere-rerank-v3-english",
   "display_name": "cohere-rerank-v3-english",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cohere-rerank-v3-english"
    }
   ]
  },
  {
   "slug": "cohere/cohere-rerank-v3-multilingual",
   "model_name": "cohere-rerank-v3-multilingual",
   "display_name": "cohere-rerank-v3-multilingual",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cohere-rerank-v3-multilingual"
    }
   ]
  },
  {
   "slug": "cohere/cohere-rerank-v3.5",
   "model_name": "cohere-rerank-v3.5",
   "display_name": "cohere-rerank-v3.5",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cohere-rerank-v3.5"
    }
   ]
  },
  {
   "slug": "cohere/cohere-rerank-v4.0-fast",
   "model_name": "cohere-rerank-v4.0-fast",
   "display_name": "cohere-rerank-v4.0-fast",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_output_tokens": 32768,
   "model_type": "text_rerank",
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cohere-rerank-v4.0-fast"
    }
   ]
  },
  {
   "slug": "cohere/cohere-rerank-v4.0-pro",
   "model_name": "cohere-rerank-v4.0-pro",
   "display_name": "cohere-rerank-v4.0-pro",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.0025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_output_tokens": 32768,
   "model_type": "text_rerank",
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cohere-rerank-v4.0-pro"
    }
   ]
  },
  {
   "slug": "cohere/cohere.command-light-text-v14",
   "model_name": "cohere.command-light-text-v14",
   "display_name": "Command Light",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.001902"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0.001902"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "open_weights": true
   },
   "released_at": "2023-11-01",
   "knowledge_cutoff": "2023-08",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-light",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Command Light"
    }
   ]
  },
  {
   "slug": "cohere/cohere.command-text-v14",
   "model_name": "cohere.command-text-v14",
   "display_name": "Command",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.011"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0.011"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "open_weights": true
   },
   "released_at": "2023-11-01",
   "knowledge_cutoff": "2023-08",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Command"
    }
   ]
  },
  {
   "slug": "cohere/cohere.embed-english-v3",
   "model_name": "cohere.embed-english-v3",
   "display_name": "Cohere Embed English v3",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ap-southeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-west-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 512,
   "model_type": "text_embedding",
   "capabilities": {
    "vision": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "released_at": "2023-11-02",
   "family": "embed",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Embed English v3"
    }
   ]
  },
  {
   "slug": "cohere/cohere.embed-multilingual-v3",
   "model_name": "cohere.embed-multilingual-v3",
   "display_name": "Cohere Embed Multilingual v3",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ap-southeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-west-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 512,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "embedding"
    ]
   },
   "released_at": "2023-11-02",
   "family": "embed",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Embed Multilingual v3"
    }
   ]
  },
  {
   "slug": "cohere/cohere.embed-v4",
   "model_name": "cohere.embed-v4",
   "display_name": "Cohere Embed v4",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0001"
      }
     }
    }
   ],
   "released_at": "2025-10-02",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "multimodal_embedding",
   "family": "embed",
   "capabilities": {
    "vision": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Embed v4"
    }
   ]
  },
  {
   "slug": "cohere/cohere.rerank-v3-5:0",
   "model_name": "cohere.rerank-v3-5:0",
   "display_name": "cohere.rerank-v3-5:0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2000"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      }
     },
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cohere.rerank-v3-5:0"
    }
   ]
  },
  {
   "slug": "cohere/command",
   "model_name": "command",
   "display_name": "command",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "cohere/command"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "intro": "Command is an instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models.",
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/command"
   ],
   "intro_i18n": {
    "zh-CN": "一款遵循指令的聊天模型，在语言任务中提供更高质量和可靠性，拥有比基础生成模型更长的上下文窗口。",
    "zh-TW": "一款遵循指令的聊天模型，在語言任務中提供更高品質與可靠性，具備比基礎生成模型更長的上下文視窗。",
    "ja-JP": "命令に従うチャットモデルであり、言語タスクにおいて高品質かつ信頼性の高い出力を提供し、ベースの生成モデルよりも長いコンテキストウィンドウを持ちます。",
    "ru-RU": "Модель чата, следящая за инструкциями, обеспечивающая более высокое качество и надёжность в языковых задачах, с увеличенным окном контекста по сравнению с базовыми генеративными моделями."
   }
  },
  {
   "slug": "cohere/command-a",
   "model_name": "command-a",
   "display_name": "Command A",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "cohere/command-a"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "cohere/command-a"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "cohere/command-a"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "cohere/command-a"
    }
   ],
   "intro": "Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases.\nCompared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "released_at": "2025-03-13",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 256000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command",
   "model_type": "text_generation",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 22.5,
    "coding_index": 27.8,
    "agentic_index": 9.2
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/command-a"
   ],
   "intro_i18n": {
    "zh-CN": "Command A 是 Cohere 迄今为止最强大的模型，擅长工具使用、智能体、RAG 和多语言场景。支持 256K 上下文长度，仅需两块 GPU 即可运行，吞吐量比 Command R+ 08-2024 提高 150%。",
    "zh-TW": "Command A 是 Cohere 目前最強大的模型，擅長工具使用、代理任務、RAG 與多語言應用。具備 256K 上下文長度，僅需兩張 GPU 即可運行，吞吐量比 Command R+ 08-2024 高出 150%。",
    "ja-JP": "Command AはCohere史上最も強力なモデルであり、ツール使用、エージェント、RAG、多言語ユースケースに優れています。256Kのコンテキスト長を持ち、わずか2つのGPUで動作し、Command R+（2024年8月版）と比べて150%のスループット向上を実現します。",
    "ru-RU": "Command A — самая мощная модель Cohere на сегодняшний день, превосходно справляющаяся с использованием инструментов, агентами, RAG и многоязычными задачами. Поддерживает контекст длиной 256K, работает всего на двух GPU и обеспечивает на 150% большую пропускную способность по сравнению с Command R+ 08-2024."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Command A"
    }
   ]
  },
  {
   "slug": "cohere/command-a-03-2025",
   "model_name": "command-a-03-2025",
   "display_name": "Command A",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "cohere/command-a-03-2025"
    }
   ],
   "intro": "Cohere command model for multilingual enterprise agents, tools, and chat",
   "released_at": "2025-03-13",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 256000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-a",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/command-a-03-2025"
   ],
   "intro_i18n": {
    "zh-CN": "Command A 是我们迄今为止最强大的模型，擅长工具使用、智能体、RAG 和多语言场景。支持 256K 上下文窗口，仅需两块 GPU 即可运行，吞吐量比 Command R+ 08-2024 提高 150%。",
    "zh-TW": "Command A 是我們目前最強大的模型，擅長工具使用、代理任務、RAG 與多語言場景。具備 256K 上下文視窗，僅需兩張 GPU 即可運行，吞吐量比 Command R+ 08-2024 高出 150%。",
    "ja-JP": "Command Aはこれまでで最も高性能なモデルであり、ツール使用、エージェント、RAG、多言語シナリオに優れています。256Kのコンテキストウィンドウを持ち、わずか2つのGPUで動作し、Command R+（2024年8月版）と比べて150%のスループット向上を実現します。",
    "ru-RU": "Command A — наша самая мощная модель на сегодняшний день, превосходно справляющаяся с использованием инструментов, агентами, RAG и многоязычными задачами. Поддерживает контекст до 256K, работает на двух GPU и обеспечивает на 150% большую пропускную способность по сравнению с Command R+ 08-2024."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "cohere/command-a-plus-05-2026",
   "model_name": "command-a-plus-05-2026",
   "display_name": "Command A Plus",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "intro": "Cohere's stronger command model for multilingual agents and enterprise workflows",
   "released_at": "2026-05-20",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-a",
   "reasoning_config": {
    "budget_min": 1
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "cohere/command-a-reasoning-08-2025",
   "model_name": "command-a-reasoning-08-2025",
   "display_name": "Command A Reasoning",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "intro": "Cohere command model for multilingual enterprise agents, tools, and chat",
   "released_at": "2025-08-21",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-a",
   "reasoning_config": {
    "budget_min": 1
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "cohere/command-a-translate-08-2025",
   "model_name": "command-a-translate-08-2025",
   "display_name": "Command A Translate",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "intro": "Translation model for multilingual conversion, localization, and cross-language workflows",
   "released_at": "2025-08-28",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 8000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-a",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "cohere/command-a-vision-07-2025",
   "model_name": "command-a-vision-07-2025",
   "display_name": "Command A Vision",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "intro": "Cohere command model for multilingual enterprise agents, tools, and chat",
   "released_at": "2025-07-31",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-a",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "cohere/command-light",
   "model_name": "command-light",
   "display_name": "command-light",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Command 的轻量快速版本，几乎同样强大但响应更快。",
    "zh-TW": "Command 的輕量快速版本，功能接近但速度更快。",
    "ja-JP": "Commandの小型かつ高速なバリアントであり、ほぼ同等の能力を持ちながらも高速です。",
    "ru-RU": "Упрощённый и более быстрый вариант Command, почти такой же мощный, но с более высокой скоростью."
   }
  },
  {
   "slug": "cohere/command-light-nightly",
   "model_name": "command-light-nightly",
   "display_name": "Command Light Nightly",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "max_input_tokens": 4000,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "为缩短主要版本之间的发布间隔，我们提供 Command 系列的每晚构建版本。command-light-nightly 是 command-light 系列中最新、最具实验性（可能不稳定）的版本，定期更新，适合测试用途，不建议用于生产环境。",
    "zh-TW": "為縮短主要版本之間的間隔，我們提供 Command 系列的夜間版本。command-light-nightly 是 command-light 系列中最新、最具實驗性（可能不穩定）的版本，會定期更新，建議僅用於測試環境。",
    "ja-JP": "主要リリース間のギャップを短縮するため、Commandのナイトリービルドを提供しています。command-lightシリーズではこれをcommand-light-nightlyと呼びます。これは最新かつ最も実験的（かつ不安定な可能性がある）バージョンであり、予告なく定期的に更新されるため、本番環境での使用は推奨されません。",
    "ru-RU": "Чтобы сократить интервал между основными релизами, мы предлагаем ночные сборки Command. Для серии command-light это называется command-light-nightly. Это самая новая и экспериментальная (возможно, нестабильная) версия, обновляется без уведомлений, поэтому не рекомендуется для продакшена."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Command Light Nightly"
    }
   ]
  },
  {
   "slug": "cohere/command-nightly",
   "model_name": "command-nightly",
   "display_name": "command-nightly",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "为缩短主要版本之间的发布间隔，我们提供 Command 系列的每晚构建版本。command-nightly 是 Command 系列中最新、最具实验性（可能不稳定）的版本，定期更新，适合测试用途，不建议用于生产环境。",
    "zh-TW": "為縮短主要版本之間的間隔，我們提供 Command 系列的夜間版本。command-nightly 是 Command 系列中最新、最具實驗性（可能不穩定）的版本，會定期更新，建議僅用於測試環境。",
    "ja-JP": "主要リリース間のギャップを短縮するため、Commandのナイトリービルドを提供しています。Commandシリーズではこれをcommand-nightlyと呼びます。これは最新かつ最も実験的（かつ不安定な可能性がある）バージョンであり、予告なく定期的に更新されるため、本番環境での使用は推奨されません。",
    "ru-RU": "Чтобы сократить интервал между основными релизами, мы предлагаем ночные сборки Command. Для основной серии это называется command-nightly. Это самая новая и экспериментальная (возможно, нестабильная) версия, обновляется без уведомлений, поэтому не рекомендуется для продакшена."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    }
   ]
  },
  {
   "slug": "cohere/command-r",
   "model_name": "command-r",
   "display_name": "command-r",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+pydantic-prices+pricetoken",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.92"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "cohere.command-r-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "cohere.command-r-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "cohere.command-r-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.476"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.428"
      }
     },
     "provider_model_id": "cohere/command-r"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "cohere/command-r"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true
   },
   "intro": "Command-R is a 35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents.",
   "released_at": "2024-03-01",
   "deprecated": true,
   "status": "deprecated",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-r",
   "knowledge_cutoff": "2024-04",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere.command-r-v1:0",
    "cohere/command-r"
   ],
   "intro_i18n": {
    "zh-CN": "Command R 是一款针对聊天和长上下文任务优化的大语言模型，适用于动态交互和知识管理。",
    "zh-TW": "Command R 是一款針對聊天與長上下文任務優化的大型語言模型，適合動態互動與知識管理。",
    "ja-JP": "Command Rは、チャットや長文コンテキストタスクに最適化されたLLMであり、動的な対話や知識管理に適しています。",
    "ru-RU": "Command R — LLM, оптимизированная для чатов и задач с длинным контекстом, идеально подходящая для динамичного взаимодействия и управления знаниями."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "open_weights: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "cohere/command-r-03-2024",
   "model_name": "command-r-03-2024",
   "display_name": "Command R 2403",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "command-r 是一款指令跟随型聊天模型，在语言任务中表现出更高的质量、更高的可靠性和更长的上下文支持。它支持复杂的工作流，如代码生成、RAG、工具使用和 Agent。",
    "zh-TW": "command-r 是一款指令跟隨聊天模型，執行語言任務的質量更高、可靠性更強，並支持比以往模型更長的上下文。它支持複雜的工作流程，例如代碼生成、RAG、工具使用和代理。",
    "ja-JP": "command-rは、以前のモデルよりも高品質で信頼性が高く、長いコンテキストを持つ言語タスクを実行する指示追従型チャットモデルです。コード生成、RAG、ツール使用、エージェントなどの複雑なワークフローをサポートします。",
    "ru-RU": "command-r — это модель чата, следящая за инструкциями, которая выполняет языковые задачи с более высоким качеством, улучшенной надёжностью и более длинным контекстом по сравнению с предыдущими моделями. Она поддерживает сложные рабочие процессы, такие как генерация кода, RAG, использование инструментов и агентов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Command R 2403"
    }
   ]
  },
  {
   "slug": "cohere/command-r-08-2024",
   "model_name": "command-r-08-2024",
   "display_name": "Command R",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "cohere/command-r-08-2024"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "cohere/command-r-08-2024"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "cohere/command-r-08-2024"
    }
   ],
   "intro": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
   "released_at": "2024-08-30",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-r",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/command-r-08-2024"
   ],
   "intro_i18n": {
    "zh-CN": "command-r-08-2024 是 2024 年 8 月发布的 Command R 模型更新版本。",
    "zh-TW": "command-r-08-2024 是 2024 年 8 月發布的 Command R 模型更新版本。",
    "ja-JP": "command-r-08-2024は、2024年8月にリリースされたCommand Rの更新版です。",
    "ru-RU": "command-r-08-2024 — обновлённая модель Command R, выпущенная в августе 2024 года."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "cohere/command-r-plus",
   "model_name": "command-r-plus",
   "display_name": "command-r-plus",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+pydantic-prices+pricetoken",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.84"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.2"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "cohere.command-r-plus-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "cohere.command-r-plus-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "cohere.command-r-plus-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "cohere/command-r-plus"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true
   },
   "intro": "Command R+ is a new, 104B-parameter LLM from Cohere. It's useful for roleplay, general consumer usecases, and Retrieval Augmented Generation (RAG).",
   "released_at": "2024-08-01",
   "deprecated": true,
   "status": "deprecated",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2024-04",
   "family": "command-r",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere.command-r-plus-v1:0",
    "cohere/command-r-plus"
   ],
   "intro_i18n": {
    "zh-CN": "Command R+ 是一款高性能大语言模型，专为真实企业场景和复杂应用设计。",
    "zh-TW": "Command R+ 是一款高效能的大型語言模型，專為真實企業場景與複雜應用而設計。",
    "ja-JP": "Command R+は、実際のエンタープライズシナリオや複雑なアプリケーションに対応する高性能LLMです。",
    "ru-RU": "Command R+ — высокопроизводительная LLM, предназначенная для реальных корпоративных сценариев и сложных приложений."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "open_weights: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "cohere/command-r-plus-04-2024",
   "model_name": "command-r-plus-04-2024",
   "display_name": "Command R+ 2404",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "command-r-plus 是 command-r-plus-04-2024 的别名，API 中使用 command-r-plus 即指向该模型。",
    "zh-TW": "command-r-plus 是 command-r-plus-04-2024 的別名，因此在 API 中使用 command-r-plus 即指向該模型。",
    "ja-JP": "command-r-plusはcommand-r-plus-04-2024の別名であり、APIでcommand-r-plusを使用するとこのモデルが指定されます。",
    "ru-RU": "command-r-plus — псевдоним модели command-r-plus-04-2024, поэтому использование command-r-plus в API указывает на эту модель."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Command R+ 2404"
    }
   ]
  },
  {
   "slug": "cohere/command-r-plus-08-2024",
   "model_name": "command-r-plus-08-2024",
   "display_name": "Command R+",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.2"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "cohere/command-r-plus-08-2024"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "cohere/command-r-plus-08-2024"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.856"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.246"
      }
     },
     "provider_model_id": "cohere/command-r-plus-08-2024"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "cohere/command-r-plus-08-2024"
    }
   ],
   "intro": "Cohere's RAG workhorse for long-context enterprise search and tool use",
   "released_at": "2024-08-30",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-r",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/command-r-plus-08-2024"
   ],
   "intro_i18n": {
    "zh-CN": "Command R+ 是一款遵循指令的聊天模型，质量更高、可靠性更强、上下文窗口更长，特别适用于复杂的 RAG 工作流和多步骤工具使用。",
    "zh-TW": "Command R+ 是一款遵循指令的聊天模型，品質更高、穩定性更強，並具備比前代模型更長的上下文視窗。最適合用於複雜的 RAG 工作流程與多步驟工具使用。",
    "ja-JP": "Command R+は、従来モデルよりも高品質で信頼性が高く、長いコンテキストウィンドウを持つ命令追従型チャットモデルです。複雑なRAGワークフローや多段階のツール使用に最適です。",
    "ru-RU": "Command R+ — модель чата, следящая за инструкциями, с более высоким качеством, надёжностью и увеличенным окном контекста по сравнению с предыдущими версиями. Идеальна для сложных RAG-процессов и многошагового использования инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "cohere/command-r7b",
   "model_name": "command-r7b",
   "display_name": "command-r7b",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "intro": "Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps.",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "command-r7b"
    }
   ]
  },
  {
   "slug": "cohere/command-r7b-12-2024",
   "model_name": "command-r7b-12-2024",
   "display_name": "Command R7B",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "cohere/command-r7b-12-2024"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "cohere/command-r7b-12-2024"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "cohere/command-r7b-12-2024"
    }
   ],
   "intro": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
   "released_at": "2024-12-02",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-r",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "docs_url": "https://docs.cohere.com/v2/docs/command-r7b",
   "model_type": "text_generation",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/command-r7b-12-2024"
   ],
   "intro_i18n": {
    "zh-CN": "command-r7b-12-2024 是 2024 年 12 月发布的小型高效更新版本，擅长 RAG、工具使用和需要复杂多步骤推理的智能体任务。",
    "zh-TW": "command-r7b-12-2024 是 2024 年 12 月發布的小型高效更新版本，擅長需要複雜多步推理的 RAG、工具使用與代理任務。",
    "ja-JP": "command-r7b-12-2024は、2024年12月にリリースされた小型かつ効率的なアップデートであり、複雑な多段階推論を必要とするRAG、ツール使用、エージェントタスクに優れています。",
    "ru-RU": "command-r7b-12-2024 — компактное и эффективное обновление, выпущенное в декабре 2024 года. Отлично справляется с задачами RAG, использования инструментов и агентов, требующих сложного многошагового рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "cohere/command-r7b-arabic-02-2025",
   "model_name": "command-r7b-arabic-02-2025",
   "display_name": "Command R7B Arabic",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "intro": "Cohere retrieval model for long-context chat and enterprise RAG workflows",
   "released_at": "2025-02-27",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "command-r",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "cohere/embed-english-light-v2.0",
   "model_name": "embed-english-light-v2.0",
   "display_name": "embed-english-light-v2.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 1024,
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "cohere/embed-english-light-v3.0",
   "model_name": "embed-english-light-v3.0",
   "display_name": "embed-english-light-v3.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 1024,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "cohere/embed-english-v2.0",
   "model_name": "embed-english-v2.0",
   "display_name": "embed-english-v2.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "cohere/embed-english-v3.0",
   "model_name": "embed-english-v3.0",
   "display_name": "embed-english-v3.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      }
     }
    }
   ],
   "max_input_tokens": 1024,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "cohere/embed-multilingual-light-v3.0",
   "model_name": "embed-multilingual-light-v3.0",
   "display_name": "embed-multilingual-light-v3.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "100"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 1024,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "cohere/embed-multilingual-v2.0",
   "model_name": "embed-multilingual-v2.0",
   "display_name": "embed-multilingual-v2.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 768,
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "cohere/embed-multilingual-v3.0",
   "model_name": "embed-multilingual-v3.0",
   "display_name": "embed-multilingual-v3.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 1024,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "cohere/embed-v4.0",
   "model_name": "embed-v4.0",
   "display_name": "embed-v4.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "cohere/embed-v4.0"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "cohere/embed-v4.0"
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "intro": "Embed v4.0 is a state-of-the-art embedding model designed for precise retrieval across noisy, multilingual, and multimodal data.",
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "embedding"
    ]
   },
   "released_at": "2025-04-15",
   "max_output_tokens": 1536,
   "family": "cohere-embed",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/embed-v4.0"
   ],
   "intro_i18n": {
    "zh-CN": "一个可将文本、图像或混合内容分类或转换为嵌入向量的模型。",
    "zh-TW": "一款可將文字、圖像或混合內容分類或轉換為嵌入向量的模型。",
    "ja-JP": "テキスト、画像、または混合コンテンツを分類または埋め込みに変換するモデルです。",
    "ru-RU": "Модель, преобразующая текст, изображения или смешанный контент в эмбеддинги для классификации или других задач."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "cohere/north-mini-code",
   "model_name": "north-mini-code",
   "display_name": "North Mini Code Free",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "cohere/north-mini-code"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "north-mini-code-free"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere/north-mini-code:free"
    }
   ],
   "intro": "Cohere coding model for practical software engineering and agentic edits",
   "released_at": "2026-06-09",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 256000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "north-free",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/north-mini-code",
    "cohere/north-mini-code:free",
    "north-mini-code-free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "North Mini Code Free"
    }
   ]
  },
  {
   "slug": "cohere/north-mini-code-1-0",
   "model_name": "north-mini-code-1-0",
   "display_name": "North Mini Code",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Cohere coding model for practical software engineering and agentic edits",
   "released_at": "2026-06-09",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 256000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "north",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "cohere/rerank-english-v2.0",
   "model_name": "rerank-english-v2.0",
   "display_name": "rerank-english-v2.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rerank-english-v2.0"
    }
   ]
  },
  {
   "slug": "cohere/rerank-english-v3.0",
   "model_name": "rerank-english-v3.0",
   "display_name": "rerank-english-v3.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rerank-english-v3.0"
    }
   ]
  },
  {
   "slug": "cohere/rerank-multilingual-v2.0",
   "model_name": "rerank-multilingual-v2.0",
   "display_name": "rerank-multilingual-v2.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rerank-multilingual-v2.0"
    }
   ]
  },
  {
   "slug": "cohere/rerank-multilingual-v3.0",
   "model_name": "rerank-multilingual-v3.0",
   "display_name": "rerank-multilingual-v3.0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rerank-multilingual-v3.0"
    }
   ]
  },
  {
   "slug": "cohere/rerank-v3.5",
   "model_name": "rerank-v3.5",
   "display_name": "Cohere Rerank 3.5",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "cohere",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_request",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "model_type": "text_rerank",
   "capabilities": {},
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2024-12-02",
   "max_output_tokens": 4096,
   "family": "o",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/rerank-v3.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Rerank 3.5"
    }
   ]
  },
  {
   "slug": "cohere/rerank-v4-fast",
   "model_name": "rerank-v4-fast",
   "display_name": "Cohere Rerank 4 Fast",
   "vendor": "cohere",
   "pricing": [],
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2025-12-11",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/rerank-v4-fast"
   ],
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Rerank 4 Fast"
    }
   ]
  },
  {
   "slug": "cohere/rerank-v4-pro",
   "model_name": "rerank-v4-pro",
   "display_name": "Cohere Rerank 4 Pro",
   "vendor": "cohere",
   "pricing": [],
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2025-12-11",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere/rerank-v4-pro"
   ],
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cohere Rerank 4 Pro"
    }
   ]
  },
  {
   "slug": "cohere/us.cohere.embed-v4:0",
   "model_name": "us.cohere.embed-v4:0",
   "display_name": "us.cohere.embed-v4:0",
   "vendor": "cohere",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere.embed-v4:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere.embed-v4:0",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "ap-northeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "ap-northeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "ap-south-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "ap-southeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "ap-southeast-4"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "eu.cohere.embed-v4:0",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "eu.cohere.embed-v4:0",
     "region": "eu-central-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "eu.cohere.embed-v4:0",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "eu.cohere.embed-v4:0",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "eu.cohere.embed-v4:0",
     "region": "eu-south-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere.embed-v4:0",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "eu.cohere.embed-v4:0",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "eu.cohere.embed-v4:0",
     "region": "eu-west-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cohere.embed-v4:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "us-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "global.cohere.embed-v4:0",
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cohere.embed-v4:0",
    "eu.cohere.embed-v4:0",
    "global.cohere.embed-v4:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.cohere.embed-v4:0"
    }
   ]
  },
  {
   "slug": "databricks/dbrx-instruct",
   "model_name": "dbrx-instruct",
   "display_name": "dbrx-instruct",
   "vendor": "databricks",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "databricks/dbrx-instruct"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {},
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "databricks/dbrx-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "DBRX Instruct 提供跨行业高度可靠的指令处理能力。",
    "zh-TW": "DBRX Instruct 提供跨產業高度可靠的指令處理能力。",
    "ja-JP": "DBRX Instruct は、業界を問わず高い信頼性のある指示処理を提供します。",
    "ru-RU": "DBRX Instruct обеспечивает надёжную обработку инструкций в различных отраслях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "dbrx-instruct"
    }
   ]
  },
  {
   "slug": "deepgram/@cf/deepgram/aura-2-en",
   "model_name": "@cf/deepgram/aura-2-en",
   "display_name": "Deepgram Aura 2 (EN)",
   "vendor": "deepgram",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/deepgram/aura-2-en"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-11-14",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "aura",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "workers-ai/@cf/deepgram/aura-2-en"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Deepgram Aura 2 (EN)"
    }
   ]
  },
  {
   "slug": "deepgram/@cf/deepgram/aura-2-es",
   "model_name": "@cf/deepgram/aura-2-es",
   "display_name": "Deepgram Aura 2 (ES)",
   "vendor": "deepgram",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/deepgram/aura-2-es"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-11-14",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "aura",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "workers-ai/@cf/deepgram/aura-2-es"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Deepgram Aura 2 (ES)"
    }
   ]
  },
  {
   "slug": "deepgram/@cf/deepgram/nova-3",
   "model_name": "@cf/deepgram/nova-3",
   "display_name": "Deepgram Nova 3",
   "vendor": "deepgram",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/deepgram/nova-3"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-11-14",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "workers-ai/@cf/deepgram/nova-3"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Deepgram Nova 3"
    }
   ]
  },
  {
   "slug": "deepgram/aura-2",
   "model_name": "aura-2",
   "display_name": "aura-2",
   "vendor": "deepgram",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "30"
      }
     },
     "provider_model_id": "deepgram/aura-2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepgram/aura-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aura-2"
    }
   ]
  },
  {
   "slug": "deepgram/nova-3-en",
   "model_name": "nova-3-en",
   "display_name": "nova-3-en",
   "vendor": "deepgram",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00012833333"
      }
     },
     "provider_model_id": "deepgram/nova-3-en"
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepgram/nova-3-en"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nova-3-en"
    }
   ]
  },
  {
   "slug": "deepgram/nova-3-multi",
   "model_name": "nova-3-multi",
   "display_name": "nova-3-multi",
   "vendor": "deepgram",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00012833333333333333"
      }
     },
     "provider_model_id": "deepgram/nova-3-multi"
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepgram/nova-3-multi"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nova-3-multi"
    }
   ]
  },
  {
   "slug": "deepseek/alicloud-deepseek-v3.2",
   "model_name": "alicloud-deepseek-v3.2",
   "display_name": "alicloud-deepseek-v3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.274"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0548"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "alicloud-deepseek-v3.2"
    }
   ]
  },
  {
   "slug": "deepseek/alicloud-deepseek-v4-flash",
   "model_name": "alicloud-deepseek-v4-flash",
   "display_name": "DeepSeek V4 Flash (Alibaba Cloud)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     }
    }
   ],
   "intro": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
   "released_at": "2026-04-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-flash",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V4 Flash (Alibaba Cloud)"
    }
   ]
  },
  {
   "slug": "deepseek/alicloud-deepseek-v4-pro",
   "model_name": "alicloud-deepseek-v4-pro",
   "display_name": "DeepSeek V4 Pro (Alibaba Cloud)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.69"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    }
   ],
   "intro": "Flagship DeepSeek model for coding, reasoning, and agentic work",
   "released_at": "2026-04-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V4 Pro (Alibaba Cloud)"
    }
   ]
  },
  {
   "slug": "deepseek/azure-DeepSeek-R1-0528",
   "model_name": "azure-DeepSeek-R1-0528",
   "display_name": "DeepSeek R1 0528 (Azure)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     }
    }
   ],
   "max_input_tokens": 65536,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "由微软部署的 DeepSeek R1 已升级为 DeepSeek-R1-0528。此次更新增强了计算能力和后训练算法优化，显著提升了推理深度和推理能力，在数学、编程和通用逻辑基准测试中表现优异，接近 O3 和 Gemini 2.5 Pro 等领先模型。",
    "zh-TW": "由微軟部署的 DeepSeek R1 已升級為 DeepSeek-R1-0528。此次更新提升了運算能力與後訓練演算法優化，顯著增強推理深度與推論表現，在數學、程式碼與邏輯基準測試中表現優異，接近 O3 與 Gemini 2.5 Pro 等領先模型。",
    "ja-JP": "Microsoftにより展開されたDeepSeek R1は、DeepSeek-R1-0528へとアップグレードされました。この更新により、計算能力と事後学習アルゴリズムが最適化され、推論の深さと精度が大幅に向上しました。数学、コーディング、一般的な論理ベンチマークで高い性能を発揮し、O3やGemini 2.5 Proといった先進モデルに迫る実力を持ちます。",
    "ru-RU": "Развернута Microsoft; DeepSeek R1 обновлена до версии DeepSeek-R1-0528. Обновление включает увеличение вычислительных ресурсов и оптимизацию алгоритмов постобучения, что значительно улучшает глубину рассуждений и выводов. Модель демонстрирует высокие результаты в математике, программировании и логике, приближаясь к лидерам, таким как O3 и Gemini 2.5 Pro."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 0528 (Azure)"
    }
   ]
  },
  {
   "slug": "deepseek/azure-deepseek-v3.2",
   "model_name": "azure-deepseek-v3.2",
   "display_name": "azure-deepseek-v3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.680028"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure-deepseek-v3.2"
    }
   ]
  },
  {
   "slug": "deepseek/azure-deepseek-v3.2-speciale",
   "model_name": "azure-deepseek-v3.2-speciale",
   "display_name": "azure-deepseek-v3.2-speciale",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.680028"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure-deepseek-v3.2-speciale"
    }
   ]
  },
  {
   "slug": "deepseek/cc-deepseek-v3",
   "model_name": "cc-deepseek-v3",
   "display_name": "cc-deepseek-v3",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-deepseek-v3"
    }
   ]
  },
  {
   "slug": "deepseek/cc-deepseek-v3.1",
   "model_name": "cc-deepseek-v3.1",
   "display_name": "cc-deepseek-v3.1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-deepseek-v3.1"
    }
   ]
  },
  {
   "slug": "deepseek/deep-deepseek-v4-flash",
   "model_name": "deep-deepseek-v4-flash",
   "display_name": "DeepSeek V4 Flash (DeepSeek)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.154"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.308"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0308"
      }
     }
    }
   ],
   "intro": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
   "released_at": "2026-04-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-flash",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V4 Flash (DeepSeek)"
    }
   ]
  },
  {
   "slug": "deepseek/deep-deepseek-v4-pro",
   "model_name": "deep-deepseek-v4-pro",
   "display_name": "DeepSeek V4 Pro (DeepSeek)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.478"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.956"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.004302"
      }
     }
    }
   ],
   "intro": "Flagship DeepSeek model for coding, reasoning, and agentic work",
   "released_at": "2026-04-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V4 Pro (DeepSeek)"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek",
   "model_name": "deepseek",
   "display_name": "deepseek",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "deepseek"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek_v3",
   "model_name": "deepseek_v3",
   "display_name": "DeepSeek V3",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.89"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.89"
      }
     },
     "provider_model_id": "deepseek/deepseek_v3"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.89"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.89"
      }
     },
     "provider_model_id": "novita/deepseek/deepseek_v3"
    }
   ],
   "released_at": "2025-01-15",
   "max_input_tokens": 64000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek_v3",
    "novita/deepseek/deepseek_v3"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-3.2",
   "model_name": "deepseek-3.2",
   "display_name": "DeepSeek V3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     }
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-12-02",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.2"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-4-flash",
   "model_name": "deepseek-4-flash",
   "display_name": "Deepseek V4 Flash",
   "vendor": "deepseek",
   "pricing": [],
   "intro": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
   "released_at": "2026-05-27",
   "max_input_tokens": 262144,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Deepseek V4 Flash"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-chat",
   "model_name": "deepseek-chat",
   "display_name": "DeepSeek Chat",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepseek",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+helicone-registry+portkey+llmdb+pricetoken+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.014"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.89"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8001"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "assistant_prefill": true,
    "stream": true
   },
   "docs_url": "https://api-docs.deepseek.com/quick_start/pricing",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "function_call",
     "functions",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "stream",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "deprecated": true,
   "status": "deprecated",
   "aliases": [
    "deepseek/deepseek-chat"
   ],
   "intro_i18n": {
    "zh-CN": "一个结合了通用能力和代码能力的新开源模型。它保留了聊天模型的通用对话能力和编码模型的强大编程能力，并具有更好的偏好对齐。DeepSeek-V2.5 还改进了写作和指令遵循能力。",
    "zh-TW": "一款結合通用能力與程式能力的開源模型。它保留了聊天模型的通用對話能力和程式模型的強大編程能力，並且在偏好對齊方面表現更佳。DeepSeek-V2.5 還改進了寫作和指令遵循能力。",
    "ja-JP": "一般的な対話能力とコード能力を組み合わせた新しいオープンソースモデルです。チャットモデルの一般的な対話能力と、コーダーモデルの強力なコーディング能力を保持し、より良い嗜好調整を実現しています。DeepSeek-V2.5は、文章作成や指示の追従能力も向上させています。",
    "ru-RU": "Новая модель с открытым исходным кодом, объединяющая общие и кодовые способности. Она сохраняет общий диалоговый стиль чат-модели и сильные навыки кодирования кодовой модели, с улучшенной согласованностью предпочтений. DeepSeek-V2.5 также улучшает навыки письма и следование инструкциям."
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-chat-cheaper",
   "model_name": "deepseek-chat-cheaper",
   "display_name": "DeepSeek V3/Chat Cheaper",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2025-04-15",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3/Chat Cheaper"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-chat-v3-0324",
   "model_name": "deepseek-chat-v3-0324",
   "display_name": "DeepSeek: DeepSeek V3 0324",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.77"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.095"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat-v3-0324"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat-v3-0324"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-03-24",
   "max_input_tokens": 163840,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-07",
   "family": "deepseek",
   "model_type": "text_generation",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 15.4,
    "coding_index": 21.2,
    "agentic_index": 1.5
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-chat-v3-0324:free",
    "deepseek/deepseek-chat-v3-0324"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek V3 是一款拥有 685B 参数的 MoE 模型，是 DeepSeek 旗舰聊天系列的最新版本。\n\n该模型基于 [DeepSeek V3](/deepseek/deepseek-chat-v3) 构建，在多项任务中表现出色。",
    "zh-TW": "DeepSeek V3 是一款擁有 685B 參數的 MoE 模型，是 DeepSeek 旗艦聊天系列的最新版本。\n\n它基於 [DeepSeek V3](/deepseek/deepseek-chat-v3) 打造，在多項任務中表現出色。",
    "ja-JP": "DeepSeek V3は、685BパラメータのMoEモデルで、DeepSeekのフラッグシップチャットシリーズの最新バージョンです。\n\n[DeepSeek V3](/deepseek/deepseek-chat-v3)を基盤とし、さまざまなタスクで高い性能を発揮します。",
    "ru-RU": "DeepSeek V3 — модель MoE с 685B параметрами и последняя итерация флагманской серии чатов DeepSeek.\n\nОснована на [DeepSeek V3](/deepseek/deepseek-chat-v3) и демонстрирует высокую производительность в различных задачах."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek: DeepSeek V3 0324"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-chat-v3.1",
   "model_name": "deepseek-chat-v3.1",
   "display_name": "DeepSeek: DeepSeek V3.1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.177"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.044"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat-v3.1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat-v3.1"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.056"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat-v3.1"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-08-21",
   "max_input_tokens": 32768,
   "max_output_tokens": 7168,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "stream": true,
    "web_search": true
   },
   "knowledge_cutoff": "2025-03",
   "family": "deepseek",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-chat-v3.1"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek-V3.1 是 DeepSeek 推出的长上下文混合推理模型，支持思考/非思考模式切换及工具集成。",
    "zh-TW": "DeepSeek-V3.1 是 DeepSeek 的長上下文混合推理模型，支援思考與非思考模式切換，並整合工具使用。",
    "ja-JP": "DeepSeek-V3.1は、長文コンテキストに対応したDeepSeekのハイブリッド推論モデルで、思考モードと非思考モードの切り替えやツール統合をサポートします。",
    "ru-RU": "DeepSeek-V3.1 — гибридная модель логического вывода с длинным контекстом от DeepSeek, поддерживающая смешанные режимы мышления/без мышления и интеграцию инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek: DeepSeek V3.1"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-chat-v3.2",
   "model_name": "deepseek-chat-v3.2",
   "display_name": "DeepSeek V3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "canopywave",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepseek/deepseek-chat-v3.2"
    }
   ],
   "intro": "DeepSeek-V3.2-Exp is an experimental model introducing the groundbreaking DeepSeek Sparse Attention (DSA) mechanism for enhanced long-context processing efficiency. Built on V3.1-Terminus, DSA achieves fine-grained sparse attention while maintaining identical output quality. This delivers substantial computational efficiency improvements without compromising accuracy. Comprehensive benchmarks confirm V3.2-Exp matches V3.1-Terminus performance, proving efficiency gains don't sacrifice capability. As both a powerful tool and research platform, it establishes new paradigms for efficient long-context AI processing.",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-chat-v3.2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.2"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-coder",
   "model_name": "deepseek-coder",
   "display_name": "deepseek-coder",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepseek",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "deepseek/deepseek-coder"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "assistant_prefill": true
   },
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-coder"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-coder-1b-base",
   "model_name": "deepseek-coder-1b-base",
   "display_name": "DeepSeek Coder 1.3B Base",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-coder-1b-base"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-coder-1b-base"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek Coder 1.3B Base"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-coder-33b",
   "model_name": "deepseek-coder-33b",
   "display_name": "DeepSeek Coder 33B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "max_input_tokens": 16000,
   "family": "DeepSeek",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek Coder 33B"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-coder-33b-instruct",
   "model_name": "deepseek-coder-33b-instruct",
   "display_name": "DeepSeek Coder 33B Instruct",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-coder-33b-instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-coder-33b-instruct"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-02-07",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-coder-33b-instruct",
    "deepseek-ai/deepseek-coder-33b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek Coder 33B 是一款代码语言模型，训练于 2T 数据（87% 代码，13% 中英文文本）。支持 16K 上下文窗口与中间填充任务，提供项目级代码补全与片段填充。",
    "zh-TW": "DeepSeek Coder 33B 是一款程式語言模型，訓練於 2T token（87% 程式碼，13% 中英文文本），支援 16K 上下文視窗與中間填充任務，提供專案級程式補全與片段填充功能。",
    "ja-JP": "DeepSeek Coder 33B は 2T トークン（コード 87%、中英テキスト 13%）で学習されたコード言語モデルです。16K のコンテキストウィンドウと Fill-in-the-Middle タスクを導入し、プロジェクトレベルのコード補完とスニペット補完を提供します。",
    "ru-RU": "DeepSeek Coder 33B — языковая модель для программирования, обученная на 2 триллионах токенов (87% кода, 13% китайского/английского текста). Поддерживает контекстное окно 16K и задачи заполнения в середине, обеспечивая автодополнение на уровне проекта и вставку фрагментов кода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek Coder 33B Instruct"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-coder-7b-base",
   "model_name": "deepseek-coder-7b-base",
   "display_name": "DeepSeek Coder 7B Base",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-coder-7b-base"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-coder-7b-base"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek Coder 7B Base"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-coder-7b-base-v1p5",
   "model_name": "deepseek-coder-7b-base-v1p5",
   "display_name": "DeepSeek Coder 7B Base v1.5",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-coder-7b-base-v1p5"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-coder-7b-base-v1p5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek Coder 7B Base v1.5"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-coder-7b-instruct-v1p5",
   "model_name": "deepseek-coder-7b-instruct-v1p5",
   "display_name": "DeepSeek Coder 7B Instruct v1.5",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-coder-7b-instruct-v1p5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek Coder 7B Instruct v1.5"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-Coder-V2-Instruct",
   "model_name": "DeepSeek-Coder-V2-Instruct",
   "display_name": "deepseek-ai/DeepSeek-Coder-V2-Instruct",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-Coder-V2-Instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepseek-coder-v2-instruct"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "model_type": "text_generation",
   "capabilities": {
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-Coder-V2-Instruct",
    "deepseek-coder-v2-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/DeepSeek-Coder-V2-Instruct"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-coder-v2-lite-base",
   "model_name": "deepseek-coder-v2-lite-base",
   "display_name": "DeepSeek Coder V2 Lite Base",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-coder-v2-lite-base"
    }
   ],
   "max_input_tokens": 163840,
   "max_output_tokens": 163840,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-coder-v2-lite-base"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek Coder V2 Lite Base"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-coder-v2-lite-instruct",
   "model_name": "deepseek-coder-v2-lite-instruct",
   "display_name": "DeepSeek Coder V2 Lite Instruct",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-coder-v2-lite-instruct"
    }
   ],
   "max_input_tokens": 163840,
   "max_output_tokens": 163840,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-coder-v2-lite-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek Coder V2 Lite Instruct"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-latest",
   "model_name": "deepseek-latest",
   "display_name": "DeepSeek Latest",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "deepseek/deepseek-latest"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2026-05-03",
   "max_input_tokens": 1048576,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-latest"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek Latest"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-llama3.3-70b",
   "model_name": "deepseek-llama3.3-70b",
   "display_name": "deepseek-llama3.3-70b",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-llama3.3-70b"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-llm-67b-chat",
   "model_name": "deepseek-llm-67b-chat",
   "display_name": "deepseek-ai/deepseek-llm-67b-chat",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-llm-67b-chat"
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/deepseek-llm-67b-chat"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek LLM Chat（67B）是一款创新模型，具备深度语言理解与交互能力。",
    "zh-TW": "DeepSeek LLM Chat（67B）是一款創新模型，具備深層語言理解與互動能力。",
    "ja-JP": "DeepSeek LLM Chat（67B）は、深い言語理解と対話能力を提供する革新的なモデルです。",
    "ru-RU": "DeepSeek LLM Chat (67B) — инновационная модель с глубоким пониманием языка и возможностью взаимодействия."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/deepseek-llm-67b-chat"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-math-v2",
   "model_name": "deepseek-math-v2",
   "display_name": "Deepseek/Deepseek-Math-V2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     },
     "provider_model_id": "deepseek/deepseek-math-v2"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-12-04",
   "max_input_tokens": 160000,
   "max_output_tokens": 160000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-math-v2"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek Math V2 是一款在数学推理能力上取得重大突破的模型。其核心创新在于“自我验证”训练机制，并在多个顶级数学竞赛中达到了金牌水平。",
    "zh-TW": "DeepSeek Math V2 是一款在數學推理能力上取得重大突破的模型。其核心創新在於「自我驗證」訓練機制，並在多項頂級數學競賽中達到金牌水準。",
    "ja-JP": "DeepSeek Math V2は、数学的推論能力において大きなブレークスルーを達成したモデルです。最大の革新は「自己検証」トレーニングメカニズムにあり、複数のトップレベルの数学コンテストで金メダルレベルの成績を収めています。",
    "ru-RU": "DeepSeek Math V2 — это модель, достигшая значительных прорывов в области математического рассуждения. Её ключевое новшество — механизм обучения с «самопроверкой», благодаря которому она достигла уровня золотой медали на нескольких ведущих математических соревнованиях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Deepseek/Deepseek-Math-V2"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-OCR",
   "model_name": "DeepSeek-OCR",
   "display_name": "DeepSeek-OCR",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "deepseek-ocr"
    },
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-ocr/models/DeepSeek-OCR"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-OCR"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "deepseek-ocr"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "deepseek/deepseek-ocr"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-OCR"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-OCR"
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.031765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.031765"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-OCR"
    }
   ],
   "intro": "OCR model for extracting structured text from documents and screenshots",
   "released_at": "2025-10-24",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "family": "deepseek",
   "model_type": "vision_understanding",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/deepseek-ai/DeepSeek-OCR",
    "deepseek-ai/DeepSeek-OCR",
    "deepseek-ai/deepseek-ocr/models/DeepSeek-OCR",
    "deepseek-ocr",
    "deepseek/deepseek-ocr"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek-OCR 是 DeepSeek AI 推出的视觉语言模型，专注于 OCR 与“上下文光学压缩”。它探索如何从图像中压缩上下文，高效处理文档并将其转换为结构化文本（如 Markdown）。该模型能够精准识别图像中的文字，适用于文档数字化、文本提取与结构化处理等场景。",
    "zh-TW": "DeepSeek-OCR 是 DeepSeek AI 推出的視覺語言模型，專注於 OCR 與「脈絡光學壓縮」。其核心在於從影像中壓縮脈絡、有效處理文件，並將其轉換為結構化文字（如 Markdown）。能精準辨識影像文字，適用於文件數位化、文字擷取與結構化處理。",
    "ja-JP": "DeepSeek-OCR は、DeepSeek AI による OCR と「コンテキスト光学圧縮」に特化したビジョン・ランゲージモデルです。画像から文脈を圧縮して抽出し、文書を効率的に処理して構造化テキスト（例：Markdown）へ変換します。画像内文字の高精度認識に優れ、文書のデジタル化、テキスト抽出、構造化処理に適しています。",
    "ru-RU": "DeepSeek-OCR — это модель восприятия и языка от DeepSeek AI, ориентированная на OCR и «контекстное оптическое сжатие». Она исследует методы сжатия контекста из изображений, эффективно обрабатывает документы и преобразует их в структурированный текст (например, Markdown). Точно распознаёт текст на изображениях и подходит для оцифровки документов, извлечения текста и структурированной обработки."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-OCR"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-OCR-2",
   "model_name": "DeepSeek-OCR-2",
   "display_name": "deepseek/deepseek-ocr-2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-ocr-2"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "deepseek/deepseek-ocr-2"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.411967696"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.411967696"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "deepseek/deepseek-ocr-2"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "deepseek/deepseek-ocr-2"
    }
   ],
   "intro": "OCR model for extracting structured text from documents and screenshots",
   "released_at": "2026-01-27",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/deepseek-ocr-2",
    "deepseek/deepseek-ocr-2"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412164704",
     "new": "0.411967696"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.412164704",
     "new": "0.411967696"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412451032",
     "new": "0.412164704"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.412451032",
     "new": "0.412164704"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412885816",
     "new": "0.412451032"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.412885816",
     "new": "0.412451032"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412970124",
     "new": "0.412885816"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.412970124",
     "new": "0.412885816"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.412823936",
     "new": "0.412970124"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.412823936",
     "new": "0.412970124"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.41210106",
     "new": "0.412823936"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.41210106",
     "new": "0.412823936"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-ocr-2"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-ocr-maas",
   "model_name": "deepseek-ocr-maas",
   "display_name": "deepseek-ocr-maas",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-ocr-maas"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/deepseek-ocr-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ocr-maas"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-prover-v2",
   "model_name": "deepseek-prover-v2",
   "display_name": "DeepSeek Prover V2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-prover-v2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.18"
      }
     }
    }
   ],
   "max_input_tokens": 163840,
   "max_output_tokens": 163840,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-prover-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek Prover V2"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-Prover-V2-671B",
   "model_name": "DeepSeek-Prover-V2-671B",
   "display_name": "Deepseek Prover V2 671B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-Prover-V2-671B"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.77"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-Prover-V2-671B"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "deepseek/deepseek-prover-v2-671b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "deepseek-prover-v2-671b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "deepseek/deepseek-prover-v2-671b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "novita/deepseek/deepseek-prover-v2-671b"
    }
   ],
   "intro": "Flagship DeepSeek model for coding, reasoning, and agentic work",
   "released_at": "2025-04-30",
   "max_input_tokens": 160000,
   "max_output_tokens": 160000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "family": "deepseek",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-Prover-V2-671B",
    "deepseek-prover-v2-671b",
    "deepseek/deepseek-prover-v2-671b",
    "novita/deepseek/deepseek-prover-v2-671b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Deepseek Prover V2 671B"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1",
   "model_name": "deepseek-r1",
   "display_name": "deepseek-r1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepseek",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1"
    },
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     },
     "provider_model_id": "360/deepseek-r1"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "DeepSeek-R1"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.294"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.294"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     }
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "DeepSeek-R1"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.79914765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.85409875"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "DeepSeek-R1"
    },
    {
     "provider": "drun",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "public/deepseek-r1"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.675"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-r1"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-r1"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-r1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "DeepSeek-R1"
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5237"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2053"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2618"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.35410112"
      }
     },
     "provider_model_id": "DeepSeek-R1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "DeepSeek-R1"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.31884"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-R1"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      }
     },
     "provider_model_id": "DeepSeek-R1"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.18"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.18"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1"
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     }
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     },
     "provider_model_id": "hf:deepseek-ai/DeepSeek-R1"
    },
    {
     "provider": "tencentcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+litellm+truefoundry+computeprices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1"
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 8192,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
   "released_at": "2025-08-05",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "knowledge_cutoff": "2024-07",
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 128
   },
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367",
   "benchmarks": {
    "intelligence_index": 18.5,
    "coding_index": 24.6,
    "agentic_index": 3.1
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_completion_tokens",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "360/deepseek-r1",
    "DeepSeek-R1",
    "Pro/deepseek-ai/DeepSeek-R1",
    "accounts/fireworks/models/deepseek-r1",
    "deepinfra/deepseek-ai/DeepSeek-R1",
    "deepseek-ai/DeepSeek-R1",
    "deepseek-ai/deepseek-r1",
    "deepseek-r1:free",
    "deepseek/deepseek-r1",
    "hf:deepseek-ai/DeepSeek-R1",
    "novita/deepseek/deepseek-r1",
    "public/deepseek-r1"
   ],
   "intro_i18n": {
    "zh-CN": "360 部署的 DeepSeek-R1 在后训练阶段应用大规模强化学习，在极少标注数据下显著提升推理能力，在数学、编程和自然语言推理任务上可与 OpenAI o1 相媲美。",
    "zh-TW": "360 部署的 DeepSeek-R1 在後訓練階段應用大規模強化學習，僅需極少標註資料即可大幅提升推理能力，在數學、程式碼與自然語言推理任務上與 OpenAI o1 表現相當。",
    "ja-JP": "360が展開するDeepSeek-R1は、ポストトレーニングで大規模な強化学習を活用し、最小限のラベルで推論能力を大幅に向上させます。数学、コード、自然言語推論タスクにおいてOpenAI o1と同等の性能を発揮します。",
    "ru-RU": "DeepSeek-R1, развернутая компанией 360, использует масштабное обучение с подкреплением на этапе дообучения, значительно улучшая логическое мышление при минимальной разметке. Сопоставима с OpenAI o1 в задачах по математике, программированию и языковому рассуждению."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592687",
     "new": "2.85409875"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800595236",
     "new": "0.79914765"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.2839",
     "new": "0.2618"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.279",
     "new": "2.2053"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.5678",
     "new": "0.5237"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35522688",
     "new": "2.35410112"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.858164925",
     "new": "2.8592687"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800286179",
     "new": "0.800595236"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.2618",
     "new": "0.2839"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.2053",
     "new": "2.279"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.5237",
     "new": "0.5678"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35686304",
     "new": "2.35522688"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.860353575",
     "new": "2.858164925"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800899001",
     "new": "0.800286179"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.2839",
     "new": "0.2618"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.279",
     "new": "2.2053"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.5678",
     "new": "0.5237"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35934752",
     "new": "2.35686304"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-0528",
   "model_name": "DeepSeek-R1-0528",
   "display_name": "DeepSeek-R1-0528",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.294"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.294"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.585"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.307"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.146"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+deepinfra+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.675"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-0528"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-0528"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-0528"
    },
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.15"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-0528"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-0528"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.31884"
      }
     },
     "provider_model_id": "deepseek-r1-0528"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      }
     }
    },
    {
     "provider": "submodel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.15"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "hf:deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.23"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.112"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-0528"
    }
   ],
   "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
   "released_at": "2025-08-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true,
    "web_search": true
   },
   "family": "deepseek-thinking",
   "knowledge_cutoff": "2025-05",
   "model_type": "deep_thinking",
   "docs_url": "https://fireworks.ai/pricing",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-r1-0528",
    "deepinfra/deepseek-ai/DeepSeek-R1-0528",
    "deepseek-ai/DeepSeek-R1-0528",
    "deepseek-r1-0528",
    "deepseek-r1-0528:free",
    "deepseek/deepseek-r1-0528",
    "hf:deepseek-ai/DeepSeek-R1-0528",
    "siliconflow/deepseek-r1-0528"
   ],
   "intro_i18n": {
    "zh-CN": "2025 年 5 月 28 日发布的 685B 全量模型。DeepSeek-R1 在后训练阶段使用大规模强化学习，显著提升推理能力，仅需极少标注数据即可在数学、编程和自然语言推理方面表现出色。",
    "zh-TW": "685B 全量模型於 2025-05-28 發布。DeepSeek-R1 在後訓練階段引入大規模強化學習（RL），即使標註資料極少，也能大幅提升推理能力，並在數學、程式碼與自然語言推理方面表現優異。",
    "ja-JP": "2025年5月28日に685Bのフルモデルをリリース。DeepSeek-R1は、事後学習において大規模な強化学習（RL）を活用し、最小限のラベル付きデータで推論能力を大幅に向上。数学、コーディング、自然言語推論において高い性能を発揮します。",
    "ru-RU": "Полная модель 685B выпущена 28.05.2025. DeepSeek-R1 использует масштабное обучение с подкреплением на этапе постобучения, значительно улучшая логическое мышление при минимуме размеченных данных. Демонстрирует высокие результаты в математике, программировании и языковом рассуждении."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-R1-0528"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-0528-distill-qwen3-8b",
   "model_name": "deepseek-r1-0528-distill-qwen3-8b",
   "display_name": "DeepSeek R1 0528 Distill Qwen3 8B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-r1-0528-distill-qwen3-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 0528 Distill Qwen3 8B"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-0528-fast",
   "model_name": "DeepSeek-R1-0528-fast",
   "display_name": "DeepSeek R1 0528 Fast",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528-fast"
    }
   ],
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-R1-0528-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 0528 Fast"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-0528-maas",
   "model_name": "deepseek-r1-0528-maas",
   "display_name": "deepseek-r1-0528-maas",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-r1-0528-maas",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 163840,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/deepseek-r1-0528-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-r1-0528-maas"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-0528-Qwen3-8B",
   "model_name": "DeepSeek-R1-0528-Qwen3-8B",
   "display_name": "DeepSeek R1 0528 Qwen3 8B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "deepseek-r1-0528-qwen3-8b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-0528-qwen3-8b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepseek-r1-0528-qwen3-8b"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B"
    }
   ],
   "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
   "released_at": "2025-05-29",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
    "deepseek-r1-0528-qwen3-8b",
    "deepseek-r1-0528-qwen3-8b:free",
    "deepseek/deepseek-r1-0528-qwen3-8b"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek-R1-0528-Qwen3-8B 将 DeepSeek-R1-0528 的链式思维能力蒸馏至 Qwen3 8B Base 模型中。在开源模型中达到 SOTA 水平，在 AIME 2024 上超越 Qwen3 8B 10%，并与 Qwen3-235B-thinking 表现相当。擅长数学推理、编程和通用逻辑任务，采用 Qwen3-8B 架构，并使用 DeepSeek-R1-0528 的分词器。",
    "zh-TW": "DeepSeek-R1-0528-Qwen3-8B 將 DeepSeek-R1-0528 的思維鏈（Chain-of-Thought）蒸餾至 Qwen3 8B Base。在開源模型中達到 SOTA 表現，於 AIME 2024 超越 Qwen3 8B 10%，並匹敵 Qwen3-235B-thinking 的表現。擅長數學推理、程式設計與邏輯基準測試。架構與 Qwen3-8B 相同，但使用 DeepSeek-R1-0528 的分詞器。",
    "ja-JP": "DeepSeek-R1-0528-Qwen3-8B は、DeepSeek-R1-0528 の連想思考を Qwen3 8B Base に蒸留したモデルです。AIME 2024 で Qwen3 8B を 10% 上回り、Qwen3-235B-thinking に匹敵する性能を発揮します。数学的推論、プログラミング、一般的な論理ベンチマークに優れています。Qwen3-8B のアーキテクチャを共有しつつ、DeepSeek-R1-0528 のトークナイザーを使用しています。",
    "ru-RU": "DeepSeek-R1-0528-Qwen3-8B — это дистиллят модели DeepSeek-R1-0528 на базе Qwen3 8B. Она достигает уровня SOTA среди открытых моделей, превосходя Qwen3 8B на 10% в AIME 2024 и сопоставима с производительностью Qwen3-235B-thinking. Отличается выдающимися результатами в математике, программировании и логике. Использует архитектуру Qwen3-8B и токенизатор DeepSeek-R1-0528."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 0528 Qwen3 8B"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-0528-TEE",
   "model_name": "DeepSeek-R1-0528-TEE",
   "display_name": "DeepSeek R1 0528 TEE",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 163840,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-R1-0528-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 0528 TEE"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-0528-tput",
   "model_name": "DeepSeek-R1-0528-tput",
   "display_name": "DeepSeek-R1-0528-tput",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528-tput"
    }
   ],
   "docs_url": "https://www.together.ai/models/deepseek-r1-0528-throughput",
   "max_input_tokens": 128000,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-R1-0528-tput"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-R1-0528-tput"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-0528-Turbo",
   "model_name": "DeepSeek-R1-0528-Turbo",
   "display_name": "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-0528-Turbo"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-07-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo",
    "deepseek-ai/DeepSeek-R1-0528-Turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-250528",
   "model_name": "deepseek-r1-250528",
   "display_name": "DeepSeek R1 250528",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    }
   ],
   "max_input_tokens": 144000,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "DeepSeek R1 250528 是 DeepSeek-R1 的完整推理模型，专为高难度数学与逻辑任务设计。",
    "zh-TW": "DeepSeek R1 250528 是專為高難度數學與邏輯任務設計的 DeepSeek-R1 全量推理模型。",
    "ja-JP": "DeepSeek R1 250528は、難解な数学および論理タスク向けのDeepSeek-R1フル推論モデルです。",
    "ru-RU": "DeepSeek R1 250528 — это полная модель логического вывода DeepSeek-R1, предназначенная для сложных математических и логических задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 250528"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-671b",
   "model_name": "deepseek-r1-671b",
   "display_name": "deepseek-r1-671b",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-r1-671b"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-baidu",
   "model_name": "deepseek-r1-baidu",
   "display_name": "deepseek-r1-baidu",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-02-05",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-r1-baidu"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-basic",
   "model_name": "deepseek-r1-basic",
   "display_name": "DeepSeek R1 (Basic)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-r1-basic"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 128000,
   "max_output_tokens": 20480,
   "model_type": "deep_thinking",
   "capabilities": {
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-r1-basic"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 (Basic)"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-Distill-Llama-70B",
   "model_name": "DeepSeek-R1-Distill-Llama-70B",
   "display_name": "DeepSeek R1 Distill Llama 70B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.99"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices+helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.99"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.74"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.852941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.852941"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.69"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-70b"
    }
   ],
   "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
   "released_at": "2025-01-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-01",
   "model_type": "deep_thinking",
   "docs_url": "https://nebius.com/prices-ai-studio",
   "deprecated": true,
   "deprecation_date": "2026-03-20",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-r1-distill-llama-70b",
    "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
    "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
    "deepseek-ai/deepseek-r1-distill-llama-70b",
    "deepseek-r1-distill-llama-70b",
    "deepseek-r1-distill-llama-70b:free",
    "deepseek/deepseek-r1-distill-llama-70b",
    "novita/deepseek/deepseek-r1-distill-llama-70b"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek R1 是 DeepSeek 系列中更大更智能的模型，已蒸馏至 Llama 70B 架构。基准测试和人工评估显示其在数学和事实精度任务上优于原始 Llama 70B。",
    "zh-TW": "DeepSeek R1 是 DeepSeek 系列中更大更智慧的模型，已蒸餾至 Llama 70B 架構。基準測試與人工評估顯示其在數學與事實精確任務上優於原始 Llama 70B。",
    "ja-JP": "DeepSeek R1は、DeepSeekスイートの中でより大規模かつ高性能なモデルであり、Llama 70Bアーキテクチャに蒸留されています。ベンチマークと人間による評価により、特に数学や事実精度のタスクで、ベースのLlama 70Bよりも優れていることが示されています。",
    "ru-RU": "DeepSeek R1, более крупная и умная модель из набора DeepSeek, дистиллирована в архитектуру Llama 70B. Бенчмарки и оценки людей показывают, что она умнее базовой Llama 70B, особенно в задачах по математике и точности фактов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Distill Llama 70B"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-Distill-Llama-70B-abliterated",
   "model_name": "DeepSeek-R1-Distill-Llama-70B-abliterated",
   "display_name": "DeepSeek R1 Llama 70B Abliterated",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated"
    }
   ],
   "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
   "released_at": "2025-01-20",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Llama 70B Abliterated"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-Distill-Llama-8B",
   "model_name": "DeepSeek-R1-Distill-Llama-8B",
   "display_name": "DeepSeek R1 Distill Llama 8B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-8b"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-8b"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-8b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "deepseek-r1-distill-llama-8b"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-llama-8b"
    }
   ],
   "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
   "released_at": "2025-01-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-r1-distill-llama-8b",
    "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
    "deepseek-r1-distill-llama-8b",
    "deepseek/deepseek-r1-distill-llama-8b"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek-R1-Distill-Llama-8B 由 Llama-3.1-8B 蒸馏而来，使用 DeepSeek R1 输出进行训练。",
    "zh-TW": "DeepSeek-R1-Distill-Llama-8B 是以 DeepSeek R1 輸出資料蒸餾自 Llama-3.1-8B。",
    "ja-JP": "DeepSeek-R1-Distill-Llama-8Bは、Llama-3.1-8BからDeepSeek R1の出力を用いて蒸留されたモデルです。",
    "ru-RU": "DeepSeek-R1-Distill-Llama-8B — дистиллированная модель на основе Llama-3.1-8B, обученная на выходных данных DeepSeek R1."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Distill Llama 8B"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-distill-qianfan-70b",
   "model_name": "deepseek-r1-distill-qianfan-70b",
   "display_name": "DeepSeek R1 Distill Qianfan 70B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "DeepSeek R1 Distill Qianfan 70B 是基于 Qianfan-70B 的 R1 蒸馏模型，具备强大价值。",
    "zh-TW": "DeepSeek R1 Distill Qianfan 70B 是基於 Qianfan-70B 的 R1 蒸餾模型，具備高價值表現。",
    "ja-JP": "DeepSeek R1 Distill Qianfan 70Bは、Qianfan-70BをベースにしたR1蒸留モデルで、高い価値を提供します。",
    "ru-RU": "DeepSeek R1 Distill Qianfan 70B — дистиллированная модель R1 на основе Qianfan-70B с высокой ценностью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Distill Qianfan 70B"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-distill-qianfan-8b",
   "model_name": "deepseek-r1-distill-qianfan-8b",
   "display_name": "DeepSeek R1 Distill Qianfan 8B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "DeepSeek R1 Distill Qianfan 8B 是基于 Qianfan-8B 的 R1 蒸馏模型，适用于中小型应用。",
    "zh-TW": "DeepSeek R1 Distill Qianfan 8B 是基於 Qianfan-8B 的 R1 蒸餾模型，適用於中小型應用場景。",
    "ja-JP": "DeepSeek R1 Distill Qianfan 8Bは、Qianfan-8BをベースにしたR1蒸留モデルで、小規模から中規模アプリケーションに適しています。",
    "ru-RU": "DeepSeek R1 Distill Qianfan 8B — дистиллированная модель R1 на базе Qianfan-8B, предназначенная для малых и средних приложений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Distill Qianfan 8B"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-distill-qianfan-llama-70b",
   "model_name": "deepseek-r1-distill-qianfan-llama-70b",
   "display_name": "DeepSeek R1 Distill Qianfan Llama 70B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "DeepSeek R1 Distill Qianfan Llama 70B 是基于 Llama-70B 的 R1 蒸馏模型。",
    "zh-TW": "DeepSeek R1 Distill Qianfan Llama 70B 是基於 Llama-70B 的 R1 蒸餾模型。",
    "ja-JP": "DeepSeek R1 Distill Qianfan Llama 70Bは、Llama-70BをベースにしたR1蒸留モデルです。",
    "ru-RU": "DeepSeek R1 Distill Qianfan Llama 70B — дистиллированная модель R1 на основе Llama-70B."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Distill Qianfan Llama 70B"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-distill-qianfan-llama-8b",
   "model_name": "deepseek-r1-distill-qianfan-llama-8b",
   "display_name": "deepseek-r1-distill-qianfan-llama-8b",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.137"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.548"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-r1-distill-qianfan-llama-8b"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-distill-qwen-1-5b",
   "model_name": "deepseek-r1-distill-qwen-1-5b",
   "display_name": "DeepSeek R1 Distill Qwen 1.5B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-1.5b"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-1.5b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18000000000000002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18000000000000002"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-01-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
    "deepseek-r1-distill-qwen-1.5b",
    "deepseek/deepseek-r1-distill-qwen-1.5b"
   ],
   "intro_i18n": {
    "zh-CN": "基于 Qwen2.5-Math-1.5B 的 DeepSeek-R1 蒸馏模型。通过强化学习与冷启动数据优化推理性能，在开源模型中树立多任务新基准。",
    "zh-TW": "基於 Qwen2.5-Math-1.5B 的 DeepSeek-R1 蒸餾模型。透過強化學習與冷啟動資料優化推理表現，為開源模型樹立多任務新基準。",
    "ja-JP": "Qwen2.5-Math-1.5BをベースにしたDeepSeek-R1蒸留モデル。強化学習とコールドスタートデータにより推論性能を最適化し、オープンモデルのマルチタスクベンチマークで新たな基準を打ち立てています。",
    "ru-RU": "Дистиллированная модель DeepSeek-R1 на основе Qwen2.5-Math-1.5B. Обучение с подкреплением и данные холодного старта оптимизируют производительность в логических задачах, устанавливая новые мультизадачные бенчмарки среди открытых моделей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Distill Qwen 1.5B"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-Distill-Qwen-14B",
   "model_name": "DeepSeek-R1-Distill-Qwen-14B",
   "display_name": "DeepSeek R1 Distill Qwen 14B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.431"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-14b"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.431"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-14b"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-14b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-14b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-qwen-14b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-14b"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-qwen-14b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "novita/deepseek/deepseek-r1-distill-qwen-14b"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.352941"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-14b"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-01-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-r1-distill-qwen-14b",
    "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
    "deepseek-r1-distill-qwen-14b",
    "deepseek-r1-distill-qwen-14b:free",
    "deepseek/deepseek-r1-distill-qwen-14b",
    "novita/deepseek/deepseek-r1-distill-qwen-14b"
   ],
   "intro_i18n": {
    "zh-CN": "基于Qwen2.5-14B的DeepSeek-R1蒸馏模型。通过强化学习和冷启动数据优化推理性能，为开放模型设立了新的多任务基准。",
    "zh-TW": "基於 Qwen2.5-14B 的 DeepSeek-R1 精煉模型。透過強化學習與冷啟動數據優化推理性能，為開放模型樹立了新的多任務基準。",
    "ja-JP": "DeepSeek-R1の蒸留モデルで、Qwen2.5-14Bをベースにしています。強化学習とコールドスタートデータにより推論性能を最適化し、オープンモデルのマルチタスクベンチマークを更新します。",
    "ru-RU": "Дистиллированная модель DeepSeek-R1 на основе Qwen2.5-14B. Обучение с подкреплением и данные для холодного старта оптимизируют производительность в области рассуждений, устанавливая новые эталонные показатели для многозадачных открытых моделей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Distill Qwen 14B"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-distill-qwen-1p5b",
   "model_name": "deepseek-r1-distill-qwen-1p5b",
   "display_name": "DeepSeek R1 Distill Qwen 1.5B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "deep_thinking",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Distill Qwen 1.5B"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-Distill-Qwen-32B",
   "model_name": "DeepSeek-R1-Distill-Qwen-32B",
   "display_name": "DeepSeek R1 Distill Qwen 32B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.861"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.88"
      }
     },
     "provider_model_id": "workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.497"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.881"
      }
     },
     "provider_model_id": "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.426471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.426471"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1853854632"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1853854632"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.320588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.320588"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "novita/deepseek/deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-32b"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-32b"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-01-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-07",
   "model_type": "deep_thinking",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/deepseek-ai/deepseek-r1-distill-qwen-32b",
    "accounts/fireworks/models/deepseek-r1-distill-qwen-32b",
    "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
    "deepseek-r1-distill-qwen-32b",
    "deepseek/deepseek-r1-distill-qwen-32b",
    "novita/deepseek/deepseek-r1-distill-qwen-32b",
    "workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek-R1系列通过强化学习和冷启动数据提升推理性能，为开放模型设立了新的多任务基准，并超越了OpenAI o1-mini。",
    "zh-TW": "DeepSeek-R1 系列透過強化學習與冷啟動數據提升推理性能，為開放模型樹立了新的多任務基準，並超越了 OpenAI o1-mini。",
    "ja-JP": "DeepSeek-R1シリーズは、強化学習とコールドスタートデータを活用して推論性能を向上させ、オープンモデルのマルチタスクベンチマークを更新し、OpenAI o1-miniを超えています。",
    "ru-RU": "Серия DeepSeek-R1 улучшает производительность в области рассуждений с помощью обучения с подкреплением и данных для холодного старта, устанавливая новые эталонные показатели для многозадачных открытых моделей и превосходя OpenAI o1-mini."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.1854741168",
     "new": "0.1853854632"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.1854741168",
     "new": "0.1853854632"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.1856029644",
     "new": "0.1854741168"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.1856029644",
     "new": "0.1854741168"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.1857986172",
     "new": "0.1856029644"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.1857986172",
     "new": "0.1856029644"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.1858365558",
     "new": "0.1857986172"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.1858365558",
     "new": "0.1857986172"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.1857707712",
     "new": "0.1858365558"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.1857707712",
     "new": "0.1858365558"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.185445477",
     "new": "0.1857707712"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.185445477",
     "new": "0.1857707712"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Distill Qwen 32B"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-Distill-Qwen-32B-abliterated",
   "model_name": "DeepSeek-R1-Distill-Qwen-32B-abliterated",
   "display_name": "DeepSeek R1 Qwen Abliterated",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-01-20",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Qwen Abliterated"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-Distill-Qwen-7B",
   "model_name": "DeepSeek-R1-Distill-Qwen-7B",
   "display_name": "DeepSeek R1 Distill Qwen 7B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.144"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-7b"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.144"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-7b"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-7b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "deepseek-r1-distill-qwen-7b"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2025-01-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-r1-distill-qwen-7b",
    "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
    "deepseek-r1-distill-qwen-7b"
   ],
   "intro_i18n": {
    "zh-CN": "基于 Qwen2.5-Math-7B 的 DeepSeek-R1 蒸馏模型。通过强化学习与冷启动数据优化推理性能，在开源模型中树立多任务新基准。",
    "zh-TW": "基於 Qwen2.5-Math-7B 的 DeepSeek-R1 蒸餾模型。透過強化學習與冷啟動資料優化推理表現，為開源模型樹立多任務新基準。",
    "ja-JP": "Qwen2.5-Math-7BをベースにしたDeepSeek-R1蒸留モデル。強化学習とコールドスタートデータにより推論性能を最適化し、オープンモデルのマルチタスクベンチマークで新たな基準を打ち立てています。",
    "ru-RU": "Дистиллированная модель DeepSeek-R1 на основе Qwen2.5-Math-7B. Обучение с подкреплением и данные холодного старта оптимизируют производительность в логических задачах, устанавливая новые мультизадачные бенчмарки среди открытых моделей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Distill Qwen 7B"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-huoshan",
   "model_name": "deepseek-r1-huoshan",
   "display_name": "deepseek-r1-huoshan",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-02-05",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-r1-huoshan"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-huoshan-0528",
   "model_name": "deepseek-r1-huoshan-0528",
   "display_name": "deepseek-r1-huoshan-0528",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-05-30",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-r1-huoshan-0528"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-Original",
   "model_name": "DeepSeek-R1-Original",
   "display_name": "DeepSeek-R1-Original",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Original"
    }
   ],
   "max_input_tokens": 160000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-R1-Original"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-R1-Original"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1-sambanova",
   "model_name": "deepseek-r1-sambanova",
   "display_name": "DeepSeek R1 Fast",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.987"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-02-20",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 Fast"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-TEE",
   "model_name": "DeepSeek-R1-TEE",
   "display_name": "DeepSeek R1 TEE",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 163840,
   "max_output_tokens": 163840,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "deepseek-thinking",
   "capabilities": {
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-R1-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 TEE"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-Turbo",
   "model_name": "DeepSeek-R1-Turbo",
   "display_name": "DeepSeek R1 (Turbo)\t",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Turbo"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "deepseek-r1-turbo"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1-turbo"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "novita/deepseek/deepseek-r1-turbo"
    }
   ],
   "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
   "released_at": "2025-03-05",
   "max_input_tokens": 64000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-R1-Turbo",
    "deepseek-r1-turbo",
    "deepseek/deepseek-r1-turbo",
    "novita/deepseek/deepseek-r1-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 (Turbo)\t"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1-Zero",
   "model_name": "DeepSeek-R1-Zero",
   "display_name": "deepseek-ai/DeepSeek-R1-Zero",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-R1-Zero"
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-R1-Zero"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/DeepSeek-R1-Zero"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-R1T-Chimera",
   "model_name": "DeepSeek-R1T-Chimera",
   "display_name": "DeepSeek R1T Chimera",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "tngtech/DeepSeek-R1T-Chimera"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "tngtech/DeepSeek-R1T-Chimera"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "tngtech/deepseek-r1t-chimera"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek-r1t-chimera:free"
    }
   ],
   "max_input_tokens": 163840,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true,
    "stream": true,
    "open_weights": true,
    "prompt_caching": true
   },
   "released_at": "2025-12-29",
   "family": "tngtech",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-r1t-chimera:free",
    "tngtech/DeepSeek-R1T-Chimera",
    "tngtech/deepseek-r1t-chimera"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1T Chimera"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-r1t2-chimera",
   "model_name": "deepseek-r1t2-chimera",
   "display_name": "TNG: DeepSeek R1T2 Chimera",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "tngtech/deepseek-r1t2-chimera"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "deepseek-r1t2-chimera:free"
    }
   ],
   "max_input_tokens": 163840,
   "max_output_tokens": 163840,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "released_at": "2025-07-08",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-r1t2-chimera:free",
    "tngtech/deepseek-r1t2-chimera"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TNG: DeepSeek R1T2 Chimera"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-reasoner",
   "model_name": "deepseek-reasoner",
   "display_name": "DeepSeek Reasoner",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepseek",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+helicone-registry+portkey+llmdb+pricetoken+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek/deepseek-reasoner"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek/deepseek-reasoner"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek/deepseek-reasoner"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "deepseek/deepseek-reasoner"
    }
   ],
   "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true
   },
   "docs_url": "https://api-docs.deepseek.com/quick_start/pricing",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "stream",
     "temperature",
     "top_logprobs",
     "top_p"
    ]
   },
   "deprecated": true,
   "status": "deprecated",
   "aliases": [
    "deepseek/deepseek-reasoner"
   ],
   "intro_i18n": {
    "zh-CN": "一个专注于复杂逻辑推理任务的 DeepSeek 推理模型。",
    "zh-TW": "一款專注於複雜邏輯推理任務的 DeepSeek 推理模型。",
    "ja-JP": "複雑な論理的推論タスクに特化したDeepSeekの推論モデルです。",
    "ru-RU": "Модель DeepSeek, ориентированная на выполнение сложных логических задач."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-reasoner-cheaper",
   "model_name": "deepseek-reasoner-cheaper",
   "display_name": "Deepseek R1 Cheaper",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-01-20",
   "max_input_tokens": 128000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Deepseek R1 Cheaper"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-TNG-R1T2-Chimera",
   "model_name": "DeepSeek-TNG-R1T2-Chimera",
   "display_name": "DeepSeek TNG R1T2 Chimera",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "tngtech/DeepSeek-TNG-R1T2-Chimera"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepseek-tng-r1t2-chimera"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-07-02",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 130000,
   "max_output_tokens": 163840,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "functions",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-tng-r1t2-chimera",
    "tngtech/DeepSeek-TNG-R1T2-Chimera"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek TNG R1T2 Chimera"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V2-Chat",
   "model_name": "DeepSeek-V2-Chat",
   "display_name": "deepseek-ai/DeepSeek-V2-Chat",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V2-Chat"
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V2-Chat"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/DeepSeek-V2-Chat"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v2-lite-chat",
   "model_name": "deepseek-v2-lite-chat",
   "display_name": "DeepSeek V2 Lite Chat",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-v2-lite-chat"
    }
   ],
   "max_input_tokens": 163840,
   "max_output_tokens": 163840,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-v2-lite-chat"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V2 Lite Chat"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V2.5",
   "model_name": "DeepSeek-V2.5",
   "display_name": "deepseek-ai/DeepSeek-V2.5",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V2.5"
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V2.5"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/DeepSeek-V2.5"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v2p5",
   "model_name": "deepseek-v2p5",
   "display_name": "DeepSeek V2.5",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-v2p5"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-v2p5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V2.5"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3",
   "model_name": "deepseek-v3",
   "display_name": "deepseek-v3",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepseek",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.272"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.088"
      }
     },
     "provider_model_id": "DeepSeek-V3"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.147"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.147"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.56"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.56"
      }
     }
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.56"
      }
     },
     "provider_model_id": "DeepSeek-V3"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.89"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "DeepSeek-V3"
    },
    {
     "provider": "drun",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "public/deepseek-v3"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-v3"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-v3"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "DeepSeek-V3"
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9441"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8443"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.472"
      }
     }
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29426264"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.17705056"
      }
     },
     "provider_model_id": "DeepSeek-V3"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "DeepSeek-V3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     }
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15942"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-V3"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "hf:deepseek-ai/DeepSeek-V3"
    },
    {
     "provider": "tencentcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.89"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-V3"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.77"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.77"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3"
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-08-13",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "knowledge_cutoff": "2024-07",
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "DeepSeek-V3",
    "Pro/deepseek-ai/DeepSeek-V3",
    "accounts/fireworks/models/deepseek-v3",
    "deepinfra/deepseek-ai/DeepSeek-V3",
    "deepseek-ai/DeepSeek-V3",
    "deepseek/deepseek-v3",
    "hf:deepseek-ai/DeepSeek-V3",
    "public/deepseek-v3"
   ],
   "intro_i18n": {
    "zh-CN": "字节跳动火山引擎的开放部署目前是最稳定的；推荐使用。已自动升级至最新版本（250324）。",
    "zh-TW": "字節跳動火山引擎的開放部署目前是最穩定的；推薦使用。已自動升級至最新版本（250324）。",
    "ja-JP": "ByteDance Volcengineのオープンデプロイメントは現在最も安定しており、推奨されています。最新リリース（250324）に自動アップグレードされています。",
    "ru-RU": "Открытое развертывание ByteDance Volcengine в настоящее время является самым стабильным; рекомендуется. Автоматически обновлено до последней версии (250324)."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17761344",
     "new": "1.17705056"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29440336",
     "new": "0.29426264"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.4855",
     "new": "0.472"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.0303",
     "new": "1.8443"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.9711",
     "new": "0.9441"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17843152",
     "new": "1.17761344"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29460788",
     "new": "0.29440336"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.469",
     "new": "0.4855"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "1.8343",
     "new": "2.0303"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.9381",
     "new": "0.9711"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17967376",
     "new": "1.17843152"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29491844",
     "new": "0.29460788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.4556",
     "new": "0.469"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "1.7703",
     "new": "1.8343"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.9111",
     "new": "0.9381"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17991464",
     "new": "1.17967376"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29497866",
     "new": "0.29491844"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17949696",
     "new": "1.17991464"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29487424",
     "new": "0.29497866"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.1774316",
     "new": "1.17949696"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3_1",
   "model_name": "DeepSeek-V3_1",
   "display_name": "DeepSeek-V3_1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76557584"
      }
     }
    }
   ],
   "released_at": "2025-08-25",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76642016",
     "new": "1.76557584"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76764728",
     "new": "1.76642016"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76951064",
     "new": "1.76764728"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76987196",
     "new": "1.76951064"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76924544",
     "new": "1.76987196"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.7661474",
     "new": "1.76924544"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3_1"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3_1-Terminus",
   "model_name": "DeepSeek-V3_1-Terminus",
   "display_name": "DeepSeek-V3_1-Terminus",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76557584"
      }
     }
    }
   ],
   "released_at": "2025-09-24",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76642016",
     "new": "1.76557584"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76764728",
     "new": "1.76642016"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76951064",
     "new": "1.76764728"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76987196",
     "new": "1.76951064"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76924544",
     "new": "1.76987196"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.7661474",
     "new": "1.76924544"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3_1-Terminus"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3-0324",
   "model_name": "DeepSeek-V3-0324",
   "display_name": "DeepSeek-V3-0324",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "siliconflow/deepseek-v3-0324"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "siliconflow/deepseek-v3-0324"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.56"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.56"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.56"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.551"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.654"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.067"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3-0324"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3-0324"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3-0324"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3-0324"
    },
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3-0324"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1875"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3-0324"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3-0324"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15942"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "novita/deepseek/deepseek-v3-0324"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     }
    },
    {
     "provider": "submodel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3-0324"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "hf:deepseek-ai/DeepSeek-V3-0324"
    },
    {
     "provider": "tencentcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     },
     "provider_model_id": "deepseek-v3-0324"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.106"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-V3-0324"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3-0324"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3-0324"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-08-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "family": "deepseek",
   "knowledge_cutoff": "2024-07",
   "docs_url": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438",
   "model_type": "text_generation",
   "deprecated": true,
   "deprecation_date": "2026-04-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-v3-0324",
    "deepinfra/deepseek-ai/DeepSeek-V3-0324",
    "deepseek-ai/DeepSeek-V3-0324",
    "deepseek-v3-0324",
    "deepseek/deepseek-v3-0324",
    "hf:deepseek-ai/DeepSeek-V3-0324",
    "novita/deepseek/deepseek-v3-0324",
    "siliconflow/deepseek-v3-0324"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek-V3-0324 是一款拥有 671B 参数的 MoE 模型，在编程与技术能力、上下文理解和长文本处理方面表现突出。",
    "zh-TW": "DeepSeek-V3-0324 是一款擁有 671B 參數的 MoE 模型，在程式設計、技術能力、語境理解與長文本處理方面表現出色。",
    "ja-JP": "DeepSeek-V3-0324は、671BパラメータのMoEモデルで、プログラミングや技術的能力、文脈理解、長文処理において優れた性能を発揮します。",
    "ru-RU": "DeepSeek-V3-0324 — модель MoE с 671B параметрами, выделяющаяся в программировании, технических задачах, понимании контекста и работе с длинными текстами."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3-0324"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3-0324-fast",
   "model_name": "DeepSeek-V3-0324-fast",
   "display_name": "DeepSeek-V3-0324 (Fast)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.28125"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3-0324-fast"
    }
   ],
   "released_at": "2025-03-24",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V3-0324-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3-0324 (Fast)"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3-0324-TEE",
   "model_name": "DeepSeek-V3-0324-TEE",
   "display_name": "DeepSeek V3 0324 TEE",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.095"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3-0324-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 163840,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V3-0324-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3 0324 TEE"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3-1",
   "model_name": "DeepSeek-V3-1",
   "display_name": "DeepSeek-V3.1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "deepseek-v3-1"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.66"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.721"
      }
     },
     "provider_model_id": "deepseek-v3-1"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.721"
      }
     },
     "provider_model_id": "deepseek-v3-1"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "deepseek-v3.1"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "deepseek-v3.1"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "deepseek-v3.1"
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.216"
      }
     },
     "provider_model_id": "DeepSeek-V3.1"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1300000002"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-v3-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     },
     "provider_model_id": "deepseek-v3.1"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     },
     "provider_model_id": "deepseek-v3.1"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.112"
      }
     },
     "provider_model_id": "deepseek-v3.1"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek-v3.1"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepseek-v3-1"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.73913"
      }
     },
     "provider_model_id": "deepseek-v3.1"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-V3.1"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "DeepSeek-V3.1"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1"
    },
    {
     "provider": "submodel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "hf:deepseek-ai/DeepSeek-V3.1"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.168"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-V3.1"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+litellm+truefoundry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3-1"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.65"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-08-19",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true,
    "web_search": true
   },
   "family": "deepseek",
   "knowledge_cutoff": "2024-07",
   "reasoning_config": {
    "budget_min": 128
   },
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "DeepSeek-V3.1",
    "TEE/deepseek-v3.1",
    "deepinfra/deepseek-ai/DeepSeek-V3.1",
    "deepseek-ai/DeepSeek-V3-1",
    "deepseek-ai/DeepSeek-V3.1",
    "deepseek-ai/DeepSeek-V3.1:thinking",
    "deepseek-ai/deepseek-v3-1",
    "deepseek-v3-1",
    "deepseek-v3.1",
    "deepseek/deepseek-v3.1",
    "hf:deepseek-ai/DeepSeek-V3.1"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek V3.1 是新一代推理模型，提升了复杂推理与思维链能力，适用于深度分析任务。",
    "zh-TW": "DeepSeek V3.1 是新一代推理模型，強化複雜推理與思維鏈能力，適用於深度分析任務。",
    "ja-JP": "DeepSeek V3.1は、複雑な推論と思考の連鎖を強化した次世代推論モデルで、深い分析タスクに適しています。",
    "ru-RU": "DeepSeek V3.1 — модель нового поколения для логических задач с улучшенными возможностями сложного рассуждения и цепочек размышлений, подходящая для глубокого анализа."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3.1"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3-1-huoshan",
   "model_name": "deepseek-v3-1-huoshan",
   "display_name": "deepseek-v3.1-huoshan",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.71"
      }
     }
    }
   ],
   "released_at": "2025-08-22",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-v3.1-huoshan"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3-1-thinking",
   "model_name": "deepseek-v3-1-thinking",
   "display_name": "deepseek-v3.1-thinking",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     }
    }
   ],
   "released_at": "2025-08-24",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-v3.1-thinking"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3-2-exp",
   "model_name": "deepseek-v3-2-exp",
   "display_name": "DeepSeek/DeepSeek-V3.2-Exp",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepseek",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     },
     "provider_model_id": "deepseek-v3.2-exp"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     },
     "provider_model_id": "deepseek-v3.2-exp"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.431"
      }
     },
     "provider_model_id": "deepseek-v3.2-exp"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.287"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.431"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2-Exp"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "deepseek-v3.2-exp"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-exp"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2-Exp"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27999999999999997"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42000000000000004"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-v3.2-exp"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     },
     "provider_model_id": "deepseek-v3.2-exp"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-exp"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-exp"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43478"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-exp"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2-Exp"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-exp"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-exp"
    }
   ],
   "intro": "DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true,
    "web_search": true
   },
   "released_at": "2025-09-29",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "knowledge_cutoff": "2025-01",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.6,
     "top_p": 0.95
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V3.2-Exp",
    "deepseek-ai/deepseek-v3.2-exp",
    "deepseek-v3.2-exp",
    "deepseek/deepseek-v3.2-exp"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek V3.2 Exp 使用混合推理架构，支持思考模式和非思考模式。",
    "zh-TW": "DeepSeek V3.2 Exp 採用混合推理架構，支持思考模式和非思考模式。",
    "ja-JP": "DeepSeek V3.2 Expは、ハイブリッド推論アーキテクチャを使用し、思考モードと非思考モードの両方をサポートします。",
    "ru-RU": "DeepSeek V3.2 Exp использует гибридную архитектуру рассуждений и поддерживает как режимы мышления, так и немышления."
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.44237766",
     "new": "0.44191182"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29491844",
     "new": "0.29460788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.44246799",
     "new": "0.44237766"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29497866",
     "new": "0.29491844"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.44231136",
     "new": "0.44246799"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29487424",
     "new": "0.29497866"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.44153685",
     "new": "0.44231136"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2943579",
     "new": "0.29487424"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek/DeepSeek-V3.2-Exp"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3-302",
   "model_name": "deepseek-v3-302",
   "display_name": "deepseek-r1-aliyun",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-02-05",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-r1-aliyun"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3-aliyun",
   "model_name": "deepseek-v3-aliyun",
   "display_name": "deepseek-v3-aliyun",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2025-02-05",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-v3-aliyun"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3-baidu",
   "model_name": "deepseek-v3-baidu",
   "display_name": "deepseek-v3-baidu",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2025-02-05",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-v3-baidu"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3-base",
   "model_name": "deepseek-v3-base",
   "display_name": "deepseek-v3-base",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-v3-base"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3-Fast",
   "model_name": "DeepSeek-V3-Fast",
   "display_name": "DeepSeek V3 (Fast)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     }
    }
   ],
   "max_input_tokens": 65536,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "提供方：sophnet。DeepSeek V3 Fast 是 DeepSeek V3 0324 的高 TPS 版本，采用全精度（非量化），在代码与数学方面更强，响应更快。",
    "zh-TW": "提供者：sophnet。DeepSeek V3 Fast 是 DeepSeek V3 0324 的高 TPS 版本，為全精度（非量化）模型，具備更強的程式碼與數學能力，回應速度更快。",
    "ja-JP": "提供元：sophnet。DeepSeek V3 Fastは、DeepSeek V3 0324の高TPSバージョンで、フル精度（非量子化）により、コードと数学に強く、応答も高速です。",
    "ru-RU": "Провайдер: sophnet. DeepSeek V3 Fast — высокоэффективная версия DeepSeek V3 0324, с полной точностью (без квантования), улучшенной производительностью в коде и математике и более быстрыми ответами."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3 (Fast)"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3-huoshan",
   "model_name": "deepseek-v3-huoshan",
   "display_name": "deepseek-v3-huoshan",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2025-02-05",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-v3-huoshan"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3-turbo",
   "model_name": "deepseek-v3-turbo",
   "display_name": "DeepSeek V3 (Turbo)\t",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3-turbo"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3-turbo"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "novita/deepseek/deepseek-v3-turbo"
    }
   ],
   "intro": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
   "released_at": "2025-03-05",
   "max_input_tokens": 64000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-v3-turbo",
    "novita/deepseek/deepseek-v3-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3 (Turbo)\t"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3.1-Base",
   "model_name": "DeepSeek-V3.1-Base",
   "display_name": "DeepSeek-V3.1-Base",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1-Base"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V3.1-Base"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3.1-Base"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3.1-cb",
   "model_name": "DeepSeek-V3.1-cb",
   "display_name": "DeepSeek-V3.1-cb",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3.1-cb"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.1-maas",
   "model_name": "deepseek-v3.1-maas",
   "display_name": "DeepSeek V3.1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-v3.1-maas",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-v3.1-maas",
     "region": "us-west2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-08-28",
   "max_input_tokens": 163840,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/deepseek-v3.1-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.1"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3.1-Nex-N1",
   "model_name": "DeepSeek-V3.1-Nex-N1",
   "display_name": "Nex AGI: DeepSeek V3.1 Nex N1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "nex-agi/deepseek-v3.1-nex-n1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27999999999999997"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42000000000000004"
      }
     },
     "provider_model_id": "nex-agi/deepseek-v3.1-nex-n1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.135"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "nex-agi/deepseek-v3.1-nex-n1"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "nex-agi/DeepSeek-V3.1-Nex-N1"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-01-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 163840,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "stream": true
   },
   "family": "deepseek",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nex-agi/DeepSeek-V3.1-Nex-N1",
    "nex-agi/deepseek-v3.1-nex-n1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nex AGI: DeepSeek V3.1 Nex N1"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3.1-TEE",
   "model_name": "DeepSeek-V3.1-TEE",
   "display_name": "DeepSeek V3.1 TEE",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 163840,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V3.1-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.1 TEE"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3.1-Terminus-TEE",
   "model_name": "DeepSeek-V3.1-Terminus-TEE",
   "display_name": "DeepSeek V3.1 Terminus TEE",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1-Terminus-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 163840,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V3.1-Terminus-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.1 Terminus TEE"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.1-terminus-thinking",
   "model_name": "deepseek-v3.1-terminus-thinking",
   "display_name": "DeepSeek/DeepSeek-V3.1-Terminus-Thinking",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.73913"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1-terminus-thinking"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-09-22",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-v3.1-terminus-thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek/DeepSeek-V3.1-Terminus-Thinking"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3.1-Terminus:thinking",
   "model_name": "DeepSeek-V3.1-Terminus:thinking",
   "display_name": "DeepSeek/DeepSeek-V3.1-Terminus",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepseek",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepseek-v3.1-terminus"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "siliconflow/deepseek-v3.1-terminus"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "siliconflow/deepseek-v3.1-terminus"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.44"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "deepseek-v3.1-terminus"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.216"
      }
     },
     "provider_model_id": "DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.21600000000000003"
      }
     },
     "provider_model_id": "deepseek-v3.1-terminus"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     },
     "provider_model_id": "deepseek-v3.1-terminus"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1-terminus"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek-v3.1-terminus"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1-terminus"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1-terminus"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.73913"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1-terminus"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "hf:deepseek-ai/DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.168"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.1-Terminus"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.1-terminus"
    }
   ],
   "intro": "DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities.",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "released_at": "2025-09-22",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "knowledge_cutoff": "2025-07",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 30.4,
    "coding_index": 43.5,
    "agentic_index": 18.1
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "DeepSeek-V3.1-Terminus",
    "Pro/deepseek-ai/DeepSeek-V3.1-Terminus",
    "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus",
    "deepseek-ai/DeepSeek-V3.1-Terminus",
    "deepseek-ai/DeepSeek-V3.1-Terminus:thinking",
    "deepseek-v3.1-terminus",
    "deepseek/deepseek-v3.1-terminus",
    "deepseek/deepseek-v3.1-terminus:exacto",
    "hf:deepseek-ai/DeepSeek-V3.1-Terminus",
    "siliconflow/deepseek-v3.1-terminus"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek-V3.1-Terminus 是 V3.1 的更新版本，定位为混合代理大模型。该版本修复了用户反馈的问题，提升了稳定性、语言一致性，并减少了中英文混杂和异常字符。它集成了思维模式与非思维模式，并配备聊天模板以实现灵活切换。同时还提升了代码代理和搜索代理的性能，使工具使用和多步骤任务更加可靠。",
    "zh-TW": "DeepSeek-V3.1-Terminus 是 V3.1 版本的更新模型，定位為混合代理型大型語言模型。修復了用戶回報的問題，提升穩定性與語言一致性，減少中英混雜與異常字符。整合思考與非思考模式，並提供聊天模板以靈活切換。強化了程式代理與搜尋代理的表現，提升工具使用與多步任務的可靠性。",
    "ja-JP": "DeepSeek-V3.1-Terminusは、ハイブリッドエージェントLLMとして位置づけられたV3.1の改良版です。ユーザーから報告された問題を修正し、安定性と言語の一貫性を向上。中英混在や異常文字を削減。思考モードと非思考モードをチャットテンプレートで柔軟に切り替え可能。Code AgentとSearch Agentの性能も向上し、ツール使用やマルチステップタスクの信頼性が高まりました。",
    "ru-RU": "DeepSeek-V3.1-Terminus — обновлённая модель V3.1, позиционируемая как гибридная агентная LLM. Исправляет ошибки, сообщённые пользователями, повышает стабильность, согласованность языка и снижает количество смешанных китайско-английских и аномальных символов. Интегрирует режимы размышления и без размышлений с шаблонами чата для гибкого переключения. Также улучшает производительность агентов кода и поиска для более надёжного использования инструментов и многошаговых задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek/DeepSeek-V3.1-Terminus"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3.1-Think",
   "model_name": "DeepSeek-V3.1-Think",
   "display_name": "DeepSeek V3.1 (Think)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "DeepSeek-V3.1 思考模式：新型混合推理模型，支持思考与非思考模式，效率优于 DeepSeek-R1-0528。后训练优化显著提升智能体工具使用与任务表现。",
    "zh-TW": "DeepSeek-V3.1 思考模式：新型混合推理模型，具備思考與非思考模式，效率優於 DeepSeek-R1-0528。後訓練優化顯著提升代理工具使用與任務表現。",
    "ja-JP": "DeepSeek-V3.1の思考モード：思考と非思考の両モードを備えた新しいハイブリッド推論モデルで、DeepSeek-R1-0528よりも効率的です。ポストトレーニングの最適化により、エージェントのツール使用とタスク性能が大幅に向上しています。",
    "ru-RU": "Режим мышления DeepSeek-V3.1: новая гибридная модель рассуждения с режимами мышления и немышления, более эффективная, чем DeepSeek-R1-0528. Оптимизации после обучения значительно улучшают использование инструментов и выполнение агентных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.1 (Think)"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.1-think-250821",
   "model_name": "deepseek-v3.1-think-250821",
   "display_name": "DeepSeek V3.1 Think 250821",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    }
   ],
   "max_input_tokens": 144000,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "DeepSeek V3.1 Think 250821 是对应 Terminus 版本的深度思考模型，专为高性能推理任务打造。",
    "zh-TW": "DeepSeek V3.1 Think 250821 是對應 Terminus 版本的深度思考模型，專為高效推理而設計。",
    "ja-JP": "DeepSeek V3.1 Think 250821は、Terminusバージョンに対応する深い思考モデルで、高性能な推論に対応します。",
    "ru-RU": "DeepSeek V3.1 Think 250821 — модель глубокого мышления, соответствующая версии Terminus, созданная для высокоэффективного логического вывода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.1 Think 250821"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.1-tm",
   "model_name": "deepseek-v3.1-tm",
   "display_name": "DeepSeek-V3.1-TM",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2727"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.0101"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1364"
      }
     }
    }
   ],
   "released_at": "2025-09-22",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3.1-TM"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.1:671b",
   "model_name": "deepseek-v3.1:671b",
   "display_name": "deepseek-v3.1:671b",
   "vendor": "deepseek",
   "pricing": [],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-08-21",
   "max_input_tokens": 163840,
   "max_output_tokens": 163840,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "DeepSeek V3.1 是下一代推理模型，具备更强的复杂推理与链式思维能力，适用于需要深度分析的任务。",
    "zh-TW": "DeepSeek V3.1 是新一代推理模型，強化複雜推理與思路鏈能力，適合需要深入分析的任務。",
    "ja-JP": "DeepSeek V3.1は、複雑な推論とChain-of-Thoughtに優れた次世代推論モデルで、深い分析を必要とするタスクに適しています。",
    "ru-RU": "DeepSeek V3.1 — модель логического вывода следующего поколения с улучшенным сложным мышлением и цепочкой рассуждений, подходящая для задач, требующих глубокого анализа."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-v3.1:671b"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.2",
   "model_name": "deepseek-v3.2",
   "display_name": "deepseek-v3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepseek",
     "official": true,
     "source": "litellm+pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "paratera/deepseek-v3.2"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0302"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      }
     },
     "provider_model_id": "siliconflow/deepseek-v3.2"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      }
     },
     "provider_model_id": "siliconflow/deepseek-v3.2"
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "avian",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.012"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     }
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "bytedance",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.266"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.444"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.067"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "deepseek-v3-2"
    },
    {
     "provider": "friendli",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.056"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-v3-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     }
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9441"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8443"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.47205"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.7125"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29426264"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44139396"
      }
     },
     "provider_model_id": "DeepSeek-V3.2"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27999999999999997"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42000000000000004"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.269"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1345"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.269"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1345"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2288"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3432"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02288"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "novita/deepseek-v3.2"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1345"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "nebius/deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4928"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7392"
      }
     },
     "provider_model_id": "route/deepseek-v3.2"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "DeepSeek-V3.2"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     },
     "provider_model_id": "DeepSeek-V3.2"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "hf:deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-V3.2"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.37999988"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2"
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0293"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2"
    }
   ],
   "max_input_tokens": 163840,
   "max_output_tokens": 163840,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "open_weights": true,
    "stream": true,
    "image_output": true
   },
   "intro": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.",
   "released_at": "2025-12-03",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "knowledge_cutoff": "2024-07",
   "deprecated": true,
   "status": "deprecated",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "docs_url": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549",
   "benchmarks": {
    "intelligence_index": 32,
    "coding_index": 44.2,
    "agentic_index": 18.3
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "DeepSeek-V3.2",
    "Pro/deepseek-ai/DeepSeek-V3.2",
    "TEE/deepseek-v3.2",
    "deepinfra/deepseek-ai/DeepSeek-V3.2",
    "deepseek-ai/DeepSeek-V3.2",
    "deepseek-ai/deepseek-v3-2",
    "deepseek-v3-2",
    "deepseek/deepseek-v3.2",
    "deepseek/deepseek-v3.2:thinking",
    "hf:deepseek-ai/DeepSeek-V3.2",
    "nebius/deepseek-ai/DeepSeek-V3.2",
    "novita/deepseek-v3.2",
    "novita/deepseek/deepseek-v3.2",
    "paratera/deepseek-v3.2",
    "route/deepseek-v3.2",
    "siliconflow/deepseek-v3.2",
    "sophnet/deepseek-v3.2",
    "vertex/deepseek-v3.2"
   ],
   "intro_i18n": {
    "zh-CN": "deepseek-v3.2 引入稀疏注意力机制，旨在提升处理长文本时的训练与推理效率，且价格低于 deepseek-v3.1。",
    "zh-TW": "deepseek-v3.2 採用稀疏注意力機制，旨在提升處理長文本時的訓練與推理效率，成本低於 deepseek-v3.1。",
    "ja-JP": "deepseek-v3.2 はスパースアテンション機構を導入し、長文処理における学習と推論の効率を向上させています。また、deepseek-v3.1 より低価格で提供されます。",
    "ru-RU": "deepseek-v3.2 использует разреженный механизм внимания, что повышает эффективность обучения и инференса при обработке длинных текстов. Стоимость ниже, чем у deepseek-v3.1."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.44160504",
     "new": "0.44139396"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29440336",
     "new": "0.29426264"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.48555",
     "new": "0.47205"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.0303",
     "new": "1.8443"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.9711",
     "new": "0.9441"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.44191182",
     "new": "0.44160504"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29460788",
     "new": "0.29440336"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.46905",
     "new": "0.48555"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "1.8343",
     "new": "2.0303"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.9381",
     "new": "0.9711"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.44237766",
     "new": "0.44191182"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29491844",
     "new": "0.29460788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.45555",
     "new": "0.46905"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "1.7703",
     "new": "1.8343"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.9111",
     "new": "0.9381"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.44246799",
     "new": "0.44237766"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29497866",
     "new": "0.29491844"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.44231136",
     "new": "0.44246799"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29487424",
     "new": "0.29497866"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.44153685",
     "new": "0.44231136"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.2-251201",
   "model_name": "deepseek-v3.2-251201",
   "display_name": "Deepseek/DeepSeek-V3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43478"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-251201"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-v3.2-251201"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "Deepseek/DeepSeek-V3.2"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.2-el",
   "model_name": "deepseek-v3.2-el",
   "display_name": "DeepSeek-V3.2-EL",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5758"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7273"
      }
     }
    }
   ],
   "released_at": "2026-04-06",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3.2-EL"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.2-exp-thinking",
   "model_name": "deepseek-v3.2-exp-thinking",
   "display_name": "DeepSeek/DeepSeek-V3.2-Exp-Thinking",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27999999999999997"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42000000000000004"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-v3.2-exp-thinking"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43478"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-exp-thinking"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-09-29",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "family": "deepseek-thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/deepseek-v3.2-exp-thinking",
    "deepseek/deepseek-v3.2-exp-thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek/DeepSeek-V3.2-Exp-Thinking"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3.2-fast",
   "model_name": "DeepSeek-V3.2-fast",
   "display_name": "DeepSeek-V3.2-fast",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.29"
      }
     },
     "provider_model_id": "deepseek-v3.2-fast"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2-fast"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-01-27",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 8000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "family": "deepseek",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V3.2-fast",
    "deepseek-v3.2-fast"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3.2-fast"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.2-maas",
   "model_name": "deepseek-v3.2-maas",
   "display_name": "DeepSeek V3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.056"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-v3.2-maas",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.056"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-v3.2-maas",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-12-17",
   "max_input_tokens": 163840,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/deepseek-v3.2-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.2"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.2-speciale",
   "model_name": "deepseek-v3.2-speciale",
   "display_name": "DeepSeek-V3.2-Speciale",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "ai360",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-speciale"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27999999999999997"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42000000000000004"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-speciale"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-speciale"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true
   },
   "docs_url": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-v3.2-speciale"
   ],
   "intro_i18n": {
    "zh-CN": "在高度复杂任务中，Speciale模型显著优于标准版本，但消耗更多的tokens并产生更高的成本。目前，DeepSeek-V3.2-Speciale仅用于研究用途，不支持工具调用，也未针对日常对话或写作任务进行特别优化。",
    "zh-TW": "在高度複雜的任務中，Speciale 模型顯著優於標準版本，但會消耗更多的 tokens 並產生更高的成本。目前，DeepSeek-V3.2-Speciale 僅用於研究用途，不支持工具調用，且未針對日常對話或寫作任務進行特別優化。",
    "ja-JP": "高度に複雑なタスクにおいて、Specialeモデルは標準バージョンを大幅に上回る性能を発揮しますが、トークン消費が多く、コストが高くなります。現在、DeepSeek-V3.2-Specialeは研究用途のみに提供されており、ツール呼び出しをサポートせず、日常会話や執筆タスク向けに最適化されていません。",
    "ru-RU": "На высоко сложных задачах модель Speciale значительно превосходит стандартную версию, но потребляет значительно больше токенов и обходится дороже. В настоящее время DeepSeek-V3.2-Speciale предназначена только для исследовательского использования, не поддерживает вызов инструментов и не оптимизирована специально для повседневных разговоров или задач письма."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3.2-Speciale"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3.2-Speciale-TEE",
   "model_name": "DeepSeek-V3.2-Speciale-TEE",
   "display_name": "DeepSeek V3.2 Speciale TEE",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2-Speciale-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 163840,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "deepseek",
   "capabilities": {
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V3.2-Speciale-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.2 Speciale TEE"
    }
   ]
  },
  {
   "slug": "deepseek/DeepSeek-V3.2-TEE",
   "model_name": "DeepSeek-V3.2-TEE",
   "display_name": "DeepSeek V3.2 TEE",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V3.2-TEE"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/DeepSeek-V3.2-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.2 TEE"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.2-think",
   "model_name": "deepseek-v3.2-think",
   "display_name": "DeepSeek-V3.2-Think",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0302"
      }
     }
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     }
    }
   ],
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 131000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "structured_output": true,
    "open_weights": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "DeepSeek V3.2 Think 是一款完整的深度思考模型，具备更强的长链推理能力。",
    "zh-TW": "DeepSeek V3.2 Think 是完整的深度思考模型，具備更強的長鏈推理能力。",
    "ja-JP": "DeepSeek V3.2 Thinkは、長い思考の連鎖に対応した完全な深層思考モデルです。",
    "ru-RU": "DeepSeek V3.2 Think — полноценная модель глубокого мышления с усиленным длинноцепочечным рассуждением."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3.2-Think"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3.2-thinking",
   "model_name": "deepseek-v3.2-thinking",
   "display_name": "DeepSeek V3.2 Thinking",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "deepseek/deepseek-v3.2-thinking"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 128000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-v3.2-thinking"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek-V3.2 Thinking是DeepSeek-V3.2的思维模式变体，专注于推理任务。",
    "zh-TW": "DeepSeek-V3.2 Thinking是DeepSeek-V3.2的思考模式變體，專注於推理任務。",
    "ja-JP": "DeepSeek-V3.2 Thinkingは、推論タスクに焦点を当てたDeepSeek-V3.2の思考モードバリアントです。",
    "ru-RU": "DeepSeek-V3.2 Thinking — вариант режима мышления модели DeepSeek-V3.2, ориентированный на задачи рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.2 Thinking"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3/community",
   "model_name": "deepseek-v3/community",
   "display_name": "DeepSeek: DeepSeek R1 (Community)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1/community"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     },
     "provider_model_id": "deepseek/deepseek-r1/community"
    }
   ],
   "max_input_tokens": 64000,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "released_at": "2025-02-14",
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-r1/community",
    "deepseek/deepseek-v3/community"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek R1 是 DeepSeek 团队最新开源模型，在数学、编程和推理任务中表现出色，性能可与 OpenAI o1 相媲美。",
    "zh-TW": "DeepSeek R1 是 DeepSeek 團隊最新釋出的開源模型，在數學、程式設計與推理任務中展現強大推理能力，表現可媲美 OpenAI o1。",
    "ja-JP": "DeepSeek R1は、DeepSeekチームがリリースした最新のオープンソースモデルで、特に数学、コーディング、推論タスクにおいて非常に高い推論性能を発揮し、OpenAI o1に匹敵します。",
    "ru-RU": "DeepSeek R1 — последняя открытая модель от команды DeepSeek с очень высокой производительностью в логическом мышлении, особенно в математике, программировании и рассуждении, сопоставимая с OpenAI o1."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek: DeepSeek R1 (Community)"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3p1",
   "model_name": "deepseek-v3p1",
   "display_name": "DeepSeek V3.1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-v3p1"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true
   },
   "released_at": "2025-08-21",
   "knowledge_cutoff": "2025-07",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-v3p1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.1"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3p1-terminus",
   "model_name": "deepseek-v3p1-terminus",
   "display_name": "DeepSeek V3.1 Terminus",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-v3p1-terminus"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-v3p1-terminus"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.1 Terminus"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v3p2",
   "model_name": "deepseek-v3p2",
   "display_name": "DeepSeek V3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-v3p2"
    }
   ],
   "docs_url": "https://fireworks.ai/models/fireworks/deepseek-v3p2",
   "max_input_tokens": 163840,
   "max_output_tokens": 163840,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true
   },
   "intro": "Model from Deepseek that harmonizes high computational efficiency with superior reasoning and agent performance. 675B parameter MoE model.",
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2025-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/deepseek-v3p2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.2"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-flash",
   "model_name": "deepseek-v4-flash",
   "display_name": "DeepSeek V4 Flash",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepseek",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "avian",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.105"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.021"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.51"
      }
     }
    },
    {
     "provider": "bytedance",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.133"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.266"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-v4-flash"
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.112"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.224"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12846"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26092"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06423"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1285"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2609"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0642"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek-v4-flash:free"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14713132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29426264"
      }
     },
     "provider_model_id": "DeepSeek-V4-Flash"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-v4-flash"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek-v4-flash-free"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     }
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.37"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14493"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4928"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7392"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "route/deepseek-v4-flash"
    },
    {
     "provider": "sensenova",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.002941"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0027999999999999995"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.138"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    },
    {
     "provider": "wafer-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "wafer.ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Flash"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash"
    }
   ],
   "intro": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
   "released_at": "2026-04-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-flash",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true,
    "web_search": true
   },
   "docs_url": "https://api-docs.deepseek.com/quick_start/pricing",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "benchmarks": {
    "intelligence_index": 40.3,
    "coding_index": 56.2,
    "agentic_index": 31.1
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "aliases": [
    "DeepSeek-V4-Flash",
    "TEE/deepseek-v4-flash",
    "accounts/fireworks/models/deepseek-v4-flash",
    "deepinfra/deepseek-ai/DeepSeek-V4-Flash",
    "deepseek-ai/DeepSeek-V4-Flash",
    "deepseek-ai/deepseek-v4-flash",
    "deepseek-v4-flash-free",
    "deepseek-v4-flash:free",
    "deepseek/deepseek-v4-flash",
    "deepseek/deepseek-v4-flash:free",
    "deepseek/deepseek-v4-flash:thinking",
    "doubleword/deepseek-v4-flash",
    "fireworks/deepseek-v4-flash",
    "novita/deepseek/deepseek-v4-flash",
    "route/deepseek-v4-flash",
    "tensorx/deepseek-v4-flash"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek-V4-Flash 是 DeepSeek-V4 系列中 MoE 语言模型的预览版本。总参数规模为 2840 亿，激活参数规模为 130 亿，支持 1M 令牌超长上下文。该模型采用结合 CSA 和 HCA 的混合注意力架构，并引入 mHC 和 Muon 优化器，以提高长上下文推理效率、训练稳定性和整体性能。",
    "zh-TW": "DeepSeek-V4-Flash 是 DeepSeek-V4 系列中的 MoE 語言模型預覽版。總參數大小為 2840 億，激活參數大小為 130 億，支持 1M 令牌超長上下文。該模型採用結合 CSA 和 HCA 的混合注意力架構，並引入 mHC 和 Muon 優化器以提高長上下文推理效率、訓練穩定性和整體性能。",
    "ja-JP": "DeepSeek-V4-FlashはDeepSeek-V4シリーズのMoE言語モデルのプレビュー版です。総パラメータサイズは2840億、アクティブパラメータサイズは130億で、1Mトークンの超長コンテキストをサポートします。このモデルはCSAとHCAを組み合わせたハイブリッドアテンションアーキテクチャを使用し、mHCとMuon Optimizerを導入して長コンテキスト推論効率、トレーニングの安定性、全体的な性能を向上させています。",
    "ru-RU": "DeepSeek-V4-Flash — это предварительная версия языковой модели MoE из серии DeepSeek-V4. Общий размер параметров составляет 284 миллиарда, размер активных параметров — 13 миллиардов, и она поддерживает ультрадлинный контекст на 1 миллион токенов. Модель использует гибридную архитектуру внимания, объединяющую CSA и HCA, и вводит mHC и Muon Optimizer для повышения эффективности рассуждений на длинных контекстах, стабильности обучения и общей производительности."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.06573",
     "new": "0.06423"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "0.26292",
     "new": "0.26092"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.13146",
     "new": "0.12846"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.0657",
     "new": "0.0642"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.2629",
     "new": "0.2609"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.1315",
     "new": "0.1285"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.29440336",
     "new": "0.29426264"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14720168",
     "new": "0.14713132"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.29460788",
     "new": "0.29440336"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14730394",
     "new": "0.14720168"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.06583",
     "new": "0.06573"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "0.26332",
     "new": "0.26292"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.13166",
     "new": "0.13146"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.0658",
     "new": "0.0657"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.2633",
     "new": "0.2629"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.1317",
     "new": "0.1315"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.29491844",
     "new": "0.29460788"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14745922",
     "new": "0.14730394"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.29497866",
     "new": "0.29491844"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14748933",
     "new": "0.14745922"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-flash-6bit",
   "model_name": "deepseek-v4-flash-6bit",
   "display_name": "DeepSeek V4 Flash 6bit",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4928"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7392"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "route/deepseek-v4-flash-6bit"
    }
   ],
   "intro": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
   "released_at": "2026-04-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-flash",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "route/deepseek-v4-flash-6bit"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V4 Flash 6bit"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-flash-e",
   "model_name": "deepseek-v4-flash-e",
   "display_name": "DeepSeek-V4-Flash-E",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.202"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.404"
      }
     }
    }
   ],
   "released_at": "2026-05-13",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V4-Flash-E"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-flash-el",
   "model_name": "deepseek-v4-flash-el",
   "display_name": "DeepSeek-V4-Flash-EL",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "empiriolabs/deepseek-v4-flash-el"
    }
   ],
   "intro": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
   "released_at": "2026-04-24",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "empiriolabs/deepseek-v4-flash-el"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V4-Flash-EL"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-flash-us",
   "model_name": "deepseek-v4-flash-us",
   "display_name": "DeepSeek-V4-Flash-US",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    }
   ],
   "released_at": "2026-05-11",
   "max_input_tokens": 1000000,
   "max_output_tokens": 393216,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V4-Flash-US"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-flash:discounted",
   "model_name": "deepseek-v4-flash:discounted",
   "display_name": "DeepSeek: DeepSeek V4 Flash (>40% off)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-flash:discounted"
    }
   ],
   "released_at": "2025-08-26",
   "max_input_tokens": 1048576,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-v4-flash:discounted"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek: DeepSeek V4 Flash (>40% off)"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-flash:flex",
   "model_name": "deepseek-v4-flash:flex",
   "display_name": "doubleword/deepseek-v4-flash:flex",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "doubleword/deepseek-v4-flash:flex"
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubleword/deepseek-v4-flash:flex"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubleword/deepseek-v4-flash:flex"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-pro",
   "model_name": "deepseek-v4-pro",
   "display_name": "DeepSeek V4 Pro",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepseek",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.464"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.928"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0038512"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     }
    },
    {
     "provider": "avian",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.305"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.61"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.10875"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      }
     }
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.145"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "bytedance",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.553"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.106"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.145"
      }
     },
     "provider_model_id": "accounts/fireworks/models/deepseek-v4-pro"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     }
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.392"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.784"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.116"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6704"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3408"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.8352"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6704"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3408"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.8352"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "deepseek-v4-pro:free"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.145"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.76557584"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.53115168"
      }
     },
     "provider_model_id": "DeepSeek-V4-Pro"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-v4-pro"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.145"
      }
     }
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0145"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.84"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.145"
      }
     }
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0145"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.73913"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.47826"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "deepinfra/deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4928"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7392"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "route/deepseek-v4-pro"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003676"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.145"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.145"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0036249999999999998"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.435"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.301"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0036"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     }
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "wafer-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "wafer.ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "deepseek-ai/DeepSeek-V4-Pro"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro"
    }
   ],
   "intro": "Open MoE flagship with million-token context for coding and long agent runs",
   "released_at": "2026-04-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true,
    "web_search": true
   },
   "docs_url": "https://api-docs.deepseek.com/quick_start/pricing",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "benchmarks": {
    "intelligence_index": 44.3,
    "coding_index": 59.4,
    "agentic_index": 36.4
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 1
    }
   },
   "aliases": [
    "DeepSeek-V4-Pro",
    "TEE/deepseek-v4-pro",
    "TEE/deepseek-v4-pro:thinking",
    "accounts/fireworks/models/deepseek-v4-pro",
    "deepinfra/deepseek-ai/DeepSeek-V4-Pro",
    "deepseek-ai/DeepSeek-V4-Pro",
    "deepseek-ai/deepseek-v4-pro",
    "deepseek-v4-pro:free",
    "deepseek/deepseek-v4-pro",
    "deepseek/deepseek-v4-pro:thinking",
    "doubleword/deepseek-v4-pro",
    "fireworks/deepseek-v4-pro",
    "nebius/deepseek-ai/deepseek-v4-pro",
    "route/deepseek-v4-pro",
    "tensorx/deepseek-v4-pro"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek-V4-Pro 是 DeepSeek-V4 系列中的旗舰 MoE 语言模型，拥有 1.6T 总参数、49B 激活参数，原生支持 100 万 tokens 的超长上下文。该模型采用创新的混合注意力架构，结合压缩稀疏注意力（CSA）与高度压缩注意力（HCA），在 1M 上下文下仅需 DeepSeek-V3.2 的 27% 单 token 推理 FLOPs 和 10% KV 缓存。模型还引入流形约束超连接（mHC）增强层间信号传播稳定性，并采用 Muon 优化器加速收敛。DeepSeek-V4-Pro 在超过 32T 高质量多样化 tokens 上预训练，后训练采用「领域专家独立培养 + 在线策略蒸馏统一整合」的两阶段范式。其最大推理强度模式 DeepSeek-V4-Pro-Max 在编程基准上取得顶尖表现，并在推理与 Agentic 任务上大幅缩小与领先闭源模型的差距，是目前最强的开源模型之一，支持 Non-think、Think High、Think Max 三种推理强度模式",
    "zh-TW": "DeepSeek-V4-Pro 是 DeepSeek-V4 系列中的旗艦 MoE 語言模型，擁有 1.6T 總參數和 49B 活躍參數，原生支持超長上下文達 100 萬個 token。該模型採用創新的混合注意力架構，結合壓縮稀疏注意力（CSA）和高度壓縮注意力（HCA），僅需 DeepSeek-V3.2 每 token 推理 FLOPs 的 27% 和 1M 上下文 KV 緩存的 10%。此外，它引入了流形約束超連接（mHC）以增強層間信號傳播穩定性，並使用 Muon 優化器加速收斂。DeepSeek-V4-Pro 在超過 32T 高質量多樣化 token 上進行預訓練，並通過獨立領域專家培養和在線策略蒸餾的兩階段範式進行後訓練以實現統一整合。其最大推理強度模式 DeepSeek-V4-Pro-Max 在編碼基準測試中表現卓越，並顯著縮小了與領先的閉源模型在推理和代理任務上的差距，使其成為當今最強大的開源模型之一，支持 Non-think、Think High 和 Think Max 推理強度模式。",
    "ja-JP": "DeepSeek-V4-ProはDeepSeek-V4シリーズのフラッグシップMoE言語モデルで、総パラメータ数1.6T、アクティブパラメータ数49Bを持ち、1百万トークンの超長文コンテキストをネイティブにサポートします。このモデルは、Compressed Sparse Attention (CSA)とHighly Compressed Attention (HCA)を組み合わせた革新的なハイブリッドアテンションアーキテクチャを採用し、DeepSeek-V3.2のトークンごとの推論FLOPsの27%と1MコンテキストでのKVキャッシュの10%のみを必要とします。また、Manifold-Constrained Hyper Connections (mHC)を導入して層間信号伝播の安定性を向上させ、Muonオプティマイザを使用して収束を加速します。DeepSeek-V4-Proは32T以上の高品質で多様なトークンで事前学習され、独立したドメインエキスパートの育成とオンラインポリシー蒸留による統合の2段階パラダイムでポストトレーニングが行われています。最大推論強度モードのDeepSeek-V4-Pro-Maxは、コーディングベンチマークで最高のパフォーマンスを達成し、推論およびエージェント的タスクにおいて主要なクローズドソースモデルとのギャップを大幅に縮小し、現在最も強力なオープンソースモデルの1つとなっています。Non-think、Think High、Think Maxの推論強度モードをサポートします。",
    "ru-RU": "DeepSeek-V4-Pro — флагманская модель MoE в серии DeepSeek-V4 с общим количеством параметров 1,6 трлн и 49 млрд активных параметров, которая нативно поддерживает ультрадлинный контекст в 1 миллион токенов. Модель использует инновационную гибридную архитектуру внимания, объединяющую Compressed Sparse Attention (CSA) и Highly Compressed Attention (HCA), требующую всего 27% FLOPs на токен по сравнению с DeepSeek-V3.2 и 10% KV-кэша при контексте 1 млн. Также она вводит Манипулируемые Гиперсвязи (mHC) для повышения стабильности передачи сигналов между слоями и использует оптимизатор Muon для ускорения сходимости. DeepSeek-V4-Pro предварительно обучена на более чем 32 трлн высококачественных разнообразных токенов с последующим обучением по двухэтапной парадигме: культивация независимых доменных экспертов и онлайн-дистилляция политики для унифицированной интеграции. Режим максимальной интенсивности рассуждений DeepSeek-V4-Pro-Max достигает лучших результатов в кодировочных тестах и значительно сокращает разрыв с ведущими закрытыми моделями в задачах рассуждений и агентности, делая её одной из самых мощных моделей с открытым исходным кодом на сегодняшний день, поддерживающей режимы рассуждений Non-think, Think High и Think Max."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.7912",
     "new": "0.8352"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "3.1648",
     "new": "3.3408"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "1.5824",
     "new": "1.6704"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.7912",
     "new": "0.8352"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "3.1648",
     "new": "3.3408"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "1.5824",
     "new": "1.6704"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.53284032",
     "new": "3.53115168"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.76642016",
     "new": "1.76557584"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.77205",
     "new": "0.7912"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "3.0882",
     "new": "3.1648"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "1.5441",
     "new": "1.5824"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.7721",
     "new": "0.7912"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "3.0882",
     "new": "3.1648"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "1.5441",
     "new": "1.5824"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.53529456",
     "new": "3.53284032"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.76764728",
     "new": "1.76642016"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.73725",
     "new": "0.77205"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.949",
     "new": "3.0882"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "1.4745",
     "new": "1.5441"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.7373",
     "new": "0.7721"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-pro-202606",
   "model_name": "deepseek-v4-pro-202606",
   "display_name": "Deepseek-v4-Pro-202606",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43478"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86957"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.00362"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro-202606"
    }
   ],
   "released_at": "2026-04-24",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-v4-pro-202606"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "Deepseek-v4-Pro-202606"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-pro-6bit",
   "model_name": "deepseek-v4-pro-6bit",
   "display_name": "DeepSeek V4 Pro 6bit",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4928"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7392"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "route/deepseek-v4-pro-6bit"
    }
   ],
   "intro": "Open MoE flagship with million-token context for coding and long agent runs",
   "released_at": "2026-04-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "route/deepseek-v4-pro-6bit"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V4 Pro 6bit"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-pro-cheaper",
   "model_name": "deepseek-v4-pro-cheaper",
   "display_name": "DeepSeek V4 Pro Cheaper",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro-cheaper"
    }
   ],
   "intro": "Flagship DeepSeek model for coding, reasoning, and agentic work",
   "released_at": "2026-04-25",
   "max_input_tokens": 1048576,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-v4-pro-cheaper",
    "deepseek/deepseek-v4-pro-cheaper:thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V4 Pro Cheaper"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-pro-e",
   "model_name": "deepseek-v4-pro-e",
   "display_name": "DeepSeek-V4-Pro-E",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.4242"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.8485"
      }
     }
    }
   ],
   "released_at": "2026-05-13",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V4-Pro-E"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-pro-el",
   "model_name": "deepseek-v4-pro-el",
   "display_name": "DeepSeek-V4-Pro-EL",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.67"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.33"
      }
     },
     "provider_model_id": "empiriolabs/deepseek-v4-pro-el"
    }
   ],
   "intro": "Flagship DeepSeek model for coding, reasoning, and agentic work",
   "released_at": "2026-04-24",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "empiriolabs/deepseek-v4-pro-el"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V4-Pro-EL"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-pro-lightning",
   "model_name": "deepseek-v4-pro-lightning",
   "display_name": "DeepSeek V4 Pro Lightning",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    }
   ],
   "intro": "Open MoE flagship with million-token context for coding and long agent runs",
   "released_at": "2026-04-24",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V4 Pro Lightning"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-pro-us",
   "model_name": "deepseek-v4-pro-us",
   "display_name": "DeepSeek-V4-Pro-US",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "released_at": "2026-05-11",
   "max_input_tokens": 1000000,
   "max_output_tokens": 393216,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V4-Pro-US"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-pro:discounted",
   "model_name": "deepseek-v4-pro:discounted",
   "display_name": "DeepSeek: DeepSeek V4 Pro (>80% off)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003625"
      }
     },
     "provider_model_id": "deepseek/deepseek-v4-pro:discounted"
    }
   ],
   "released_at": "2025-08-26",
   "max_input_tokens": 1048576,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek/deepseek-v4-pro:discounted"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek: DeepSeek V4 Pro (>80% off)"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-v4-pro:flex",
   "model_name": "deepseek-v4-pro:flex",
   "display_name": "doubleword/deepseek-v4-pro:flex",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.31"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     },
     "provider_model_id": "doubleword/deepseek-v4-pro:flex"
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubleword/deepseek-v4-pro:flex"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubleword/deepseek-v4-pro:flex"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-vl2",
   "model_name": "deepseek-vl2",
   "display_name": "deepseek-ai/deepseek-vl2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-vl2"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "deepseek-ai/deepseek-vl2"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.145588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.145588"
      }
     }
    }
   ],
   "released_at": "2024-12-13",
   "max_input_tokens": 4000,
   "max_output_tokens": 4000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "family": "deepseek",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "stream": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/deepseek-vl2"
   ],
   "intro_i18n": {
    "zh-CN": "DeepSeek VL2 是一款多模态模型，专注于图文理解和细粒度视觉问答。",
    "zh-TW": "DeepSeek VL2 是一款多模態模型，支援圖文理解與細緻的視覺問答任務。",
    "ja-JP": "DeepSeek VL2は、画像と言語の理解および精緻な視覚的質問応答に対応するマルチモーダルモデルです。",
    "ru-RU": "DeepSeek VL2 — мультимодальная модель для понимания изображений и текста и точного визуального вопросо-ответа."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/deepseek-vl2"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek-vl2-small",
   "model_name": "deepseek-vl2-small",
   "display_name": "DeepSeek VL2 Small",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 2048,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "DeepSeek VL2 Small 是一款轻量级多模态模型，适用于资源受限和高并发场景。",
    "zh-TW": "DeepSeek VL2 Small 是輕量級多模態模型，適用於資源受限與高併發場景。",
    "ja-JP": "DeepSeek VL2 Smallは、リソース制約や高同時接続環境向けの軽量マルチモーダルモデルです。",
    "ru-RU": "DeepSeek VL2 Small — лёгкая мультимодальная модель для сред с ограниченными ресурсами и высокой нагрузкой."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek VL2 Small"
    }
   ]
  },
  {
   "slug": "deepseek/deepseek.v3.1",
   "model_name": "deepseek.v3.1",
   "display_name": "deepseek.v3.1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5974"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7304"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek.v3.1"
    }
   ]
  },
  {
   "slug": "deepseek/e2ee-deepseek-v4-flash",
   "model_name": "e2ee-deepseek-v4-flash",
   "display_name": "DeepSeek V4 Flash",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.182"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.373"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.038"
      }
     }
    }
   ],
   "released_at": "2026-07-07",
   "max_input_tokens": 1000000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "DeepSeek V4 Flash"
    }
   ]
  },
  {
   "slug": "deepseek/hunyuan-image/v3",
   "model_name": "hunyuan-image/v3",
   "display_name": "DeepSeek-V3.1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "deepseek.v3-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7017"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.0324"
      }
     },
     "provider_model_id": "deepseek.v3-v1:0",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9767"
      }
     },
     "provider_model_id": "deepseek.v3-v1:0",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5974"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7304"
      }
     },
     "provider_model_id": "deepseek.v3-v1:0",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.74"
      }
     },
     "provider_model_id": "deepseek.v3-v1:0",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "deepseek.v3-v1:0",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6069"
      }
     },
     "provider_model_id": "deepseek.v3-v1:0",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "deepseek.v3-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.68"
      }
     },
     "provider_model_id": "deepseek.v3-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "fal",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output_per_megapixel": {
       "unit": "per_image",
       "price": "0.1"
      }
     },
     "provider_model_id": "fal-ai/hunyuan-image/v3"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-09-18",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 163840,
   "max_output_tokens": 81920,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek.v3-v1:0",
    "fal-ai/hunyuan-image/v3"
   ],
   "intro_i18n": {
    "zh-CN": "一款强大的原生多模态图像生成模型。",
    "zh-TW": "一款強大的原生多模態圖像生成模型。",
    "ja-JP": "強力なネイティブマルチモーダル画像生成モデルです。",
    "ru-RU": "Мощная нативная мультимодальная модель генерации изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3.1"
    }
   ]
  },
  {
   "slug": "deepseek/Janus-Pro-1B",
   "model_name": "Janus-Pro-1B",
   "display_name": "Janus-Pro-1B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0005"
      }
     },
     "provider_model_id": "deepseek-ai/Janus-Pro-1B"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/Janus-Pro-1B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Janus-Pro-1B"
    }
   ]
  },
  {
   "slug": "deepseek/Janus-Pro-7B",
   "model_name": "Janus-Pro-7B",
   "display_name": "deepseek-ai/Janus-Pro-7B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "deepseek-ai/Janus-Pro-7B"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.002"
      }
     },
     "provider_model_id": "deepseek-ai/Janus-Pro-7B"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek-ai/Janus-Pro-7B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/Janus-Pro-7B"
    }
   ]
  },
  {
   "slug": "deepseek/parasail-deepseek-v4-flash",
   "model_name": "parasail-deepseek-v4-flash",
   "display_name": "parasail/parasail-deepseek-v4-flash",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "parasail/parasail-deepseek-v4-flash"
    }
   ],
   "released_at": "2026-06-13",
   "max_input_tokens": 1048576,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "parasail/parasail-deepseek-v4-flash"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "parasail/parasail-deepseek-v4-flash"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-deepseek-ocr-2",
   "model_name": "ppio-deepseek-deepseek-ocr-2",
   "display_name": "deepseek/deepseek-ocr-2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.031"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.031"
      }
     }
    }
   ],
   "released_at": "2026-02-04",
   "max_input_tokens": 8192,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-ocr-2"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-deepseek-prover-v2-671b",
   "model_name": "ppio-deepseek-deepseek-prover-v2-671b",
   "display_name": "deepseek/deepseek-prover-v2-671b",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-06-10",
   "max_input_tokens": 160000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-prover-v2-671b"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-deepseek-r1-0528",
   "model_name": "ppio-deepseek-deepseek-r1-0528",
   "display_name": "deepseek/deepseek-r1-0528",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-06-04",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-r1-0528"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-deepseek-r1-community",
   "model_name": "ppio-deepseek-deepseek-r1-community",
   "display_name": "deepseek/deepseek-r1/community",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "released_at": "2025-06-10",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-r1/community"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-deepseek-r1-turbo",
   "model_name": "ppio-deepseek-deepseek-r1-turbo",
   "display_name": "deepseek/deepseek-r1-turbo",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-06-10",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-r1-turbo"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-deepseek-v3-0324",
   "model_name": "ppio-deepseek-deepseek-v3-0324",
   "display_name": "deepseek/deepseek-v3-0324",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2025-06-10",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-v3-0324"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-deepseek-v3-1",
   "model_name": "ppio-deepseek-deepseek-v3-1",
   "display_name": "deepseek/deepseek-v3.1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.72"
      }
     }
    }
   ],
   "released_at": "2025-08-25",
   "max_input_tokens": 163840,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-v3.1"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-deepseek-v3-2",
   "model_name": "ppio-deepseek-deepseek-v3-2",
   "display_name": "deepseek/deepseek-v3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.429"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 163840,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-v3.2"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-deepseek-v3-community",
   "model_name": "ppio-deepseek-deepseek-v3-community",
   "display_name": "deepseek/deepseek-v3/community",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "released_at": "2025-06-10",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-v3/community"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-deepseek-v3-turbo",
   "model_name": "ppio-deepseek-deepseek-v3-turbo",
   "display_name": "deepseek/deepseek-v3-turbo",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     }
    }
   ],
   "released_at": "2025-06-10",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-v3-turbo"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-v3-1-terminus",
   "model_name": "ppio-deepseek-v3-1-terminus",
   "display_name": "deepseek/deepseek-v3.1-terminus",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.715"
      }
     }
    }
   ],
   "released_at": "2025-09-30",
   "max_input_tokens": 98304,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-v3.1-terminus"
    }
   ]
  },
  {
   "slug": "deepseek/ppio-deepseek-v3-2-exp",
   "model_name": "ppio-deepseek-v3-2-exp",
   "display_name": "deepseek/deepseek-v3.2-exp",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4286"
      }
     }
    }
   ],
   "released_at": "2025-09-30",
   "max_input_tokens": 163840,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek/deepseek-v3.2-exp"
    }
   ]
  },
  {
   "slug": "deepseek/pro-deepseek-r1",
   "model_name": "pro-deepseek-r1",
   "display_name": "DeepSeek R1 (Pro)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "企业专用服务模型，支持并发打包使用。",
    "zh-TW": "企業專用服務模型，內含綁定併發能力。",
    "ja-JP": "同時実行性をバンドルしたエンタープライズ向け専用サービスモデルです。",
    "ru-RU": "Выделенная корпоративная модель обслуживания с включенной параллельной обработкой."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek R1 (Pro)"
    }
   ]
  },
  {
   "slug": "deepseek/pro-deepseek-v3",
   "model_name": "pro-deepseek-v3",
   "display_name": "DeepSeek V3 (Pro)",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "企业专用服务模型，支持并发打包使用。",
    "zh-TW": "企業專用服務模型，內含綁定併發能力。",
    "ja-JP": "同時実行性をバンドルしたエンタープライズ向け専用サービスモデルです。",
    "ru-RU": "Выделенная корпоративная модель обслуживания с включенной параллельной обработкой."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3 (Pro)"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-deepseek-ai-deepseek-r1",
   "model_name": "siliconflow-deepseek-ai-deepseek-r1",
   "display_name": "deepseek-ai/DeepSeek-R1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-01-20",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/DeepSeek-R1"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-deepseek-ai-deepseek-r1-distill-qwen-14b",
   "model_name": "siliconflow-deepseek-ai-deepseek-r1-distill-qwen-14b",
   "display_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "released_at": "2025-02-04",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-deepseek-ai-deepseek-r1-distill-qwen-32b",
   "model_name": "siliconflow-deepseek-ai-deepseek-r1-distill-qwen-32b",
   "display_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    }
   ],
   "released_at": "2025-02-04",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-deepseek-ai-deepseek-v2-5",
   "model_name": "siliconflow-deepseek-ai-deepseek-v2-5",
   "display_name": "deepseek-ai/DeepSeek-V2.5",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2024-09-05",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/DeepSeek-V2.5"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-deepseek-ai-deepseek-v3",
   "model_name": "siliconflow-deepseek-ai-deepseek-v3",
   "display_name": "deepseek-ai/DeepSeek-V3",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2024-12-26",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/DeepSeek-V3"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-deepseek-ai-DeepSeek-V3-2",
   "model_name": "siliconflow-deepseek-ai-DeepSeek-V3-2",
   "display_name": "deepseek-ai/DeepSeek-V3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.429"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 160000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/DeepSeek-V3.2"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-deepseek-ai-deepseek-vl2",
   "model_name": "siliconflow-deepseek-ai-deepseek-vl2",
   "display_name": "deepseek-ai/deepseek-vl2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.142"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.142"
      }
     }
    }
   ],
   "released_at": "2025-02-09",
   "max_input_tokens": 4000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepseek-ai/deepseek-vl2"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-deepseek-v-3-1-terminus",
   "model_name": "siliconflow-deepseek-v-3-1-terminus",
   "display_name": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.715"
      }
     }
    }
   ],
   "released_at": "2025-09-30",
   "max_input_tokens": 160000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/deepseek-ai/DeepSeek-V3.1-Terminus"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-pro-deepseek-ai-deepseek-r1",
   "model_name": "siliconflow-pro-deepseek-ai-deepseek-r1",
   "display_name": "Pro/deepseek-ai/DeepSeek-R1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-02-07",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/deepseek-ai/DeepSeek-R1"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-pro-deepseek-ai-deepseek-v3",
   "model_name": "siliconflow-pro-deepseek-ai-deepseek-v3",
   "display_name": "Pro/deepseek-ai/DeepSeek-V3",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2025-02-07",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/deepseek-ai/DeepSeek-V3"
    }
   ]
  },
  {
   "slug": "deepseek/siliconflow-Pro-deepseek-ai-DeepSeek-V3-2",
   "model_name": "siliconflow-Pro-deepseek-ai-DeepSeek-V3-2",
   "display_name": "Pro/deepseek-ai/DeepSeek-V3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.429"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 160000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/deepseek-ai/DeepSeek-V3.2"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-r1",
   "model_name": "sophnet-deepseek-r1",
   "display_name": "sophnet/DeepSeek-R1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     }
    }
   ],
   "released_at": "2025-07-08",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-R1"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-r1-0528",
   "model_name": "sophnet-deepseek-r1-0528",
   "display_name": "sophnet/DeepSeek-R1-0528",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     }
    }
   ],
   "released_at": "2025-07-08",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-R1-0528"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-r1-distill-qwen-32b",
   "model_name": "sophnet-deepseek-r1-distill-qwen-32b",
   "display_name": "sophnet/DeepSeek-R1-Distill-Qwen-32B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-R1-Distill-Qwen-32B"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-r1-distill-qwen-7b",
   "model_name": "sophnet-deepseek-r1-distill-qwen-7b",
   "display_name": "sophnet/DeepSeek-R1-Distill-Qwen-7B",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-R1-Distill-Qwen-7B"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-v3",
   "model_name": "sophnet-deepseek-v3",
   "display_name": "sophnet/DeepSeek-v3",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-v3"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-v3-1",
   "model_name": "sophnet-deepseek-v3-1",
   "display_name": "sophnet/DeepSeek-V3.1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7143"
      }
     }
    }
   ],
   "released_at": "2025-09-09",
   "max_input_tokens": 163000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-V3.1"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-v3-1-fast",
   "model_name": "sophnet-deepseek-v3-1-fast",
   "display_name": "sophnet/DeepSeek-V3.1-Fast",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.4286"
      }
     }
    }
   ],
   "released_at": "2025-09-09",
   "max_input_tokens": 163000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-V3.1-Fast"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-v3-2",
   "model_name": "sophnet-deepseek-v3-2",
   "display_name": "sophnet/DeepSeek-V3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.429"
      }
     }
    }
   ],
   "released_at": "2026-01-06",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-V3.2"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-v3-2-exp",
   "model_name": "sophnet-deepseek-v3-2-exp",
   "display_name": "sophnet/DeepSeek-V3.2-Exp",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    }
   ],
   "released_at": "2025-10-13",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-V3.2-Exp"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-DeepSeek-V3-2-Fast",
   "model_name": "sophnet-DeepSeek-V3-2-Fast",
   "display_name": "sophnet/DeepSeek-V3.2-Fast",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.429"
      }
     }
    }
   ],
   "released_at": "2026-01-06",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-V3.2-Fast"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-v3-30b-a3b-instruct-2507",
   "model_name": "sophnet-deepseek-v3-30b-a3b-instruct-2507",
   "display_name": "sophnet/Qwen3-30B-A3B-Instruct-2507",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-09-09",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Qwen3-30B-A3B-Instruct-2507"
    }
   ]
  },
  {
   "slug": "deepseek/sophnet-deepseek-v3-fast",
   "model_name": "sophnet-deepseek-v3-fast",
   "display_name": "sophnet/DeepSeek-V3-Fast",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.571"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.28"
      }
     }
    }
   ],
   "released_at": "2025-07-09",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/DeepSeek-V3-Fast"
    }
   ]
  },
  {
   "slug": "deepseek/us.deepseek.r1-v1:0",
   "model_name": "us.deepseek.r1-v1:0",
   "display_name": "DeepSeek-R1",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "deepseek.r1-v1:0"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
   "released_at": "2025-01-20",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek.r1-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-R1"
    }
   ]
  },
  {
   "slug": "deepseek/us.deepseek.v3.2",
   "model_name": "us.deepseek.v3.2",
   "display_name": "DeepSeek-V3.2",
   "vendor": "deepseek",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      }
     },
     "provider_model_id": "deepseek.v3.2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.22"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.22"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6386"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9055"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.22"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.22"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.22"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.22"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.22"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6386"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9055"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.22"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.22"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.22"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      }
     },
     "provider_model_id": "deepseek.v3.2",
     "region": "us-west-2"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2026-02-06",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 163840,
   "max_output_tokens": 81920,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepseek.v3.2",
    "deepseek.v3.2-v1:0",
    "eu.deepseek.v3.2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek-V3.2"
    }
   ]
  },
  {
   "slug": "elevenlabs/elevenlabs-music",
   "model_name": "elevenlabs-music",
   "display_name": "ElevenLabs-Music",
   "vendor": "elevenlabs",
   "pricing": [],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-08-29",
   "max_input_tokens": 2000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "elevenlabs",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "audio_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "elevenlabs/elevenlabs-music"
   ],
   "model_type": "music_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ElevenLabs-Music"
    }
   ]
  },
  {
   "slug": "elevenlabs/elevenlabs-v2.5-turbo",
   "model_name": "elevenlabs-v2.5-turbo",
   "display_name": "ElevenLabs-v2.5-Turbo",
   "vendor": "elevenlabs",
   "pricing": [],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2024-10-28",
   "max_input_tokens": 128000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "elevenlabs",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "audio_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "elevenlabs/elevenlabs-v2.5-turbo"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ElevenLabs-v2.5-Turbo"
    }
   ]
  },
  {
   "slug": "elevenlabs/elevenlabs-v3",
   "model_name": "elevenlabs-v3",
   "display_name": "ElevenLabs-v3",
   "vendor": "elevenlabs",
   "pricing": [],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-06-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "elevenlabs",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "audio_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "elevenlabs/elevenlabs-v3"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ElevenLabs-v3"
    }
   ]
  },
  {
   "slug": "elevenlabs/elevenlabs/tts/multilingual-v2",
   "model_name": "elevenlabs/tts/multilingual-v2",
   "display_name": "ElevenLabs Multilingual TTS v2",
   "vendor": "elevenlabs",
   "pricing": [],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2023-08-22",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "elevenlabs",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fal-ai/elevenlabs/tts/multilingual-v2"
   ],
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ElevenLabs Multilingual TTS v2"
    }
   ]
  },
  {
   "slug": "essentialai/EssentialAI-RNJ-1-Instruct",
   "model_name": "EssentialAI-RNJ-1-Instruct",
   "display_name": "EssentialAI-RNJ-1-Instruct",
   "vendor": "essentialai",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "togethercomputer/EssentialAI-RNJ-1-Instruct"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/EssentialAI-RNJ-1-Instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "EssentialAI-RNJ-1-Instruct"
    }
   ]
  },
  {
   "slug": "essentialai/Rnj-1-Instruct",
   "model_name": "Rnj-1-Instruct",
   "display_name": "EssentialAI: Rnj 1 Instruct",
   "vendor": "essentialai",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "essentialai/rnj-1-instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "essentialai/rnj-1-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "essentialai/rnj-1-instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "essentialai/Rnj-1-Instruct"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-12-05",
   "max_input_tokens": 32768,
   "max_output_tokens": 6554,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-10",
   "family": "rnj",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "essentialai/Rnj-1-Instruct",
    "essentialai/rnj-1-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "EssentialAI: Rnj 1 Instruct"
    }
   ]
  },
  {
   "slug": "google/amoral-gemma3-27B-v2",
   "model_name": "amoral-gemma3-27B-v2",
   "display_name": "Amoral Gemma3 27B v2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "soob3123/amoral-gemma3-27B-v2"
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-05-23",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "soob3123/amoral-gemma3-27B-v2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Amoral Gemma3 27B v2"
    }
   ]
  },
  {
   "slug": "google/antigravity-preview-05-2026",
   "model_name": "antigravity-preview-05-2026",
   "display_name": "antigravity-preview-05-2026",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "prompt_caching": true,
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "antigravity-preview-05-2026"
    }
   ]
  },
  {
   "slug": "google/aqa",
   "model_name": "aqa",
   "display_name": "Model that performs Attributed Question Answering.",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "llmdb",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    }
   ],
   "max_input_tokens": 7168,
   "max_output_tokens": 1024,
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Model that performs Attributed Question Answering."
    }
   ]
  },
  {
   "slug": "google/automl-vision-image-object-detection",
   "model_name": "automl-vision-image-object-detection",
   "display_name": "automl-vision-image-object-detection",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.000556111"
      }
     },
     "provider_model_id": "google/automl-vision-image-object-detection"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/automl-vision-image-object-detection"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "automl-vision-image-object-detection"
    }
   ]
  },
  {
   "slug": "google/chat-bison",
   "model_name": "chat-bison",
   "display_name": "chat-bison",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chat-bison"
    }
   ]
  },
  {
   "slug": "google/chat-bison-32k",
   "model_name": "chat-bison-32k",
   "display_name": "chat-bison-32k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chat-bison-32k"
    }
   ]
  },
  {
   "slug": "google/chat-bison-32k@002",
   "model_name": "chat-bison-32k@002",
   "display_name": "chat-bison-32k@002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chat-bison-32k@002"
    }
   ]
  },
  {
   "slug": "google/chat-bison@001",
   "model_name": "chat-bison@001",
   "display_name": "chat-bison@001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chat-bison@001"
    }
   ]
  },
  {
   "slug": "google/chat-bison@002",
   "model_name": "chat-bison@002",
   "display_name": "chat-bison@002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chat-bison@002"
    }
   ]
  },
  {
   "slug": "google/chirp-2",
   "model_name": "chirp-2",
   "display_name": "chirp-2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0002666666666666667"
      }
     },
     "provider_model_id": "google/chirp-2"
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/chirp-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chirp-2"
    }
   ]
  },
  {
   "slug": "google/chirp-3",
   "model_name": "chirp-3",
   "display_name": "chirp-3",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.000266666666666667"
      }
     },
     "provider_model_id": "google/chirp-3"
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/chirp-3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chirp-3"
    }
   ]
  },
  {
   "slug": "google/code-bison",
   "model_name": "code-bison",
   "display_name": "code-bison",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-bison"
    }
   ]
  },
  {
   "slug": "google/code-bison-32k@002",
   "model_name": "code-bison-32k@002",
   "display_name": "code-bison-32k@002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-bison-32k@002"
    }
   ]
  },
  {
   "slug": "google/code-bison@001",
   "model_name": "code-bison@001",
   "display_name": "code-bison@001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-bison@001"
    }
   ]
  },
  {
   "slug": "google/code-bison@002",
   "model_name": "code-bison@002",
   "display_name": "code-bison@002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-bison@002"
    }
   ]
  },
  {
   "slug": "google/code-gecko",
   "model_name": "code-gecko",
   "display_name": "code-gecko",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 64,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-gecko"
    }
   ]
  },
  {
   "slug": "google/code-gecko-latest",
   "model_name": "code-gecko-latest",
   "display_name": "code-gecko-latest",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 64,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-gecko-latest"
    }
   ]
  },
  {
   "slug": "google/code-gecko@001",
   "model_name": "code-gecko@001",
   "display_name": "code-gecko@001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 64,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-gecko@001"
    }
   ]
  },
  {
   "slug": "google/code-gecko@002",
   "model_name": "code-gecko@002",
   "display_name": "code-gecko@002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 64,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-gecko@002"
    }
   ]
  },
  {
   "slug": "google/codechat-bison",
   "model_name": "codechat-bison",
   "display_name": "codechat-bison",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codechat-bison"
    }
   ]
  },
  {
   "slug": "google/codechat-bison-32k",
   "model_name": "codechat-bison-32k",
   "display_name": "codechat-bison-32k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codechat-bison-32k"
    }
   ]
  },
  {
   "slug": "google/codechat-bison-32k@002",
   "model_name": "codechat-bison-32k@002",
   "display_name": "codechat-bison-32k@002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codechat-bison-32k@002"
    }
   ]
  },
  {
   "slug": "google/codechat-bison@001",
   "model_name": "codechat-bison@001",
   "display_name": "codechat-bison@001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codechat-bison@001"
    }
   ]
  },
  {
   "slug": "google/codechat-bison@002",
   "model_name": "codechat-bison@002",
   "display_name": "codechat-bison@002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codechat-bison@002"
    }
   ]
  },
  {
   "slug": "google/codechat-bison@latest",
   "model_name": "codechat-bison@latest",
   "display_name": "codechat-bison@latest",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codechat-bison@latest"
    }
   ]
  },
  {
   "slug": "google/codegemma-2b",
   "model_name": "codegemma-2b",
   "display_name": "CodeGemma 2B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/codegemma-2b"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/codegemma-2b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CodeGemma 2B"
    }
   ]
  },
  {
   "slug": "google/codegemma-7b",
   "model_name": "codegemma-7b",
   "display_name": "CodeGemma 7B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/codegemma-7b"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/codegemma-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CodeGemma 7B"
    }
   ]
  },
  {
   "slug": "google/content-moderation",
   "model_name": "content-moderation",
   "display_name": "content-moderation",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0015"
      }
     },
     "provider_model_id": "google/content-moderation"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "safety_detection",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/content-moderation"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "content-moderation"
    }
   ]
  },
  {
   "slug": "google/databricks-gemini-2-5-flash",
   "model_name": "databricks-gemini-2-5-flash",
   "display_name": "Gemini 2.5 Flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "intro": "Fast Gemini workhorse for multimodal apps where latency and price matter",
   "released_at": "2025-06-17",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash",
   "reasoning_config": {
    "budget_min": 0
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Flash"
    }
   ]
  },
  {
   "slug": "google/databricks-gemini-2-5-pro",
   "model_name": "databricks-gemini-2-5-pro",
   "display_name": "Gemini 2.5 Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Google's proven reasoning model for coding, math, and multimodal analysis",
   "released_at": "2025-06-17",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-pro",
   "reasoning_config": {
    "budget_min": 128
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Pro"
    }
   ]
  },
  {
   "slug": "google/databricks-gemini-3-1-flash-lite",
   "model_name": "databricks-gemini-3-1-flash-lite",
   "display_name": "Gemini 3.1 Flash Lite Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "intro": "Low-latency Gemini model for high-volume multimodal and agent workloads",
   "released_at": "2026-03-03",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash-lite",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.1 Flash Lite Preview"
    }
   ]
  },
  {
   "slug": "google/databricks-gemini-3-1-pro",
   "model_name": "databricks-gemini-3-1-pro",
   "display_name": "Gemini 3.1 Pro Preview Custom Tools",
   "vendor": "google",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
   "released_at": "2026-02-19",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-pro",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.1 Pro Preview Custom Tools"
    }
   ]
  },
  {
   "slug": "google/databricks-gemini-3-flash",
   "model_name": "databricks-gemini-3-flash",
   "display_name": "Gemini 3 Flash Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "intro": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs",
   "released_at": "2025-12-17",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3 Flash Preview"
    }
   ]
  },
  {
   "slug": "google/databricks-gemini-3-pro",
   "model_name": "databricks-gemini-3-pro",
   "display_name": "Gemini 3 Pro Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts",
   "released_at": "2025-11-18",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-pro",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3 Pro Preview"
    }
   ]
  },
  {
   "slug": "google/databricks-gemma-3-12b",
   "model_name": "databricks-gemma-3-12b",
   "display_name": "databricks-gemma-3-12b",
   "vendor": "google",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15000999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.50001"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-gemma-3-12b"
    }
   ]
  },
  {
   "slug": "google/deep-research-max-preview-04-2026",
   "model_name": "deep-research-max-preview-04-2026",
   "display_name": "deep-research-max-preview-04-2026",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deep-research-max-preview-04-2026"
    }
   ]
  },
  {
   "slug": "google/deep-research-preview-04-2026",
   "model_name": "deep-research-preview-04-2026",
   "display_name": "deep-research-preview-04-2026",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deep-research-preview-04-2026"
    }
   ]
  },
  {
   "slug": "google/deep-research-pro-preview-12-2025",
   "model_name": "deep-research-pro-preview-12-2025",
   "display_name": "deep-research-pro-preview-12-2025",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.134"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0011"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.134"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0011"
      }
     }
    }
   ],
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "max_input_tokens": 65536,
   "max_output_tokens": 32768,
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "rate_limits": {
    "rpm": 1000,
    "tpm": 4000000
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "google/deep-research-pro-preview-12-2025-gt-128k",
   "model_name": "deep-research-pro-preview-12-2025-gt-128k",
   "display_name": "deep-research-pro-preview-12-2025-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deep-research-pro-preview-12-2025-gt-128k"
    }
   ]
  },
  {
   "slug": "google/deep-research-pro-preview-12-2025-lte-128k",
   "model_name": "deep-research-pro-preview-12-2025-lte-128k",
   "display_name": "deep-research-pro-preview-12-2025-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deep-research-pro-preview-12-2025-lte-128k"
    }
   ]
  },
  {
   "slug": "google/deepinfra-gemma-4-26b-a4b-it",
   "model_name": "deepinfra-gemma-4-26b-a4b-it",
   "display_name": "deepinfra-gemma-4-26b-a4b-it",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.385"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.011"
      }
     }
    }
   ],
   "max_input_tokens": 262100,
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra-gemma-4-26b-a4b-it"
    }
   ]
  },
  {
   "slug": "google/e2ee-gemma-3-27b-p",
   "model_name": "e2ee-gemma-3-27b-p",
   "display_name": "Gemma 3 27B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2026-03-18",
   "max_input_tokens": 40000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 3 27B"
    }
   ]
  },
  {
   "slug": "google/e2ee-gemma-4-26b-a4b-uncensored-p",
   "model_name": "e2ee-gemma-4-26b-a4b-uncensored-p",
   "display_name": "Gemma 4 26B A4B Uncensored",
   "vendor": "google",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     }
    }
   ],
   "released_at": "2026-05-24",
   "max_input_tokens": 64000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 26B A4B Uncensored"
    }
   ]
  },
  {
   "slug": "google/e2ee-gemma-4-31b",
   "model_name": "e2ee-gemma-4-31b",
   "display_name": "Gemma 4 31B Instruct",
   "vendor": "google",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.139"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     }
    }
   ],
   "released_at": "2026-05-20",
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B Instruct"
    }
   ]
  },
  {
   "slug": "google/embedding-001",
   "model_name": "embedding-001",
   "display_name": "embedding-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "embedding-001"
    }
   ]
  },
  {
   "slug": "google/embeddinggemma-300m",
   "model_name": "embeddinggemma-300m",
   "display_name": "google/embeddinggemma-300m",
   "vendor": "google",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.002"
      }
     },
     "provider_model_id": "google/embeddinggemma-300m"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.002"
      }
     },
     "provider_model_id": "deepinfra/google/embeddinggemma-300m"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true
   },
   "max_input_tokens": 2048,
   "max_output_tokens": 2048,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "deepinfra/google/embeddinggemma-300m",
    "google/embeddinggemma-300m"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "google/embeddinggemma-300m"
    }
   ]
  },
  {
   "slug": "google/face-detector",
   "model_name": "face-detector",
   "display_name": "face-detector",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0015"
      }
     },
     "provider_model_id": "google/face-detector"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/face-detector"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "face-detector"
    }
   ]
  },
  {
   "slug": "google/fireworks/models/gemma-4-31b-it-nvfp4",
   "model_name": "fireworks/models/gemma-4-31b-it-nvfp4",
   "display_name": "Gemma 4 31B IT NVFP4",
   "vendor": "google",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-4-31b-it-nvfp4"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/gemma-4-31b-it-nvfp4"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B IT NVFP4"
    }
   ]
  },
  {
   "slug": "google/fireworks/models/gemma-4-e4b",
   "model_name": "fireworks/models/gemma-4-e4b",
   "display_name": "Gemma 4 E4B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-4-e4b"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/gemma-4-e4b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 E4B"
    }
   ]
  },
  {
   "slug": "google/flash-image-2.5",
   "model_name": "flash-image-2.5",
   "display_name": "flash-image-2.5",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.039"
      }
     },
     "provider_model_id": "google/flash-image-2.5"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/flash-image-2.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "flash-image-2.5"
    }
   ]
  },
  {
   "slug": "google/flash-image-3.1",
   "model_name": "flash-image-3.1",
   "display_name": "flash-image-3.1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.05"
      }
     },
     "provider_model_id": "google/flash-image-3.1"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/flash-image-3.1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "flash-image-3.1"
    }
   ]
  },
  {
   "slug": "google/flash-image-3.1-lite",
   "model_name": "flash-image-3.1-lite",
   "display_name": "flash-image-3.1-lite",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/flash-image-3.1-lite"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/flash-image-3.1-lite"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "flash-image-3.1-lite"
    }
   ]
  },
  {
   "slug": "google/gemini-1-5-flash-8b",
   "model_name": "gemini-1-5-flash-8b",
   "display_name": "Gemini 1.5 Flash-8B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gemini-1.5-flash-8b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-1.5-flash-8b"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "gemini-1.5-flash-8b"
    }
   ],
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "doc",
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true,
    "reasoning": true
   },
   "max_input_tokens": 1000000,
   "released_at": "2024-10-03",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-1.5-flash-8b",
    "google/gemini-1.5-flash-8b"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Flash 8B 是一款高效多模态模型，适用于广泛应用场景。",
    "zh-TW": "Gemini 1.5 Flash 8B 是一款高效率的多模態模型，適用於廣泛應用的擴展場景。",
    "ja-JP": "Gemini 1.5 Flash 8B は、幅広い応用に対応する効率的なマルチモーダルモデルです。",
    "ru-RU": "Gemini 1.5 Flash 8B — эффективная мультимодальная модель для масштабируемого применения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Flash-8B"
    }
   ]
  },
  {
   "slug": "google/gemini-1.0-pro",
   "model_name": "gemini-1.0-pro",
   "display_name": "gemini-1.0-pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.125"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.0-pro"
    }
   ]
  },
  {
   "slug": "google/gemini-1.0-pro-001",
   "model_name": "gemini-1.0-pro-001",
   "display_name": "Gemini 1.0 Pro 001 (Tuning)",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.125"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "released_at": "2023-12-06",
   "max_input_tokens": 32768,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.0 Pro 001（调优版）为复杂任务提供稳定、可调性能。",
    "zh-TW": "Gemini 1.0 Pro 001（調校版）在處理複雜任務時提供穩定且可調整的效能。",
    "ja-JP": "Gemini 1.0 Pro 001（チューニング）は、複雑なタスクに対して安定かつ調整可能な性能を提供します。",
    "ru-RU": "Gemini 1.0 Pro 001 (Tuning) обеспечивает стабильную и настраиваемую производительность для сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.0 Pro 001 (Tuning)"
    }
   ]
  },
  {
   "slug": "google/gemini-1.0-pro-002",
   "model_name": "gemini-1.0-pro-002",
   "display_name": "Gemini 1.0 Pro 002 (Tuning)",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.125"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "released_at": "2023-12-06",
   "max_input_tokens": 32768,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.0 Pro 002（调优版）为复杂任务提供强大的多模态支持。",
    "zh-TW": "Gemini 1.0 Pro 002（調校版）在處理複雜任務時提供強大的多模態支援。",
    "ja-JP": "Gemini 1.0 Pro 002（チューニング）は、複雑なタスクに対して強力なマルチモーダル対応を提供します。",
    "ru-RU": "Gemini 1.0 Pro 002 (Tuning) обеспечивает мощную мультимодальную поддержку для сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.0 Pro 002 (Tuning)"
    }
   ]
  },
  {
   "slug": "google/gemini-1.0-pro-latest",
   "model_name": "gemini-1.0-pro-latest",
   "display_name": "Gemini 1.0 Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "released_at": "2023-12-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.0 Pro 是 Google 的高性能 AI 模型，适用于大规模任务处理。",
    "zh-TW": "Gemini 1.0 Pro 是 Google 所推出的高效能 AI 模型，專為大規模任務擴展而設計。",
    "ja-JP": "Gemini 1.0 Pro は、Google による高性能 AI モデルで、幅広いタスクに対応可能です。",
    "ru-RU": "Gemini 1.0 Pro — высокопроизводительная модель ИИ от Google, предназначенная для масштабирования широкого спектра задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.0 Pro"
    }
   ]
  },
  {
   "slug": "google/gemini-1.0-pro-vision",
   "model_name": "gemini-1.0-pro-vision",
   "display_name": "gemini-1.0-pro-vision",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.0-pro-vision"
    }
   ]
  },
  {
   "slug": "google/gemini-1.0-pro-vision-001",
   "model_name": "gemini-1.0-pro-vision-001",
   "display_name": "gemini-1.0-pro-vision-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Google's first-generation advanced multimodal model that can understand text, code, and images. It provides strong reasoning capabilities and follows instructions effectively.",
   "max_input_tokens": 32768,
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "vision": true
   },
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.0-pro-vision-001"
    }
   ]
  },
  {
   "slug": "google/gemini-1.0-ultra",
   "model_name": "gemini-1.0-ultra",
   "display_name": "gemini-1.0-ultra",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.125"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.0-ultra"
    }
   ]
  },
  {
   "slug": "google/gemini-1.0-ultra-001",
   "model_name": "gemini-1.0-ultra-001",
   "display_name": "gemini-1.0-ultra-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.125"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.0-ultra-001"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash",
   "model_name": "gemini-1.5-flash",
   "display_name": "gemini-1.5-flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01875"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.01875"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00002"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "13.333333",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-1.5-flash"
    }
   ],
   "docs_url": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
   "max_input_tokens": 8192,
   "deprecated": true,
   "model_type": "vision_understanding",
   "deprecation_date": "2025-09-29",
   "rate_limits": {
    "rpm": 10000,
    "tpm": 10000000
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "intro": "A faster, more cost-effective variant of Gemini 1.5 that maintains strong capabilities while optimizing for performance and cost efficiency. Suitable for production deployments requiring high throughput.",
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "doc",
     "image",
     "pdf"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-1.5-flash"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "limit",
     "new": "8192",
     "note": "max_output_tokens"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-001",
   "model_name": "gemini-1.5-flash-001",
   "display_name": "Gemini 1.5 Flash 001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.01875"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00002"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.05"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "13.333333",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "doc",
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 1008192,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Flash 001 是一款高效多模态模型，适用于广泛应用场景。",
    "zh-TW": "Gemini 1.5 Flash 001 是一款高效率的多模態模型，適用於廣泛應用的擴展場景。",
    "ja-JP": "Gemini 1.5 Flash 001 は、幅広い応用に対応する効率的なマルチモーダルモデルです。",
    "ru-RU": "Gemini 1.5 Flash 001 — эффективная мультимодальная модель для масштабируемого применения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Flash 001"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-001-gt-128k",
   "model_name": "gemini-1.5-flash-001-gt-128k",
   "display_name": "gemini-1.5-flash-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-001-lte-128k",
   "model_name": "gemini-1.5-flash-001-lte-128k",
   "display_name": "gemini-1.5-flash-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-002",
   "model_name": "gemini-1.5-flash-002",
   "display_name": "Gemini 1.5 Flash 002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.01875"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00002"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.05"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "13.333333",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "doc",
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 1008192,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Flash 002 是一款高效多模态模型，适用于大规模部署。",
    "zh-TW": "Gemini 1.5 Flash 002 是一款高效率的多模態模型，專為大規模部署而打造。",
    "ja-JP": "Gemini 1.5 Flash 002 は、広範な展開を目的とした効率的なマルチモーダルモデルです。",
    "ru-RU": "Gemini 1.5 Flash 002 — эффективная мультимодальная модель, созданная для широкого внедрения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Flash 002"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-002-gt-128k",
   "model_name": "gemini-1.5-flash-002-gt-128k",
   "display_name": "gemini-1.5-flash-002-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-002-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-002-lte-128k",
   "model_name": "gemini-1.5-flash-002-lte-128k",
   "display_name": "gemini-1.5-flash-002-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-002-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-128k",
   "model_name": "gemini-1.5-flash-128k",
   "display_name": "Gemini 1.5 Flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Flash"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-8b-001-gt-128k",
   "model_name": "gemini-1.5-flash-8b-001-gt-128k",
   "display_name": "gemini-1.5-flash-8b-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-8b-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-8b-001-lte-128k",
   "model_name": "gemini-1.5-flash-8b-001-lte-128k",
   "display_name": "gemini-1.5-flash-8b-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-8b-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-8b-128k",
   "model_name": "gemini-1.5-flash-8b-128k",
   "display_name": "Gemini 1.5 Flash-8B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Flash-8B"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-8b-exp-0924",
   "model_name": "gemini-1.5-flash-8b-exp-0924",
   "display_name": "Gemini 1.5 Flash 8B 0924",
   "vendor": "google",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2024-09-24",
   "max_input_tokens": 1008192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Flash 8B 0924 是最新实验模型，在文本与多模态用例中取得显著提升。",
    "zh-TW": "Gemini 1.5 Flash 8B 0924 是最新的實驗性模型，在文字與多模態應用上有顯著提升。",
    "ja-JP": "Gemini 1.5 Flash 8B 0924 は、テキストおよびマルチモーダルのユースケースにおいて顕著な進歩を示す最新の実験モデルです。",
    "ru-RU": "Gemini 1.5 Flash 8B 0924 — новейшая экспериментальная модель с заметными улучшениями в текстовых и мультимодальных сценариях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Flash 8B 0924"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-8b-gt-128k",
   "model_name": "gemini-1.5-flash-8b-gt-128k",
   "display_name": "gemini-1.5-flash-8b-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-8b-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-8b-latest-gt-128k",
   "model_name": "gemini-1.5-flash-8b-latest-gt-128k",
   "display_name": "gemini-1.5-flash-8b-latest-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-8b-latest-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-8b-latest-lte-128k",
   "model_name": "gemini-1.5-flash-8b-latest-lte-128k",
   "display_name": "gemini-1.5-flash-8b-latest-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-8b-latest-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-8b-lte-128k",
   "model_name": "gemini-1.5-flash-8b-lte-128k",
   "display_name": "gemini-1.5-flash-8b-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-8b-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-exp-0827",
   "model_name": "gemini-1.5-flash-exp-0827",
   "display_name": "Gemini 1.5 Flash 0827",
   "vendor": "google",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2024-08-27",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 1008192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Flash 0827 优化多模态处理，适用于复杂任务。",
    "zh-TW": "Gemini 1.5 Flash 0827 提供針對複雜任務的最佳化多模態處理能力。",
    "ja-JP": "Gemini 1.5 Flash 0827 は、複雑なタスクに対する最適化されたマルチモーダル処理を提供します。",
    "ru-RU": "Gemini 1.5 Flash 0827 обеспечивает оптимизированную мультимодальную обработку для сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Flash 0827"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-gt-128k",
   "model_name": "gemini-1.5-flash-gt-128k",
   "display_name": "gemini-1.5-flash-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-latest",
   "model_name": "gemini-1.5-flash-latest",
   "display_name": "Gemini 1.5 Flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "doc",
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 1008192,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Flash 是 Google 最新的多模态 AI 模型，处理速度快，支持文本、图像与视频输入，适用于高效任务扩展。",
    "zh-TW": "Gemini 1.5 Flash 是 Google 最新的多模態 AI 模型，具備快速處理能力，支援文字、圖像與影片輸入，能高效擴展至各類任務。",
    "ja-JP": "Gemini 1.5 Flash は、Google による最新のマルチモーダル AI モデルで、テキスト・画像・動画入力に対応し、タスク全体の効率的なスケーリングを実現します。",
    "ru-RU": "Gemini 1.5 Flash — новейшая мультимодальная модель ИИ от Google с быстрой обработкой, поддержкой текста, изображений и видео для эффективного масштабирования задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Flash"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-latest-gt-128k",
   "model_name": "gemini-1.5-flash-latest-gt-128k",
   "display_name": "gemini-1.5-flash-latest-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-latest-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-latest-lte-128k",
   "model_name": "gemini-1.5-flash-latest-lte-128k",
   "display_name": "gemini-1.5-flash-latest-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-latest-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-lte-128k",
   "model_name": "gemini-1.5-flash-lte-128k",
   "display_name": "gemini-1.5-flash-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-flash-preview-0514",
   "model_name": "gemini-1.5-flash-preview-0514",
   "display_name": "gemini-1.5-flash-preview-0514",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-flash-preview-0514"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro",
   "model_name": "gemini-1.5-pro",
   "display_name": "Gemini 1.5 Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "pydantic-prices+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.3125"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00032875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Google's most capable multimodal model with an extremely long context window of up to 1 million tokens. It excels at complex reasoning, long-form content processing, and multimodal understanding.",
   "max_input_tokens": 1000000,
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true
   },
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Pro"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-001",
   "model_name": "gemini-1.5-pro-001",
   "display_name": "Gemini 1.5 Pro 001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.3125"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00032875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.5"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "doc",
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2024-02-15",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 2008192,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Pro 001 是一款可扩展的多模态 AI 解决方案，适用于复杂任务。",
    "zh-TW": "Gemini 1.5 Pro 001 是一款可擴展的多模態 AI 解決方案，適用於處理複雜任務。",
    "ja-JP": "Gemini 1.5 Pro 001 は、複雑なタスクに対応するスケーラブルなマルチモーダル AI ソリューションです。",
    "ru-RU": "Gemini 1.5 Pro 001 — масштабируемое мультимодальное ИИ-решение для сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Pro 001"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-001-gt-128k",
   "model_name": "gemini-1.5-pro-001-gt-128k",
   "display_name": "gemini-1.5-pro-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-001-lte-128k",
   "model_name": "gemini-1.5-pro-001-lte-128k",
   "display_name": "gemini-1.5-pro-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-002",
   "model_name": "gemini-1.5-pro-002",
   "display_name": "Gemini 1.5 Pro 002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.3125"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00032875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.315"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "doc",
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2024-09-24",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 2008192,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Pro 002 是最新的生产级模型，在数学、长上下文和视觉任务方面输出质量更高。",
    "zh-TW": "Gemini 1.5 Pro 002 是最新的生產就緒模型，輸出品質更高，特別適用於數學、長上下文與視覺任務。",
    "ja-JP": "Gemini 1.5 Pro 002 は、特に数学、長文コンテキスト、視覚タスクにおいて高品質な出力を提供する最新の本番対応モデルです。",
    "ru-RU": "Gemini 1.5 Pro 002 — новейшая модель, готовая к производству, с более качественным выводом, особенно в математике, длинном контексте и визуальных задачах."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Pro 002"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-002-batchx",
   "model_name": "gemini-1.5-pro-002-batchx",
   "display_name": "gemini-1.5-pro-002-batchx",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-002-batchx"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-002-gt-128k",
   "model_name": "gemini-1.5-pro-002-gt-128k",
   "display_name": "gemini-1.5-pro-002-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-002-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-002-lte-128k",
   "model_name": "gemini-1.5-pro-002-lte-128k",
   "display_name": "gemini-1.5-pro-002-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-002-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-128k",
   "model_name": "gemini-1.5-pro-128k",
   "display_name": "Gemini 1.5 Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Pro"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-exp-0801",
   "model_name": "gemini-1.5-pro-exp-0801",
   "display_name": "Gemini 1.5 Pro 0801",
   "vendor": "google",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.5"
      }
     }
    }
   ],
   "released_at": "2024-08-01",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 2008192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Pro 0801 提供强大的多模态处理能力，为应用开发带来更大灵活性。",
    "zh-TW": "Gemini 1.5 Pro 0801 提供強大的多模態處理能力，並具備更高的應用開發彈性。",
    "ja-JP": "Gemini 1.5 Pro 0801 は、アプリ開発における柔軟性を高めた強力なマルチモーダル処理を提供します。",
    "ru-RU": "Gemini 1.5 Pro 0801 обеспечивает мощную мультимодальную обработку с большей гибкостью для разработки приложений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Pro 0801"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-exp-0827",
   "model_name": "gemini-1.5-pro-exp-0827",
   "display_name": "Gemini 1.5 Pro 0827",
   "vendor": "google",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.5"
      }
     }
    }
   ],
   "released_at": "2024-08-27",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 2008192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Pro 0827 应用了最新优化，提升多模态处理效率。",
    "zh-TW": "Gemini 1.5 Pro 0827 採用最新優化技術，提升多模態處理效率。",
    "ja-JP": "Gemini 1.5 Pro 0827 は、より効率的なマルチモーダル処理のための最新の最適化を適用しています。",
    "ru-RU": "Gemini 1.5 Pro 0827 использует последние оптимизации для более эффективной мультимодальной обработки."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Pro 0827"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-gt-128k",
   "model_name": "gemini-1.5-pro-gt-128k",
   "display_name": "gemini-1.5-pro-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-latest",
   "model_name": "gemini-1.5-pro-latest",
   "display_name": "Gemini 1.5 Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.875"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.5"
      }
     }
    }
   ],
   "released_at": "2024-02-15",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 2008192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 1.5 Pro 支持最多 200 万个 token，是一款适用于复杂任务的中型多模态模型。",
    "zh-TW": "Gemini 1.5 Pro 支援最多 200 萬個 token，是一款中型多模態模型，適合處理複雜任務。",
    "ja-JP": "Gemini 1.5 Pro は最大 200 万トークンに対応し、複雑なタスクに最適な中規模マルチモーダルモデルです。",
    "ru-RU": "Gemini 1.5 Pro поддерживает до 2 миллионов токенов, являясь идеальной мультимодальной моделью среднего размера для сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Pro"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-latest-gt-128k",
   "model_name": "gemini-1.5-pro-latest-gt-128k",
   "display_name": "gemini-1.5-pro-latest-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-latest-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-latest-lte-128k",
   "model_name": "gemini-1.5-pro-latest-lte-128k",
   "display_name": "gemini-1.5-pro-latest-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-latest-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-lte-128k",
   "model_name": "gemini-1.5-pro-lte-128k",
   "display_name": "gemini-1.5-pro-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-preview-0409",
   "model_name": "gemini-1.5-pro-preview-0409",
   "display_name": "gemini-1.5-pro-preview-0409",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-preview-0409"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-pro-preview-0514",
   "model_name": "gemini-1.5-pro-preview-0514",
   "display_name": "gemini-1.5-pro-preview-0514",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-pro-preview-0514"
    }
   ]
  },
  {
   "slug": "google/gemini-1.5-vision",
   "model_name": "gemini-1.5-vision",
   "display_name": "gemini-1.5-vision",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-1.5-vision"
    }
   ]
  },
  {
   "slug": "google/gemini-2-5-flash-deepsearch",
   "model_name": "gemini-2-5-flash-deepsearch",
   "display_name": "gemini-2.5-flash-deepsearch",
   "vendor": "google",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    }
   ],
   "released_at": "2025-06-08",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-deepsearch"
    }
   ]
  },
  {
   "slug": "google/gemini-2-5-flash-nothink",
   "model_name": "gemini-2-5-flash-nothink",
   "display_name": "gemini-2.5-flash-nothink",
   "vendor": "google",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "gemini-2.5-flash-nothink"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.499"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "gemini-2.5-flash-nothink"
    }
   ],
   "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
   "released_at": "2025-06-24",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-2.5-flash-nothink"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-nothink"
    }
   ]
  },
  {
   "slug": "google/gemini-2-5-flash-search",
   "model_name": "gemini-2-5-flash-search",
   "display_name": "gemini-2.5-flash-search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.499"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "gemini-2.5-flash-search"
    }
   ],
   "released_at": "2025-07-16",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-2.5-flash-search"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-search"
    }
   ]
  },
  {
   "slug": "google/gemini-2-5-pro-deepsearch",
   "model_name": "gemini-2-5-pro-deepsearch",
   "display_name": "gemini-2.5-pro-deepsearch",
   "vendor": "google",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "35"
      }
     }
    }
   ],
   "released_at": "2025-06-08",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-deepsearch"
    }
   ]
  },
  {
   "slug": "google/gemini-2-5-pro-search",
   "model_name": "gemini-2-5-pro-search",
   "display_name": "gemini-2.5-pro-search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gemini-2.5-pro-search"
    }
   ],
   "released_at": "2025-07-16",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-2.5-pro-search"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-search"
    }
   ]
  },
  {
   "slug": "google/gemini-2-flash",
   "model_name": "gemini-2-flash",
   "display_name": "gemini-2.0-flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2025-02-06",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash"
    }
   ]
  },
  {
   "slug": "google/gemini-2-flash-exp-search",
   "model_name": "gemini-2-flash-exp-search",
   "display_name": "gemini-2.0-flash-exp-search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2025-01-23",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-exp-search"
    }
   ]
  },
  {
   "slug": "google/gemini-2-flash-lite",
   "model_name": "gemini-2-flash-lite",
   "display_name": "gemini-2.0-flash-lite",
   "vendor": "google",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2025-06-16",
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-lite"
    }
   ]
  },
  {
   "slug": "google/gemini-2-flash-search",
   "model_name": "gemini-2-flash-search",
   "display_name": "gemini-2.0-flash-search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2025-02-08",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-search"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash",
   "model_name": "gemini-2.0-flash",
   "display_name": "Gemini 2.0 Flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.75",
        "completion": "0.75"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-west9",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1425"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "gemini-2.0-flash-20250609"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash"
    }
   ],
   "intro": "Earlier Gemini Flash workhorse for responsive multimodal apps and tool use",
   "released_at": "2024-12-11",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 1048576,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/pricing#2_0flash",
   "model_type": "vision_understanding",
   "deprecation_date": "2026-06-01",
   "rate_limits": {
    "rpm": 10000,
    "tpm": 10000000
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-2.0-flash-20250609",
    "google/gemini-2.0-flash"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.0 Flash 提供下一代功能，包括卓越速度、原生工具使用、多模态生成以及 100 万 token 上下文窗口。",
    "zh-TW": "Gemini 2.0 Flash 提供次世代功能，包括極速處理、原生工具使用、多模態生成，以及 100 萬 token 的上下文視窗。",
    "ja-JP": "Gemini 2.0 Flash は、次世代の機能を提供するモデルで、卓越したスピード、ネイティブツールの使用、マルチモーダル生成、100万トークンのコンテキストウィンドウを備えています。",
    "ru-RU": "Gemini 2.0 Flash предлагает функции следующего поколения, включая исключительную скорость, нативное использование инструментов, мультимодальную генерацию и контекст до 1 миллиона токенов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-001",
   "model_name": "gemini-2.0-flash-001",
   "display_name": "gemini-2.0-flash-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "europe-west9",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-001",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-001"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-001"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1833"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-001"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "deepinfra/google/gemini-2.0-flash-001"
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "max_input_tokens": 1048576,
   "max_output_tokens": 8192,
   "deprecated": true,
   "model_type": "vision_understanding",
   "deprecation_date": "2026-06-01",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "rate_limits": {
    "rpm": 10000,
    "tpm": 10000000
   },
   "modalities": {
    "input": [
     "doc",
     "image",
     "pdf"
    ],
    "output": []
   },
   "released_at": "2025-02-05",
   "knowledge_cutoff": "2024-08",
   "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
   "family": "gemini-flash",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "deepinfra/google/gemini-2.0-flash-001",
    "google/gemini-2.0-flash-001"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.0 Flash 提供下一代功能，包括卓越速度、原生工具使用、多模态生成以及 100 万 token 上下文窗口。",
    "zh-TW": "Gemini 2.0 Flash 提供次世代功能，包括極速處理、原生工具使用、多模態生成，以及 100 萬 token 的上下文視窗。",
    "ja-JP": "Gemini 2.0 Flash は、次世代の機能を提供するモデルで、卓越したスピード、ネイティブツールの使用、マルチモーダル生成、100万トークンのコンテキストウィンドウを備えています。",
    "ru-RU": "Gemini 2.0 Flash предлагает функции следующего поколения, включая исключительную скорость, нативное использование инструментов, мультимодальную генерацию и контекст до 1 миллиона токенов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-001-gt-128k",
   "model_name": "gemini-2.0-flash-001-gt-128k",
   "display_name": "gemini-2.0-flash-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-001-lte-128k",
   "model_name": "gemini-2.0-flash-001-lte-128k",
   "display_name": "gemini-2.0-flash-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-exp-001",
   "model_name": "gemini-2.0-flash-exp-001",
   "display_name": "gemini-2.0-flash-exp-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-exp-001"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-exp-001-gt-128k",
   "model_name": "gemini-2.0-flash-exp-001-gt-128k",
   "display_name": "gemini-2.0-flash-exp-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-exp-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-exp-001-lte-128k",
   "model_name": "gemini-2.0-flash-exp-001-lte-128k",
   "display_name": "gemini-2.0-flash-exp-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-exp-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-exp-image-generation",
   "model_name": "gemini-2.0-flash-exp-image-generation",
   "display_name": "gemini-2.0-flash-exp-image-generation",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.039"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "docs_url": "https://ai.google.dev/pricing",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "image_generation",
   "capabilities": {
    "vision": true
   },
   "rate_limits": {
    "rpm": 10,
    "tpm": 250000
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-02-19",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   }
  },
  {
   "slug": "google/gemini-2.0-flash-exp:free",
   "model_name": "gemini-2.0-flash-exp:free",
   "display_name": "Google Gemini 2.0 Flash Experimental",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "helicone-registry",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     },
     "provider_model_id": "gemini-2.0-flash-exp"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "helicone-registry+portkey",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "gemini-2.0-flash-exp",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "126.6"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-exp:free"
    }
   ],
   "intro": "Experimental version of Gemini 2.0 Flash with native image generation capabilities. Features multimodal input and output support including text and images.",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "structured_output": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-2.0-flash-exp",
    "google/gemini-2.0-flash-exp:free"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Google Gemini 2.0 Flash Experimental"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-gt-128k",
   "model_name": "gemini-2.0-flash-gt-128k",
   "display_name": "gemini-2.0-flash-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-lite",
   "model_name": "gemini-2.0-flash-lite",
   "display_name": "Gemini 2.0 Flash-Lite",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01875"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "provider_model_id": "gemini-2-0-flash-lite",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "2.666667"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01875"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "europe-west9",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0712"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.285"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.052"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2024-12-11",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 1048576,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash-lite",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.0-flash-lite",
   "model_type": "vision_understanding",
   "deprecation_date": "2026-06-01",
   "rate_limits": {
    "rpm": 4000,
    "tpm": 4000000
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-2-0-flash-lite",
    "google/gemini-2.0-flash-lite"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.0 Flash 的一个轻量变体，优化了成本效率与低延迟表现。",
    "zh-TW": "Gemini 2.0 Flash 的一個變體，針對成本效益與低延遲進行最佳化。",
    "ja-JP": "コスト効率と低遅延に最適化された Gemini 2.0 Flash のバリアントです。",
    "ru-RU": "Вариант Gemini 2.0 Flash, оптимизированный по стоимости и задержке."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-lite-001",
   "model_name": "gemini-2.0-flash-lite-001",
   "display_name": "gemini-2.0-flash-lite-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01875"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01875"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "asia-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "asia-east2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "asia-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "asia-northeast3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "asia-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "australia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "europe-west2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "europe-west3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "europe-west6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "europe-west9",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "me-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "me-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "me-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "northamerica-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "southamerica-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001",
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.0-flash-lite-001"
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
   "max_input_tokens": 1048576,
   "max_output_tokens": 8192,
   "deprecated": true,
   "model_type": "vision_understanding",
   "deprecation_date": "2026-06-01",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "rate_limits": {
    "rpm": 4000,
    "tpm": 4000000
   },
   "modalities": {
    "input": [
     "doc",
     "image",
     "pdf"
    ],
    "output": [
     "audio"
    ]
   },
   "released_at": "2025-02-05",
   "knowledge_cutoff": "2024-08",
   "intro": "Low-latency Gemini model for high-volume multimodal and agent workloads",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-2.0-flash-lite-001"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.0 Flash 的一个轻量变体，优化了成本效率与低延迟表现。",
    "zh-TW": "Gemini 2.0 Flash 的一個變體，針對成本效益與低延遲進行最佳化。",
    "ja-JP": "コスト効率と低遅延に最適化された Gemini 2.0 Flash のバリアントです。",
    "ru-RU": "Вариант Gemini 2.0 Flash, оптимизированный по стоимости и задержке."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-lite-001-gt-128k",
   "model_name": "gemini-2.0-flash-lite-001-gt-128k",
   "display_name": "gemini-2.0-flash-lite-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "0"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-lite-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-lite-001-lte-128k",
   "model_name": "gemini-2.0-flash-lite-001-lte-128k",
   "display_name": "gemini-2.0-flash-lite-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "0"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-lite-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-lite-gt-128k",
   "model_name": "gemini-2.0-flash-lite-gt-128k",
   "display_name": "gemini-2.0-flash-lite-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "0"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-lite-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-lite-lte-128k",
   "model_name": "gemini-2.0-flash-lite-lte-128k",
   "display_name": "gemini-2.0-flash-lite-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "0"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-lite-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-lite-preview-02-05",
   "model_name": "gemini-2.0-flash-lite-preview-02-05",
   "display_name": "gemini-2.0-flash-lite-preview-02-05",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-lite-preview-02-05"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-lte-128k",
   "model_name": "gemini-2.0-flash-lte-128k",
   "display_name": "gemini-2.0-flash-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-preview-image-generation",
   "model_name": "gemini-2.0-flash-preview-image-generation",
   "display_name": "gemini-2.0-flash-preview-image-generation",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.0-flash-preview-image-generation"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-thinking-exp-01-21",
   "model_name": "gemini-2.0-flash-thinking-exp-01-21",
   "display_name": "Gemini 2.0 Flash Thinking 0121",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.003"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-01-21",
   "max_input_tokens": 1000000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.0 Flash Thinking 0121"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-flash-thinking-exp-1219",
   "model_name": "gemini-2.0-flash-thinking-exp-1219",
   "display_name": "Gemini 2.0 Flash Thinking 1219",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-12-19",
   "max_input_tokens": 32767,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.0 Flash Thinking 1219"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-pro-exp-02-05",
   "model_name": "gemini-2.0-pro-exp-02-05",
   "display_name": "Gemini 2.0 Pro 0205",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.956"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-02-05",
   "max_input_tokens": 2097152,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.0 Pro 0205"
    }
   ]
  },
  {
   "slug": "google/gemini-2.0-pro-reasoner",
   "model_name": "gemini-2.0-pro-reasoner",
   "display_name": "Gemini 2.0 Pro Reasoner",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.292"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.998"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-02-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "audio_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.0 Pro Reasoner"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-computer-use-preview-10-2025",
   "model_name": "gemini-2.5-computer-use-preview-10-2025",
   "display_name": "gemini-2.5-computer-use-preview-10-2025",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-computer-use-preview-10-2025",
     "region": "us-central1",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use",
   "max_input_tokens": 128000,
   "max_output_tokens": 64000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "computer_use": true,
    "parallel_function_calling": true
   },
   "rate_limits": {
    "rpm": 2000,
    "tpm": 800000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-10-01",
   "aliases": [
    "google/gemini-2.5-computer-use-preview-10-2025"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-computer-use-preview-10-2025-gt-128k",
   "model_name": "gemini-2.5-computer-use-preview-10-2025-gt-128k",
   "display_name": "gemini-2.5-computer-use-preview-10-2025-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-computer-use-preview-10-2025-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-computer-use-preview-10-2025-lte-128k",
   "model_name": "gemini-2.5-computer-use-preview-10-2025-lte-128k",
   "display_name": "gemini-2.5-computer-use-preview-10-2025-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-computer-use-preview-10-2025-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash",
   "model_name": "gemini-2.5-flash",
   "display_name": "Gemini 2.5 Flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "1"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "gemini-2-5-flash",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+litellm+helicone-registry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.383"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "1"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "image_output": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "image_output": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "0.666667"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "image_output": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "asia-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "asia-northeast3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "asia-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "australia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "europe-west2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "europe-west3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "europe-west9",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "northamerica-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "southamerica-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "gemini-2-5-flash"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.268"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.236"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.026"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "gemini-2-5-flash"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0000003"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.021"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "qihang-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "deepinfra/google/gemini-2.5-flash"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash"
    }
   ],
   "intro": "Fast Gemini workhorse for multimodal apps where latency and price matter",
   "released_at": "2025-06-17",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 0
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
   "model_type": "image_generation",
   "rate_limits": {
    "rpm": 100000,
    "tpm": 8000000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "deprecated": true,
   "aliases": [
    "coding/gemini-2.5-flash",
    "deepinfra/google/gemini-2.5-flash",
    "gemini-2-5-flash",
    "google/gemini-2.5-flash",
    "vertex/gemini-2.5-flash"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.5 Flash 是 Google 功能最全、性价比最高的模型。",
    "zh-TW": "Gemini 2.5 Flash 是 Google 功能最完整、性價比最高的模型。",
    "ja-JP": "Gemini 2.5 Flash は、Google によるフル機能を備えた最もコスト効率の高いモデルです。",
    "ru-RU": "Gemini 2.5 Flash — самая выгодная модель от Google с полным набором возможностей."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-gt-128k",
   "model_name": "gemini-2.5-flash-gt-128k",
   "display_name": "gemini-2.5-flash-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image",
   "model_name": "gemini-2.5-flash-image",
   "display_name": "Nano Banana",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.039"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.041667"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.039"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333333333333334"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0000003"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4999999"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "25"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.039"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image",
     "tracks": [
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image"
    }
   ],
   "intro": "Nano Banana image model for fast generation, edits, and character-consistent assets",
   "released_at": "2025-08-26",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "gemini-flash",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image",
   "model_type": "image_generation",
   "rate_limits": {
    "rpm": 100000,
    "tpm": 8000000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_p"
    ]
   },
   "aliases": [
    "google/gemini-2.5-flash-image",
    "vertex/gemini-2.5-flash-image"
   ],
   "intro_i18n": {
    "zh-CN": "Nano Banana 是 Google 最新、最快、最高效的原生多模态模型，支持对话式图像生成与编辑。",
    "zh-TW": "Nano Banana 是 Google 最新、最快且最有效率的原生多模態模型，支援對話式圖像生成與編輯。",
    "ja-JP": "Nano Banana は、Google による最新かつ最速、最も効率的なネイティブマルチモーダルモデルで、会話形式での画像生成と編集が可能です。",
    "ru-RU": "Nano Banana — новейшая, самая быстрая и эффективная нативная мультимодальная модель от Google, поддерживающая генерацию и редактирование изображений в диалоговом режиме."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "audio_input: true→false"
    },
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "video_input: true→false"
    },
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image-gt-128k",
   "model_name": "gemini-2.5-flash-image-gt-128k",
   "display_name": "gemini-2.5-flash-image-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-image-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image-lte-128k",
   "model_name": "gemini-2.5-flash-image-lte-128k",
   "display_name": "gemini-2.5-flash-image-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-image-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image-preview",
   "model_name": "gemini-2.5-flash-image-preview",
   "display_name": "Nano Banana Preview (Gemini 2.5 Flash Image Preview)",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "image_output": "0.5",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "image_output": "0.5",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-image-preview"
    }
   ],
   "capabilities": {
    "image_output": true
   },
   "released_at": "2025-03-20",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "gemini-flash",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-2.5-flash-image-preview"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nano Banana Preview (Gemini 2.5 Flash Image Preview)"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image-preview-gt-128k",
   "model_name": "gemini-2.5-flash-image-preview-gt-128k",
   "display_name": "gemini-2.5-flash-image-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.039"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-image-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image-preview-lte-128k",
   "model_name": "gemini-2.5-flash-image-preview-lte-128k",
   "display_name": "gemini-2.5-flash-image-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.039"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-image-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image:image",
   "model_name": "gemini-2.5-flash-image:image",
   "display_name": "Nano Banana",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    }
   ],
   "released_at": "2025-08-26",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Nano Banana 是 Google 最新、最快、最高效的原生多模态模型，支持对话式图像生成与编辑。",
    "zh-TW": "Nano Banana 是 Google 最新、最快且最有效率的原生多模態模型，支援對話式圖像生成與編輯。",
    "ja-JP": "Nano Banana は、Google による最新かつ最速、最も効率的なネイティブマルチモーダルモデルで、会話形式での画像生成と編集が可能です。",
    "ru-RU": "Nano Banana — новейшая, самая быстрая и эффективная нативная мультимодальная модель от Google, поддерживающая генерацию и редактирование изображений в диалоговом режиме."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nano Banana"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@europe-central2",
   "model_name": "gemini-2.5-flash-image@europe-central2",
   "display_name": "vertex/gemini-2.5-flash-image@europe-central2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@europe-central2"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@europe-central2"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@europe-central2"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@europe-north1",
   "model_name": "gemini-2.5-flash-image@europe-north1",
   "display_name": "vertex/gemini-2.5-flash-image@europe-north1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@europe-north1"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@europe-north1"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@europe-north1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@europe-southwest1",
   "model_name": "gemini-2.5-flash-image@europe-southwest1",
   "display_name": "vertex/gemini-2.5-flash-image@europe-southwest1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@europe-southwest1"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@europe-southwest1"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@europe-southwest1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@europe-west1",
   "model_name": "gemini-2.5-flash-image@europe-west1",
   "display_name": "vertex/gemini-2.5-flash-image@europe-west1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@europe-west1"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@europe-west1"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@europe-west1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@europe-west4",
   "model_name": "gemini-2.5-flash-image@europe-west4",
   "display_name": "vertex/gemini-2.5-flash-image@europe-west4",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@europe-west4"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@europe-west4"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@europe-west4"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@europe-west8",
   "model_name": "gemini-2.5-flash-image@europe-west8",
   "display_name": "vertex/gemini-2.5-flash-image@europe-west8",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@europe-west8"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@europe-west8"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@europe-west8"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@us-central1",
   "model_name": "gemini-2.5-flash-image@us-central1",
   "display_name": "vertex/gemini-2.5-flash-image@us-central1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@us-central1"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@us-central1"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@us-central1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@us-east1",
   "model_name": "gemini-2.5-flash-image@us-east1",
   "display_name": "vertex/gemini-2.5-flash-image@us-east1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@us-east1"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@us-east1"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@us-east1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@us-east4",
   "model_name": "gemini-2.5-flash-image@us-east4",
   "display_name": "vertex/gemini-2.5-flash-image@us-east4",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@us-east4"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@us-east4"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@us-east4"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@us-east5",
   "model_name": "gemini-2.5-flash-image@us-east5",
   "display_name": "vertex/gemini-2.5-flash-image@us-east5",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@us-east5"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@us-east5"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@us-east5"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@us-south1",
   "model_name": "gemini-2.5-flash-image@us-south1",
   "display_name": "vertex/gemini-2.5-flash-image@us-south1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@us-south1"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@us-south1"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@us-south1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@us-west1",
   "model_name": "gemini-2.5-flash-image@us-west1",
   "display_name": "vertex/gemini-2.5-flash-image@us-west1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@us-west1"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@us-west1"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@us-west1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-image@us-west4",
   "model_name": "gemini-2.5-flash-image@us-west4",
   "display_name": "vertex/gemini-2.5-flash-image@us-west4",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-image@us-west4"
    }
   ],
   "released_at": "2025-09-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-image@us-west4"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-image@us-west4"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite",
   "model_name": "gemini-2.5-flash-lite",
   "display_name": "Gemini 2.5 Flash-Lite",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02499999"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "1"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+litellm+helicone-registry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02499999"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "1"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "europe-west9",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "gemini-2-5-flash-lite"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09999999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39999999999999997"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.024999999999999998"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.09999999999999999"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0000001"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite"
    }
   ],
   "intro": "Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents",
   "released_at": "2025-06-17",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash-lite",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 512
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite",
   "model_type": "deep_thinking",
   "rate_limits": {
    "rpm": 15,
    "tpm": 250000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "deprecated": true,
   "aliases": [
    "gemini-2-5-flash-lite",
    "google/gemini-2.5-flash-lite",
    "vertex/gemini-2.5-flash-lite"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.5 Flash-Lite 是 Google 最小、性价比最高的模型，适用于大规模使用场景。",
    "zh-TW": "Gemini 2.5 Flash-Lite 是 Google 體積最小、性價比最高的模型，專為大規模應用而設計。",
    "ja-JP": "Gemini 2.5 Flash-Lite は、Google による最小かつ最もコストパフォーマンスに優れたモデルで、大規模利用に適しています。",
    "ru-RU": "Gemini 2.5 Flash-Lite — самая компактная и экономичная модель от Google, предназначенная для масштабного использования."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-gt-128k",
   "model_name": "gemini-2.5-flash-lite-gt-128k",
   "display_name": "gemini-2.5-flash-lite-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-lite-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-lte-128k",
   "model_name": "gemini-2.5-flash-lite-lte-128k",
   "display_name": "gemini-2.5-flash-lite-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-lite-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-nothink",
   "model_name": "gemini-2.5-flash-lite-nothink",
   "display_name": "gemini-2.5-flash-lite-nothink",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    }
   ],
   "max_input_tokens": 1048576,
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-lite-nothink"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-preview-06-17",
   "model_name": "gemini-2.5-flash-lite-preview-06-17",
   "display_name": "gemini-2.5-flash-lite-preview-06-17",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "0.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "docs_url": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2025-11-18",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "rate_limits": {
    "rpm": 15,
    "tpm": 250000
   },
   "released_at": "2025-06-17",
   "knowledge_cutoff": "2025-01",
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash-lite",
   "intro": "Low-latency Gemini model for high-volume multimodal and agent workloads",
   "intro_i18n": {
    "zh-CN": "Gemini 2.5 Flash-Lite Preview 是 Google 最小、性价比最高的模型，适用于大规模使用场景。",
    "zh-TW": "Gemini 2.5 Flash-Lite Preview 是 Google 體積最小、性價比最高的模型，專為大規模應用而設計。",
    "ja-JP": "Gemini 2.5 Flash-Lite Preview は、Google による最小かつ最もコストパフォーマンスに優れたモデルで、大規模利用に適しています。",
    "ru-RU": "Gemini 2.5 Flash-Lite Preview — самая компактная и экономичная модель от Google, предназначенная для масштабного использования."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-preview-06-17-gt-128k",
   "model_name": "gemini-2.5-flash-lite-preview-06-17-gt-128k",
   "display_name": "gemini-2.5-flash-lite-preview-06-17-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-lite-preview-06-17-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-preview-06-17-lte-128k",
   "model_name": "gemini-2.5-flash-lite-preview-06-17-lte-128k",
   "display_name": "gemini-2.5-flash-lite-preview-06-17-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-lite-preview-06-17-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-preview-09-2025",
   "model_name": "gemini-2.5-flash-lite-preview-09-2025",
   "display_name": "gemini-2.5-flash-lite-preview-09-2025",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite-preview-09-2025",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "gemini-2-5-flash-lite-preview-09-2025"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite-preview-09-2025"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite-preview-09-2025"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0000001"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite-preview-09-2025"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-lite-preview-09-2025"
    }
   ],
   "docs_url": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "rate_limits": {
    "rpm": 15,
    "tpm": 250000
   },
   "modalities": {
    "input": [
     "audio",
     "doc",
     "image",
     "pdf"
    ],
    "output": []
   },
   "released_at": "2025-09-25",
   "knowledge_cutoff": "2025-01",
   "family": "gemini-flash-lite",
   "intro": "Low-latency Gemini model for high-volume multimodal and agent workloads",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 512
   },
   "deprecated": true,
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "aliases": [
    "gemini-2-5-flash-lite-preview-09-2025",
    "google/gemini-2.5-flash-lite-preview-09-2025"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-preview-09-2025-gt-128k",
   "model_name": "gemini-2.5-flash-lite-preview-09-2025-gt-128k",
   "display_name": "gemini-2.5-flash-lite-preview-09-2025-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-lite-preview-09-2025-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-preview-09-2025-lte-128k",
   "model_name": "gemini-2.5-flash-lite-preview-09-2025-lte-128k",
   "display_name": "gemini-2.5-flash-lite-preview-09-2025-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-lite-preview-09-2025-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-preview-09-2025-nothink",
   "model_name": "gemini-2.5-flash-lite-preview-09-2025-nothink",
   "display_name": "gemini-2.5-flash-lite-preview-09-2025-nothink",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    }
   ],
   "max_input_tokens": 1048576,
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-lite-preview-09-2025-nothink"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-preview-09-2025-thinking",
   "model_name": "gemini-2.5-flash-lite-preview-09-2025-thinking",
   "display_name": "Gemini 2.5 Flash Lite Preview (09/2025) – Thinking",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-09-25",
   "max_input_tokens": 1048756,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Flash Lite Preview (09/2025) – Thinking"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite-preview-tts",
   "model_name": "gemini-2.5-flash-lite-preview-tts",
   "display_name": "gemini-2.5-flash-lite-preview-tts",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-lite-preview-tts"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite@europe-central2",
   "model_name": "gemini-2.5-flash-lite@europe-central2",
   "display_name": "vertex/gemini-2.5-flash-lite@europe-central2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-lite@europe-central2"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-lite@europe-central2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-lite@europe-central2"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite@europe-north1",
   "model_name": "gemini-2.5-flash-lite@europe-north1",
   "display_name": "vertex/gemini-2.5-flash-lite@europe-north1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-lite@europe-north1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-lite@europe-north1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-lite@europe-north1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite@europe-west1",
   "model_name": "gemini-2.5-flash-lite@europe-west1",
   "display_name": "vertex/gemini-2.5-flash-lite@europe-west1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-lite@europe-west1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-lite@europe-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-lite@europe-west1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite@europe-west4",
   "model_name": "gemini-2.5-flash-lite@europe-west4",
   "display_name": "vertex/gemini-2.5-flash-lite@europe-west4",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-lite@europe-west4"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-lite@europe-west4"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-lite@europe-west4"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite@europe-west8",
   "model_name": "gemini-2.5-flash-lite@europe-west8",
   "display_name": "vertex/gemini-2.5-flash-lite@europe-west8",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-lite@europe-west8"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-lite@europe-west8"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-lite@europe-west8"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite@us-central1",
   "model_name": "gemini-2.5-flash-lite@us-central1",
   "display_name": "vertex/gemini-2.5-flash-lite@us-central1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-lite@us-central1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-lite@us-central1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-lite@us-central1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite@us-east1",
   "model_name": "gemini-2.5-flash-lite@us-east1",
   "display_name": "vertex/gemini-2.5-flash-lite@us-east1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-lite@us-east1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-lite@us-east1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-lite@us-east1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite@us-east5",
   "model_name": "gemini-2.5-flash-lite@us-east5",
   "display_name": "vertex/gemini-2.5-flash-lite@us-east5",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-lite@us-east5"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-lite@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-lite@us-east5"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite@us-south1",
   "model_name": "gemini-2.5-flash-lite@us-south1",
   "display_name": "vertex/gemini-2.5-flash-lite@us-south1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-lite@us-south1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-lite@us-south1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-lite@us-south1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lite@us-west1",
   "model_name": "gemini-2.5-flash-lite@us-west1",
   "display_name": "vertex/gemini-2.5-flash-lite@us-west1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18333"
      }
     },
     "provider_model_id": "vertex/gemini-2.5-flash-lite@us-west1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-2.5-flash-lite@us-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-2.5-flash-lite@us-west1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-lte-128k",
   "model_name": "gemini-2.5-flash-lte-128k",
   "display_name": "gemini-2.5-flash-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-native-audio-latest",
   "model_name": "gemini-2.5-flash-native-audio-latest",
   "display_name": "gemini-2.5-flash-native-audio-latest",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    }
   ],
   "docs_url": "https://ai.google.dev/pricing",
   "max_input_tokens": 1048576,
   "max_output_tokens": 8192,
   "model_type": "realtime_omni",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true
   },
   "rate_limits": {
    "rpm": 10,
    "tpm": 250000
   },
   "modalities": {
    "input": [
     "text",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-native-audio-preview-09-2025",
   "model_name": "gemini-2.5-flash-native-audio-preview-09-2025",
   "display_name": "gemini-2.5-flash-native-audio-preview-09-2025",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    }
   ],
   "docs_url": "https://ai.google.dev/pricing",
   "max_input_tokens": 1048576,
   "max_output_tokens": 8192,
   "model_type": "realtime_omni",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true
   },
   "rate_limits": {
    "rpm": 10,
    "tpm": 250000
   },
   "modalities": {
    "input": [
     "text",
     "audio",
     "video",
     "image"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-native-audio-preview-12-2025",
   "model_name": "gemini-2.5-flash-native-audio-preview-12-2025",
   "display_name": "gemini-2.5-flash-native-audio-preview-12-2025",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    }
   ],
   "docs_url": "https://ai.google.dev/pricing",
   "max_input_tokens": 1048576,
   "max_output_tokens": 8192,
   "model_type": "realtime_omni",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "pdf_input": true
   },
   "rate_limits": {
    "rpm": 10,
    "tpm": 250000
   },
   "modalities": {
    "input": [
     "text",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "released_at": "2025-09-01",
   "knowledge_cutoff": "2025-01",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-nothinking",
   "model_name": "gemini-2.5-flash-nothinking",
   "display_name": "Gemini 2.5 Flash (No Thinking)",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-06-05",
   "max_input_tokens": 1048756,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Flash (No Thinking)"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-04-17-gt-128k",
   "model_name": "gemini-2.5-flash-preview-04-17-gt-128k",
   "display_name": "gemini-2.5-flash-preview-04-17-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview-04-17-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-04-17-lte-128k",
   "model_name": "gemini-2.5-flash-preview-04-17-lte-128k",
   "display_name": "gemini-2.5-flash-preview-04-17-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview-04-17-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-04-17:thinking",
   "model_name": "gemini-2.5-flash-preview-04-17:thinking",
   "display_name": "Gemini 2.5 Flash Preview 04-17",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey+llmdb",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "gemini-2.5-flash-preview-04-17",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "3.6",
        "completion": "7.5",
        "cache_read": "1.666667"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1",
        "completion": "2.083333"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "gemini-2.5-flash-preview-04-17"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "gemini-2.5-flash-preview-04-17"
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "released_at": "2025-04-17",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "gemini-flash",
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-2.5-flash-preview-04-17"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.5 Flash Preview 是 Google 功能最全、性价比最高的模型。",
    "zh-TW": "Gemini 2.5 Flash Preview 是 Google 功能最完整、性價比最高的模型。",
    "ja-JP": "Gemini 2.5 Flash Preview は、Google によるフル機能を備えた最もコスト効率の高いモデルです。",
    "ru-RU": "Gemini 2.5 Flash Preview — самая выгодная модель от Google с полным набором возможностей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Flash Preview 04-17"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-05-20-gt-128k",
   "model_name": "gemini-2.5-flash-preview-05-20-gt-128k",
   "display_name": "gemini-2.5-flash-preview-05-20-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview-05-20-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-05-20-lte-128k",
   "model_name": "gemini-2.5-flash-preview-05-20-lte-128k",
   "display_name": "gemini-2.5-flash-preview-05-20-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview-05-20-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-05-20-nothink",
   "model_name": "gemini-2.5-flash-preview-05-20-nothink",
   "display_name": "gemini-2.5-flash-preview-05-20-nothink",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.499"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    }
   ],
   "max_input_tokens": 1048576,
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview-05-20-nothink"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-05-20-search",
   "model_name": "gemini-2.5-flash-preview-05-20-search",
   "display_name": "gemini-2.5-flash-preview-05-20-search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.499"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    }
   ],
   "max_input_tokens": 1048576,
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview-05-20-search"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-05-20:thinking",
   "model_name": "gemini-2.5-flash-preview-05-20:thinking",
   "display_name": "Gemini 2.5 Flash Preview 05-20",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "llmdb",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      }
     },
     "provider_model_id": "gemini-2.5-flash-preview-05-20"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey+llmdb",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "gemini-2.5-flash-preview-05-20",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "3.6",
        "completion": "7.5",
        "cache_read": "1.666667"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1",
        "completion": "2.083333"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.135"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.15"
      }
     },
     "provider_model_id": "gemini-2.5-flash-preview-05-20"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "gemini-2.5-flash-preview-05-20"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2333"
      }
     }
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "released_at": "2025-05-20",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "gemini-flash",
   "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-2.5-flash-preview-05-20"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Flash Preview 05-20"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-09-2025",
   "model_name": "gemini-2.5-flash-preview-09-2025",
   "display_name": "gemini-2.5-flash-preview-09-2025",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.383"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "image_output": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "image_output": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "0.666667"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "image_output": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-preview-09-2025",
     "region": "global"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "gemini-2-5-flash-preview-09-2025"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.499"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-preview-09-2025"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.383"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-preview-09-2025"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.383"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-preview-09-2025"
    }
   ],
   "docs_url": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "rate_limits": {
    "rpm": 15,
    "tpm": 250000
   },
   "modalities": {
    "input": [
     "doc",
     "image",
     "pdf"
    ],
    "output": []
   },
   "released_at": "2025-09-25",
   "knowledge_cutoff": "2025-01",
   "family": "gemini-flash",
   "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
   "aliases": [
    "gemini-2-5-flash-preview-09-2025",
    "google/gemini-2.5-flash-preview-09-2025"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-09-2025-gt-128k",
   "model_name": "gemini-2.5-flash-preview-09-2025-gt-128k",
   "display_name": "gemini-2.5-flash-preview-09-2025-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview-09-2025-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-09-2025-lte-128k",
   "model_name": "gemini-2.5-flash-preview-09-2025-lte-128k",
   "display_name": "gemini-2.5-flash-preview-09-2025-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview-09-2025-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-09-2025-thinking",
   "model_name": "gemini-2.5-flash-preview-09-2025-thinking",
   "display_name": "Gemini 2.5 Flash Preview (09/2025) – Thinking",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-09-25",
   "max_input_tokens": 1048756,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Flash Preview (09/2025) – Thinking"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-tts",
   "model_name": "gemini-2.5-flash-preview-tts",
   "display_name": "Gemini 2.5 Flash Preview TTS",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-preview-tts"
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-05-01",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 8192,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "gemini-flash",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "audio_output": true,
    "structured_output": true
   },
   "model_type": "speech_synthesis",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-2.5-flash-preview-tts"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-tts-gt-128k",
   "model_name": "gemini-2.5-flash-preview-tts-gt-128k",
   "display_name": "gemini-2.5-flash-preview-tts-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview-tts-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview-tts-lte-128k",
   "model_name": "gemini-2.5-flash-preview-tts-lte-128k",
   "display_name": "gemini-2.5-flash-preview-tts-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview-tts-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-preview:thinking",
   "model_name": "gemini-2.5-flash-preview:thinking",
   "display_name": "gemini-2.5-flash-preview:thinking",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "gemini-2.5-flash-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2333"
      }
     },
     "provider_model_id": "gemini-2.5-flash-preview"
    }
   ],
   "intro": "Gemini 2.5 Flash May 20th Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-2.5-flash-preview",
    "google/gemini-2.5-flash-preview",
    "google/gemini-2.5-flash-preview:thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-flash-preview:thinking"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash-tts",
   "model_name": "gemini-2.5-flash-tts",
   "display_name": "Gemini 2.5 Flash TTS",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "northamerica-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-flash-tts",
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-09-30",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "gemini-flash",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "audio_output": true
   },
   "model_type": "speech_synthesis",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-2.5-flash-tts"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Flash TTS"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash@europe-central2",
   "model_name": "gemini-2.5-flash@europe-central2",
   "display_name": "coding/gemini-2.5-flash@europe-central2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "coding/gemini-2.5-flash@europe-central2"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-flash@europe-central2",
    "vertex/gemini-2.5-flash@europe-central2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-flash@europe-central2"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash@europe-north1",
   "model_name": "gemini-2.5-flash@europe-north1",
   "display_name": "coding/gemini-2.5-flash@europe-north1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "coding/gemini-2.5-flash@europe-north1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-flash@europe-north1",
    "vertex/gemini-2.5-flash@europe-north1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-flash@europe-north1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash@europe-west1",
   "model_name": "gemini-2.5-flash@europe-west1",
   "display_name": "coding/gemini-2.5-flash@europe-west1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "coding/gemini-2.5-flash@europe-west1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-flash@europe-west1",
    "vertex/gemini-2.5-flash@europe-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-flash@europe-west1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash@europe-west4",
   "model_name": "gemini-2.5-flash@europe-west4",
   "display_name": "coding/gemini-2.5-flash@europe-west4",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "coding/gemini-2.5-flash@europe-west4"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-flash@europe-west4",
    "vertex/gemini-2.5-flash@europe-west4"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-flash@europe-west4"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash@europe-west8",
   "model_name": "gemini-2.5-flash@europe-west8",
   "display_name": "coding/gemini-2.5-flash@europe-west8",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "coding/gemini-2.5-flash@europe-west8"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-flash@europe-west8",
    "vertex/gemini-2.5-flash@europe-west8"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-flash@europe-west8"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash@us-central1",
   "model_name": "gemini-2.5-flash@us-central1",
   "display_name": "coding/gemini-2.5-flash@us-central1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "coding/gemini-2.5-flash@us-central1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-flash@us-central1",
    "vertex/gemini-2.5-flash@us-central1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-flash@us-central1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash@us-east1",
   "model_name": "gemini-2.5-flash@us-east1",
   "display_name": "coding/gemini-2.5-flash@us-east1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "coding/gemini-2.5-flash@us-east1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-flash@us-east1",
    "vertex/gemini-2.5-flash@us-east1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-flash@us-east1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash@us-east5",
   "model_name": "gemini-2.5-flash@us-east5",
   "display_name": "coding/gemini-2.5-flash@us-east5",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "coding/gemini-2.5-flash@us-east5"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-flash@us-east5",
    "vertex/gemini-2.5-flash@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-flash@us-east5"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash@us-south1",
   "model_name": "gemini-2.5-flash@us-south1",
   "display_name": "coding/gemini-2.5-flash@us-south1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "coding/gemini-2.5-flash@us-south1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-flash@us-south1",
    "vertex/gemini-2.5-flash@us-south1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-flash@us-south1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-flash@us-west1",
   "model_name": "gemini-2.5-flash@us-west1",
   "display_name": "coding/gemini-2.5-flash@us-west1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "coding/gemini-2.5-flash@us-west1"
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-flash@us-west1",
    "vertex/gemini-2.5-flash@us-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-flash@us-west1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro",
   "model_name": "gemini-2.5-pro",
   "display_name": "Gemini 2.5 Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "4.5"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "gemini-2-5-pro",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.4"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200000000K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "5",
        "prompt": "2",
        "image_input": "2",
        "video_input": "2",
        "audio_input": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+litellm+helicone-registry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "4.5"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.84"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "0.2",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "asia-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "europe-west9",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "northamerica-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gemini-2-5-pro"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     }
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.654"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.024"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.217"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gemini-2-5-pro",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00000125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "cache_write": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.087"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "0.806452"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "deepinfra/google/gemini-2.5-pro"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro"
    }
   ],
   "intro": "Google's proven reasoning model for coding, math, and multimodal analysis",
   "released_at": "2025-06-17",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-pro",
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 128
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "stream": true
   },
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "model_type": "deep_thinking",
   "rate_limits": {
    "rpm": 2000,
    "tpm": 800000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 25.8,
    "coding_index": 33.3,
    "agentic_index": 7.1
   },
   "aliases": [
    "coding/gemini-2.5-pro",
    "deepinfra/google/gemini-2.5-pro",
    "gemini-2-5-pro",
    "google/gemini-2.5-pro",
    "vertex/gemini-2.5-pro"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.5 Pro 是 Google 的旗舰推理模型，支持长上下文，适用于复杂任务。",
    "zh-TW": "Gemini 2.5 Pro 是 Google 的旗艦推理模型，支援長上下文，適用於處理複雜任務。",
    "ja-JP": "Gemini 2.5 Pro は、Google による最も高度な推論モデルで、コード、数学、STEM 問題に対する推論や、大規模なデータセット、コードベース、文書の分析に対応します。",
    "ru-RU": "Gemini 2.5 Pro — флагманская модель рассуждения от Google с поддержкой длинного контекста для сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-exp-03-25",
   "model_name": "gemini-2.5-pro-exp-03-25",
   "display_name": "Gemini 2.5 Pro Experimental 0325",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-03-25",
   "max_input_tokens": 1048756,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Pro Experimental 0325"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-gt-128k",
   "model_name": "gemini-2.5-pro-gt-128k",
   "display_name": "gemini-2.5-pro-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-lte-128k",
   "model_name": "gemini-2.5-pro-lte-128k",
   "display_name": "gemini-2.5-pro-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview",
   "model_name": "gemini-2.5-pro-preview",
   "display_name": "Google: Gemini 2.5 Pro Preview 06-05",
   "vendor": "google",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00000125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "cache_write": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
   "released_at": "2025-06-05",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "audio",
     "image",
     "pdf",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-01",
   "family": "gemini",
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 128
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-2.5-pro-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.5 Pro Preview 是 Google 最先进的思考模型，擅长处理代码、数学、STEM 等复杂问题，并能分析大规模数据集、代码库和长文档。",
    "zh-TW": "Gemini 2.5 Pro Preview 是 Google 最先進的思考模型，適用於程式碼、數學與 STEM 領域的複雜推理，並能分析大型資料集、程式碼庫與長文件。",
    "ja-JP": "Gemini 2.5 Pro Previewは、コード、数学、STEM分野の複雑な問題に対する推論や、大規模データセット、コードベース、長文ドキュメントの分析に最適なGoogleの最先端思考モデルです。",
    "ru-RU": "Gemini 2.5 Pro Preview — самая продвинутая модель Google с режимом мышления, предназначенная для решения сложных задач в области программирования, математики и STEM, а также для анализа больших наборов данных, кодовых баз и документов с длинным контекстом."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Google: Gemini 2.5 Pro Preview 06-05"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-03-25",
   "model_name": "gemini-2.5-pro-preview-03-25",
   "display_name": "Gemini 2.5 Pro Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.769231"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "1.923077"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-preview-03-25"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-03-25",
   "max_input_tokens": 1048756,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2025-01",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-2.5-pro-preview-03-25"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.5 Pro Preview 是 Google 最先进的推理模型，能够处理代码、数学、STEM 问题，并分析大规模数据集、代码库和长文档。",
    "zh-TW": "Gemini 2.5 Pro Preview 是 Google 最先進的推理模型，能處理程式碼、數學與 STEM 問題，並分析大型資料集、程式碼庫與長篇文件。",
    "ja-JP": "Gemini 2.5 Pro Preview は、Google による最も高度な推論モデルで、コード、数学、STEM 問題に対する推論や、大規模なデータセット、コードベース、文書の分析に対応します。",
    "ru-RU": "Gemini 2.5 Pro Preview — самая продвинутая модель рассуждения от Google, способная анализировать код, математику и задачи STEM, а также обрабатывать большие наборы данных, кодовые базы и документы с длинным контекстом."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Pro Preview"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-03-25-gt-128k",
   "model_name": "gemini-2.5-pro-preview-03-25-gt-128k",
   "display_name": "gemini-2.5-pro-preview-03-25-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-preview-03-25-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-03-25-lte-128k",
   "model_name": "gemini-2.5-pro-preview-03-25-lte-128k",
   "display_name": "gemini-2.5-pro-preview-03-25-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-preview-03-25-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-03-25-search",
   "model_name": "gemini-2.5-pro-preview-03-25-search",
   "display_name": "gemini-2.5-pro-preview-03-25-search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-preview-03-25-search"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-05-06",
   "model_name": "gemini-2.5-pro-preview-05-06",
   "display_name": "Gemini 2.5 Pro Preview 05-06",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey+llmdb",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.045"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.769231"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "1.923077"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-preview-05-06"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00000125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-preview-05-06",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "cache_write": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "released_at": "2025-05-06",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "gemini-pro",
   "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 128
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-2.5-pro-preview-05-06"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 2.5 Pro Preview 是 Google 最先进的推理模型，能够处理代码、数学、STEM 问题，并分析大规模数据集、代码库和长文档。",
    "zh-TW": "Gemini 2.5 Pro Preview 是 Google 最先進的推理模型，能處理程式碼、數學與 STEM 問題，並分析大型資料集、程式碼庫與長篇文件。",
    "ja-JP": "Gemini 2.5 Pro Preview は、Google による最も高度な推論モデルで、コード、数学、STEM 問題に対する推論や、大規模なデータセット、コードベース、文書の分析に対応します。",
    "ru-RU": "Gemini 2.5 Pro Preview — самая продвинутая модель рассуждения от Google, способная анализировать код, математику и задачи STEM, а также обрабатывать большие наборы данных, кодовые базы и документы с длинным контекстом."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Pro Preview 05-06"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-05-06-gt-128k",
   "model_name": "gemini-2.5-pro-preview-05-06-gt-128k",
   "display_name": "gemini-2.5-pro-preview-05-06-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-preview-05-06-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-05-06-lte-128k",
   "model_name": "gemini-2.5-pro-preview-05-06-lte-128k",
   "display_name": "gemini-2.5-pro-preview-05-06-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-preview-05-06-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-05-06-search",
   "model_name": "gemini-2.5-pro-preview-05-06-search",
   "display_name": "gemini-2.5-pro-preview-05-06-search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-preview-05-06-search"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-06-05",
   "model_name": "gemini-2.5-pro-preview-06-05",
   "display_name": "Gemini 2.5 Pro Preview 06-05",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-preview-06-05"
    }
   ],
   "released_at": "2025-06-05",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "gemini-pro",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-2.5-pro-preview-06-05"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Pro Preview 06-05"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-06-05-search",
   "model_name": "gemini-2.5-pro-preview-06-05-search",
   "display_name": "gemini-2.5-pro-preview-06-05-search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-preview-06-05-search"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-tts",
   "model_name": "gemini-2.5-pro-preview-tts",
   "display_name": "Gemini 2.5 Pro Preview TTS",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2.5",
        "completion": "0.75"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-preview-tts"
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-05-01",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 8192,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "gemini-flash",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_output": true,
    "structured_output": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview",
   "model_type": "speech_synthesis",
   "rate_limits": {
    "rpm": 10000,
    "tpm": 10000000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-2.5-pro-preview-tts"
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-tts-gt-128k",
   "model_name": "gemini-2.5-pro-preview-tts-gt-128k",
   "display_name": "gemini-2.5-pro-preview-tts-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-preview-tts-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-preview-tts-lte-128k",
   "model_name": "gemini-2.5-pro-preview-tts-lte-128k",
   "display_name": "gemini-2.5-pro-preview-tts-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-2.5-pro-preview-tts-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro-tts",
   "model_name": "gemini-2.5-pro-tts",
   "display_name": "Gemini 2.5 Pro TTS",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "asia-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "asia-east2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "asia-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "asia-northeast3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "asia-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "australia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "europe-west2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "europe-west3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "europe-west6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "europe-west9",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "me-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "me-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "me-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "northamerica-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "southamerica-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-2.5-pro-tts",
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-09-30",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "gemini-pro",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "audio_output": true
   },
   "model_type": "speech_synthesis",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-2.5-pro-tts"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 2.5 Pro TTS"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro@europe-central2",
   "model_name": "gemini-2.5-pro@europe-central2",
   "display_name": "coding/gemini-2.5-pro@europe-central2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "coding/gemini-2.5-pro@europe-central2"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-pro@europe-central2",
    "vertex/gemini-2.5-pro@europe-central2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-pro@europe-central2"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro@europe-north1",
   "model_name": "gemini-2.5-pro@europe-north1",
   "display_name": "coding/gemini-2.5-pro@europe-north1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "coding/gemini-2.5-pro@europe-north1"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-pro@europe-north1",
    "vertex/gemini-2.5-pro@europe-north1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-pro@europe-north1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro@europe-west1",
   "model_name": "gemini-2.5-pro@europe-west1",
   "display_name": "coding/gemini-2.5-pro@europe-west1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "coding/gemini-2.5-pro@europe-west1"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-pro@europe-west1",
    "vertex/gemini-2.5-pro@europe-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-pro@europe-west1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro@europe-west4",
   "model_name": "gemini-2.5-pro@europe-west4",
   "display_name": "coding/gemini-2.5-pro@europe-west4",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "coding/gemini-2.5-pro@europe-west4"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-pro@europe-west4",
    "vertex/gemini-2.5-pro@europe-west4"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-pro@europe-west4"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro@europe-west8",
   "model_name": "gemini-2.5-pro@europe-west8",
   "display_name": "coding/gemini-2.5-pro@europe-west8",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "coding/gemini-2.5-pro@europe-west8"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-pro@europe-west8",
    "vertex/gemini-2.5-pro@europe-west8"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-pro@europe-west8"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro@us-central1",
   "model_name": "gemini-2.5-pro@us-central1",
   "display_name": "coding/gemini-2.5-pro@us-central1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "coding/gemini-2.5-pro@us-central1"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-pro@us-central1",
    "vertex/gemini-2.5-pro@us-central1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-pro@us-central1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro@us-east1",
   "model_name": "gemini-2.5-pro@us-east1",
   "display_name": "coding/gemini-2.5-pro@us-east1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "coding/gemini-2.5-pro@us-east1"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-pro@us-east1",
    "vertex/gemini-2.5-pro@us-east1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-pro@us-east1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro@us-east5",
   "model_name": "gemini-2.5-pro@us-east5",
   "display_name": "coding/gemini-2.5-pro@us-east5",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "coding/gemini-2.5-pro@us-east5"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-pro@us-east5",
    "vertex/gemini-2.5-pro@us-east5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-pro@us-east5"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro@us-south1",
   "model_name": "gemini-2.5-pro@us-south1",
   "display_name": "coding/gemini-2.5-pro@us-south1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "coding/gemini-2.5-pro@us-south1"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-pro@us-south1",
    "vertex/gemini-2.5-pro@us-south1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-pro@us-south1"
    }
   ]
  },
  {
   "slug": "google/gemini-2.5-pro@us-west1",
   "model_name": "gemini-2.5-pro@us-west1",
   "display_name": "coding/gemini-2.5-pro@us-west1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.375"
      }
     },
     "provider_model_id": "coding/gemini-2.5-pro@us-west1"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "coding/gemini-2.5-pro@us-west1",
    "vertex/gemini-2.5-pro@us-west1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding/gemini-2.5-pro@us-west1"
    }
   ]
  },
  {
   "slug": "google/gemini-3-1-pro",
   "model_name": "gemini-3-1-pro",
   "display_name": "Gemini 3.1 Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "gemini-3.1-pro"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "gemini-3.1-pro",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "gemini-3.1-pro"
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "gemini-3.1-pro"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro"
    }
   ],
   "max_input_tokens": 1000000,
   "family": "Gemini",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
   "released_at": "2026-02-19",
   "knowledge_cutoff": "2025-01",
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemini-3.1-pro",
    "google/gemini-3.1-pro"
   ],
   "intro_i18n": {
    "zh-CN": "Google 的 Gemini 3.1 Pro —— 高端多模态模型，具备 100 万上下文窗口。",
    "zh-TW": "Google Gemini 3.1 Pro —— 旗艦多模態模型，具備 100 萬上下文。",
    "ja-JP": "Gemini 3.1 Pro by Google — 1Mコンテキストウィンドウを備えたプレミアムマルチモーダルモデル。",
    "ru-RU": "Gemini 3.1 Pro от Google — премиальная мультимодальная модель с контекстом 1M."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.1 Pro"
    }
   ]
  },
  {
   "slug": "google/gemini-3-flash",
   "model_name": "gemini-3-flash",
   "display_name": "Gemini 3 Flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.37"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "google/gemini-3-flash"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3-flash",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 1000000,
   "family": "Gemini",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "structured_output": true,
    "web_search": true,
    "stream": true
   },
   "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
   "released_at": "2025-12-17",
   "max_output_tokens": 65000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-3-flash"
   ],
   "intro_i18n": {
    "zh-CN": "Google 的 Gemini 3 Flash —— 超高速模型，支持多模态输入。",
    "zh-TW": "Google Gemini 3 Flash —— 超高速模型，支援多模態輸入。",
    "ja-JP": "Gemini 3 Flash by Google — 超高速モデルでマルチモーダル入力をサポートします。",
    "ru-RU": "Gemini 3 Flash от Google — ультрабыстрая модель с поддержкой мультимодальных входов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3 Flash"
    }
   ]
  },
  {
   "slug": "google/gemini-3-flash-preview",
   "model_name": "gemini-3-flash-preview",
   "display_name": "Gemini 3 Flash Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+litellm+helicone-registry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "pa/gemini-3-flash-preview"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0000005"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333333333333334"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "qihang-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview"
    }
   ],
   "intro": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs",
   "released_at": "2025-12-17",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/pricing/gemini-3",
   "model_type": "deep_thinking",
   "rate_limits": {
    "rpm": 2000,
    "tpm": 800000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 256
   },
   "aliases": [
    "google/gemini-3-flash-preview",
    "pa/gemini-3-flash-preview",
    "vertex/gemini-3-flash-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 3 Flash 是一款以速度为核心的智能模型，融合前沿智能与卓越的搜索能力。",
    "zh-TW": "Gemini 3 Flash 是一款以速度為核心的智慧模型，結合尖端智能與卓越的搜尋基礎能力。",
    "ja-JP": "Gemini 3 Flash は、最先端の知能と優れた検索基盤を融合し、スピードに特化した最もスマートなモデルです。",
    "ru-RU": "Gemini 3 Flash — самая быстрая и интеллектуальная модель, сочетающая передовые ИИ-возможности с точной привязкой к поисковым данным."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3-flash-preview-gt-128k",
   "model_name": "gemini-3-flash-preview-gt-128k",
   "display_name": "gemini-3-flash-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-flash-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3-flash-preview-lte-128k",
   "model_name": "gemini-3-flash-preview-lte-128k",
   "display_name": "gemini-3-flash-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-flash-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3-flash-preview-search",
   "model_name": "gemini-3-flash-preview-search",
   "display_name": "gemini-3-flash-preview-search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "max_input_tokens": 1048576,
   "modalities": {
    "input": [
     "audio",
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-flash-preview-search"
    }
   ]
  },
  {
   "slug": "google/gemini-3-flash-preview-thinking",
   "model_name": "gemini-3-flash-preview-thinking",
   "display_name": "Gemini 3 Flash Thinking",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "google/gemini-3-flash-preview-thinking"
    }
   ],
   "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
   "released_at": "2025-12-17",
   "max_input_tokens": 1048756,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash",
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "audio_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-3-flash-preview-thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3 Flash Thinking"
    }
   ]
  },
  {
   "slug": "google/gemini-3-flash-preview:flex",
   "model_name": "gemini-3-flash-preview:flex",
   "display_name": "vertex/gemini-3-flash-preview:flex",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "vertex/gemini-3-flash-preview:flex"
    }
   ],
   "released_at": "2025-12-18",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-3-flash-preview:flex"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-3-flash-preview:flex"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro",
   "model_name": "gemini-3-pro",
   "display_name": "Gemini 3 Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     }
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-3-pro"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "google/gemini-3-pro"
    }
   ],
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 1000000,
   "family": "Gemini",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "intro": "Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts",
   "released_at": "2025-11-18",
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "deprecated": true,
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-3-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3 Pro"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-image",
   "model_name": "gemini-3-pro-image",
   "display_name": "gemini-3-pro-image",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.134"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0011"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.134"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0011"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0011"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000002"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.134"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.1344"
      },
      "image_output_2048px": {
       "unit": "per_image",
       "price": "0.1344"
      },
      "image_output_4096px": {
       "unit": "per_image",
       "price": "0.24"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.1344"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image",
     "tracks": [
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image",
   "max_input_tokens": 65536,
   "max_output_tokens": 32768,
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "rate_limits": {
    "rpm": 1000,
    "tpm": 4000000
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "released_at": "2025-11-01",
   "knowledge_cutoff": "2025-01",
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "family": "gemini-pro",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "google/gemini-3-pro-image"
   ],
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-image-gt-128k",
   "model_name": "gemini-3-pro-image-gt-128k",
   "display_name": "gemini-3-pro-image-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000011"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-pro-image-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-image-lte-128k",
   "model_name": "gemini-3-pro-image-lte-128k",
   "display_name": "gemini-3-pro-image-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000011"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-pro-image-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-image-preview",
   "model_name": "gemini-3-pro-image-preview",
   "display_name": "Nano Banana Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.134"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0011"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.05"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "0.15"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.134"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0011"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.00112"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image-preview",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image-preview"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image-preview"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000002"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "126.6"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2.11",
        "completion": "1.5825",
        "image_output": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "vertex/gemini-3-pro-image-preview"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image-preview"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "google/gemini-3-pro-image-preview"
    }
   ],
   "intro": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits",
   "released_at": "2025-11-20",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "gemini-pro",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "model_type": "image_generation",
   "rate_limits": {
    "rpm": 1000,
    "tpm": 4000000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "google/gemini-3-pro-image-preview",
    "vertex/gemini-3-pro-image-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 3 Pro Image（Nano Banana Pro）是 Google 的图像生成模型，同时支持多模态对话。",
    "zh-TW": "Gemini 3 Pro Image (Nano Banana Pro) 是 Google 的影像生成模型，亦支持多模態對話。",
    "ja-JP": "Gemini 3 Pro Image（Nano Banana Pro）は、Googleの画像生成モデルで、マルチモーダル対話もサポートします。",
    "ru-RU": "Gemini 3 Pro Image (Nano Banana Pro) — это модель генерации изображений от Google, которая также поддерживает мультимодальный диалог."
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-image-preview-gt-128k",
   "model_name": "gemini-3-pro-image-preview-gt-128k",
   "display_name": "gemini-3-pro-image-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000011"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-pro-image-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-image-preview-lte-128k",
   "model_name": "gemini-3-pro-image-preview-lte-128k",
   "display_name": "gemini-3-pro-image-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000011"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-pro-image-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-image-preview:image",
   "model_name": "gemini-3-pro-image-preview:image",
   "display_name": "Nano Banana Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    }
   ],
   "released_at": "2025-11-18",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 3 Pro Image（Nano Banana Pro）是 Google 的图像生成模型，同时支持多模态聊天。",
    "zh-TW": "Gemini 3 Pro Image（Nano Banana Pro）是 Google 的圖像生成模型，並支持多模態聊天。",
    "ja-JP": "Gemini 3 Pro Image（Nano Banana Pro）は、Googleの画像生成モデルで、マルチモーダルチャットもサポートしています。",
    "ru-RU": "Gemini 3 Pro Image (Nano Banana Pro) — модель генерации изображений от Google, также поддерживающая мультимодальный чат."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nano Banana Pro"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-preview",
   "model_name": "gemini-3-pro-preview",
   "display_name": "Gemini 3 Pro Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+llmdb+pricetoken+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "4.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+helicone-registry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "4.5"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.014"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "image_output": "0.5",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "image_output": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "image_output": "0.5",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "cache_write": "1.25",
        "prompt": "2",
        "completion": "1.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "image_output": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "asia-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "asia-east2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "asia-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "asia-northeast3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "asia-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "australia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "europe-west2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "europe-west3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "europe-west6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "europe-west9",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "me-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "me-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "me-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "northamerica-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "southamerica-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "tracks": [
      {
       "label": ">200000000K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "0.8",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19999999999999998"
      }
     },
     "provider_model_id": "pa/gemini-3-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.8"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "google/gemini-3-pro-preview"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "litellm+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3-pro-preview"
    },
    {
     "provider": "qihang-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.43"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "google/gemini-3-pro-preview"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3-pro-preview",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "tracks": [
      {
       "label": ">200000000K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "google/gemini-3-pro-preview"
    }
   ],
   "intro": "Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts",
   "released_at": "2025-11-18",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-pro",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "stream": true
   },
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "model_type": "image_generation",
   "deprecation_date": "2026-03-09",
   "rate_limits": {
    "rpm": 2000,
    "tpm": 800000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "aliases": [
    "google/gemini-3-pro-preview",
    "pa/gemini-3-pro-preview",
    "vertex/gemini-3-pro-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 3 Pro 是 Google 最强大的智能体与编程模型，在最先进推理基础上提供更丰富的视觉效果与更深入的交互体验。",
    "zh-TW": "Gemini 3 Pro 是 Google 最強大的智能代理與情境編碼模型，具備頂尖推理能力、豐富視覺表現與深度互動。",
    "ja-JP": "Gemini 3 Pro は、Google による最も強力なエージェントおよびバイブコーディングモデルで、最先端の推論に加え、より豊かなビジュアルと深い対話を実現します。",
    "ru-RU": "Gemini 3 Pro — самая мощная агентная модель от Google с поддержкой визуализации и глубокой интерактивности, основанная на передовых возможностях рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-preview-02-05",
   "model_name": "gemini-3-pro-preview-02-05",
   "display_name": "gemini-3-pro-preview-02-05",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "0.08"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "0.088889"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-pro-preview-02-05"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-preview-02-05-gt-128k",
   "model_name": "gemini-3-pro-preview-02-05-gt-128k",
   "display_name": "gemini-3-pro-preview-02-05-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-pro-preview-02-05-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-preview-02-05-lte-128k",
   "model_name": "gemini-3-pro-preview-02-05-lte-128k",
   "display_name": "gemini-3-pro-preview-02-05-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-pro-preview-02-05-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-preview-gt-128k",
   "model_name": "gemini-3-pro-preview-gt-128k",
   "display_name": "gemini-3-pro-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-pro-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-preview-lte-128k",
   "model_name": "gemini-3-pro-preview-lte-128k",
   "display_name": "gemini-3-pro-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3-pro-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3-pro-preview-search",
   "model_name": "gemini-3-pro-preview-search",
   "display_name": "Gemini 3 Pro Preview Search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2025-11-19",
   "knowledge_cutoff": "2025-11",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65000,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "gemini-pro",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3 Pro Preview Search"
    }
   ]
  },
  {
   "slug": "google/gemini-3.0-flash-preview",
   "model_name": "gemini-3.0-flash-preview",
   "display_name": "Gemini 3.0 Flash Preview",
   "vendor": "google",
   "pricing": [],
   "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
   "released_at": "2025-12-18",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.0 Flash Preview"
    }
   ]
  },
  {
   "slug": "google/gemini-3.0-pro-image-preview",
   "model_name": "gemini-3.0-pro-image-preview",
   "display_name": "Gemini 3.0 Pro Image Preview",
   "vendor": "google",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-11-20",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.0 Pro Image Preview"
    }
   ]
  },
  {
   "slug": "google/gemini-3.0-pro-preview",
   "model_name": "gemini-3.0-pro-preview",
   "display_name": "Gemini 3.0 Pro Preview",
   "vendor": "google",
   "pricing": [],
   "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
   "released_at": "2025-11-19",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "pdf",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.0 Pro Preview"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-image",
   "model_name": "gemini-3.1-flash-image",
   "display_name": "gemini-3.1-flash-image",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.045"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "gemini-3-1-flash-image",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.0672"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00056"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output_512px": {
       "unit": "per_image",
       "price": "0.045"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.067"
      },
      "image_output_2048px": {
       "unit": "per_image",
       "price": "0.101"
      },
      "image_output_4096px": {
       "unit": "per_image",
       "price": "0.151"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.067"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image"
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
   "max_input_tokens": 65536,
   "max_output_tokens": 32768,
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "rate_limits": {
    "rpm": 1000,
    "tpm": 4000000
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "Gemini",
   "released_at": "2026-02-01",
   "knowledge_cutoff": "2025-01",
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "gemini-3-1-flash-image",
    "google/gemini-3.1-flash-image"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-image-gt-128k",
   "model_name": "gemini-3.1-flash-image-gt-128k",
   "display_name": "gemini-3.1-flash-image-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-image-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-image-lte-128k",
   "model_name": "gemini-3.1-flash-image-lte-128k",
   "display_name": "gemini-3.1-flash-image-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-image-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-image-preview",
   "model_name": "gemini-3.1-flash-image-preview",
   "display_name": "Nano Banana 2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.045"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.025"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.0672"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00056"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image-preview",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image-preview"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image-preview"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image-preview"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image-preview"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image-preview"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output_512px": {
       "unit": "per_image",
       "price": "0.045"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.067"
      },
      "image_output_2048px": {
       "unit": "per_image",
       "price": "0.101"
      },
      "image_output_4096px": {
       "unit": "per_image",
       "price": "0.151"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.067"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-image-preview",
     "tracks": [
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-02-26",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "gemini-flash",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview",
   "model_type": "image_generation",
   "rate_limits": {
    "rpm": 1000,
    "tpm": 4000000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "deprecated": true,
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "google/gemini-3.1-flash-image-preview",
    "vertex/gemini-3.1-flash-image-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 3.1 Flash Image（Nano Banana 2）是 Google 最快的原生图像生成模型，支持思考、对话式图像生成和编辑。",
    "zh-TW": "Gemini 3.1 Flash Image (Nano Banana 2) 是 Google 最快的原生影像生成模型，支持思考、對話式影像生成與編輯。",
    "ja-JP": "Gemini 3.1 Flash Image（Nano Banana 2）は、Googleの最速のネイティブ画像生成モデルで、思考サポート、対話型画像生成および編集を提供します。",
    "ru-RU": "Gemini 3.1 Flash Image (Nano Banana 2) — это самая быстрая нативная модель генерации изображений от Google с поддержкой мышления, генерации и редактирования изображений в диалоговом режиме."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-image-preview-gt-128k",
   "model_name": "gemini-3.1-flash-image-preview-gt-128k",
   "display_name": "gemini-3.1-flash-image-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-image-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-image-preview-lte-128k",
   "model_name": "gemini-3.1-flash-image-preview-lte-128k",
   "display_name": "gemini-3.1-flash-image-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-image-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-image-preview:image",
   "model_name": "gemini-3.1-flash-image-preview:image",
   "display_name": "Nano Banana 2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "released_at": "2026-02-26",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemini 3.1 Flash Image（Nano Banana 2）是 Google 最快速的原生图像生成模型，支持思维能力、对话式图像生成和编辑功能。",
    "zh-TW": "Gemini 3.1 Flash Image（Nano Banana 2）是 Google 最快速的原生圖像生成模型，支持思維能力、對話式圖像生成和編輯。",
    "ja-JP": "Gemini 3.1 Flash Image（Nano Banana 2）は、Googleの最速のネイティブ画像生成モデルで、思考サポート、会話型画像生成、編集を可能にします。",
    "ru-RU": "Gemini 3.1 Flash Image (Nano Banana 2) — самая быстрая модель генерации изображений от Google с поддержкой размышлений, генерации и редактирования изображений в рамках диалога."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nano Banana 2"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite",
   "model_name": "gemini-3.1-flash-lite",
   "display_name": "Gemini 3.1 Flash Lite",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "gemini-3-1-flash-lite",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "cache_read": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1.98",
        "completion": "1.98",
        "cache_read": "1.98"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.55",
        "completion": "0.55",
        "cache_read": "0.55"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.055"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0275"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.65"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.055"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0275"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.65"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.244"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.464"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gemini-3-1-flash-lite"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00000025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "gemini-3-1-flash-lite"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      }
     },
     "provider_model_id": "vertex/gemini-3.1-flash-lite"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.416667"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite"
    }
   ],
   "intro": "Low-latency Gemini model for high-volume multimodal and agent workloads",
   "released_at": "2026-05-07",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash-lite",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite",
   "model_type": "deep_thinking",
   "rate_limits": {
    "rpm": 15,
    "tpm": 250000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "gemini-3-1-flash-lite",
    "google/gemini-3.1-flash-lite",
    "vertex/gemini-3.1-flash-lite"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 3.1 Flash-Lite 是谷歌最具成本效益的多模态模型，优化用于高容量代理任务、翻译和数据处理。",
    "zh-TW": "Gemini 3.1 Flash-Lite 是 Google 最具成本效益的多模態模型，專為高容量代理任務、翻譯和數據處理而優化。",
    "ja-JP": "Gemini 3.1 Flash-LiteはGoogleの最もコスト効率の高いマルチモーダルモデルで、大量のエージェントタスク、翻訳、データ処理に最適化されています。",
    "ru-RU": "Gemini 3.1 Flash-Lite — самая экономичная мультимодальная модель от Google, оптимизированная для задач с высоким объемом, перевода и обработки данных."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite-gt-128k",
   "model_name": "gemini-3.1-flash-lite-gt-128k",
   "display_name": "gemini-3.1-flash-lite-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-lite-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite-image",
   "model_name": "gemini-3.1-flash-lite-image",
   "display_name": "Nano Banana 2 Lite",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "image_output": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "image_output": "0.5",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-image",
     "region": "global"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-image"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-image"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-image"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-image"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.034"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.034"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-image"
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true,
    "image_output": true,
    "pdf_input": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "web_search": true,
    "audio_input": true
   },
   "released_at": "2026-06-01",
   "knowledge_cutoff": "2025-01",
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "family": "gemini",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "temperature",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-3.1-flash-lite-image"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 是 Google 最快且最具成本效益的图像生成模型，专为高容量生成和编辑而设计。",
    "zh-TW": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 是 Google 最快且最具成本效益的圖像生成模型，專為高容量生成和編輯而設計。",
    "ja-JP": "Gemini 3.1 Flash Lite Image（Nano Banana 2 Lite）は、Googleが開発した最速かつ最もコスト効率の高い画像生成モデルで、大量生成と編集に特化しています。",
    "ru-RU": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) — это самая быстрая и экономичная модель генерации изображений от Google, созданная для массовой генерации и редактирования."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nano Banana 2 Lite"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite-image-gt-128k",
   "model_name": "gemini-3.1-flash-lite-image-gt-128k",
   "display_name": "gemini-3.1-flash-lite-image-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-lite-image-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite-image-lte-128k",
   "model_name": "gemini-3.1-flash-lite-image-lte-128k",
   "display_name": "gemini-3.1-flash-lite-image-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-lite-image-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite-lte-128k",
   "model_name": "gemini-3.1-flash-lite-lte-128k",
   "display_name": "gemini-3.1-flash-lite-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-lite-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite-preview",
   "model_name": "gemini-3.1-flash-lite-preview",
   "display_name": "Gemini 3.1 Flash Lite Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+truefoundry+helicone-registry+llmdb+lobehub-modelbank+pricetoken+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "1"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+litellm+helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "1"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "cache_read": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1.98",
        "completion": "1.98",
        "cache_read": "1.98"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.55",
        "completion": "0.55",
        "cache_read": "0.55"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-preview",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "pa/gemini-3.1-flash-lite-preview"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.425"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333333333333334"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-preview"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00000025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-preview"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-preview"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-preview"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-preview",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.416667"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-lite-preview"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2026-03-03",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash-lite",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/models",
   "model_type": "deep_thinking",
   "rate_limits": {
    "rpm": 15,
    "tpm": 250000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "benchmarks": {
    "intelligence_index": 25,
    "coding_index": 34.7,
    "agentic_index": 6.2
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "google/gemini-3.1-flash-lite-preview",
    "pa/gemini-3.1-flash-lite-preview",
    "vertex/gemini-3.1-flash-lite-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 3.1 Flash-Lite Preview是谷歌最具成本效益的多模态模型，专为高容量代理任务、翻译和数据处理优化。",
    "zh-TW": "Gemini 3.1 Flash-Lite Preview 是 Google 最具成本效益的多模態模型，專為高容量代理任務、翻譯和數據處理而優化。",
    "ja-JP": "Gemini 3.1 Flash-Lite PreviewはGoogleの最もコスト効率の高いマルチモーダルモデルで、大量のエージェントタスク、翻訳、データ処理に最適化されています。",
    "ru-RU": "Gemini 3.1 Flash-Lite Preview — самая экономичная мультимодальная модель от Google, оптимизированная для задач с высоким объемом, перевода и обработки данных."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite-preview-gt-128k",
   "model_name": "gemini-3.1-flash-lite-preview-gt-128k",
   "display_name": "gemini-3.1-flash-lite-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-lite-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite-preview-lte-128k",
   "model_name": "gemini-3.1-flash-lite-preview-lte-128k",
   "display_name": "gemini-3.1-flash-lite-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-lite-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite-preview-nothink",
   "model_name": "gemini-3.1-flash-lite-preview-nothink",
   "display_name": "gemini-3.1-flash-lite-preview-nothink",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-lite-preview-nothink"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite@eu",
   "model_name": "gemini-3.1-flash-lite@eu",
   "display_name": "vertex/gemini-3.1-flash-lite@eu",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      }
     },
     "provider_model_id": "vertex/gemini-3.1-flash-lite@eu"
    }
   ],
   "released_at": "2026-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-3.1-flash-lite@eu"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-3.1-flash-lite@eu"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-lite@us",
   "model_name": "gemini-3.1-flash-lite@us",
   "display_name": "vertex/gemini-3.1-flash-lite@us",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      }
     },
     "provider_model_id": "vertex/gemini-3.1-flash-lite@us"
    }
   ],
   "released_at": "2026-05-07",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-3.1-flash-lite@us"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-3.1-flash-lite@us"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-live-preview",
   "model_name": "gemini-3.1-flash-live-preview",
   "display_name": "gemini-3.1-flash-live-preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    }
   ],
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "model_type": "realtime_omni",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "pdf_input": true,
    "web_search": true
   },
   "rate_limits": {
    "rpm": 10,
    "tpm": 250000
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "released_at": "2026-03-01",
   "knowledge_cutoff": "2025-01",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-tts",
   "model_name": "gemini-3.1-flash-tts",
   "display_name": "gemini-3.1-flash-tts",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-flash-tts"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-flash-tts-preview",
   "model_name": "gemini-3.1-flash-tts-preview",
   "display_name": "Gemini 3.1 Flash TTS Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-tts-preview",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "google/gemini-3.1-flash-tts-preview"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "released_at": "2026-04-01",
   "knowledge_cutoff": "2025-01",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-3.1-flash-tts-preview"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.1 Flash TTS Preview"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview",
   "model_name": "gemini-3.1-pro-preview",
   "display_name": "Gemini 3.1 Pro Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "gemini-3-1-pro-preview",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200000000K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "image_input": "2",
        "video_input": "2",
        "audio_input": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+litellm+helicone-registry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.00012"
      },
      "cache_storage": {
       "unit": "per_M_tokens_per_hour",
       "price": "4.5"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "1.25",
        "web_search": "1",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "gemini-3-1-pro-preview"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "tracks": [
      {
       "label": ">200000000K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "gemini-3-1-pro-preview"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "gemini-3-1-pro-preview"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "pa/gemini-3.1-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.4"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000002"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "0.666667"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gemini-3-1-pro-preview",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "1",
        "cache_write": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "tracks": [
      {
       "label": ">200000000K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "image_input": "2",
        "video_input": "2",
        "audio_input": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview"
    }
   ],
   "intro": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
   "released_at": "2026-02-19",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-pro",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview",
   "model_type": "image_generation",
   "rate_limits": {
    "rpm": 2000,
    "tpm": 800000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 256
   },
   "benchmarks": {
    "intelligence_index": 46.5,
    "coding_index": 68.8,
    "agentic_index": 21.4
   },
   "aliases": [
    "gemini-3-1-pro-preview",
    "google/gemini-3.1-pro-preview",
    "pa/gemini-3.1-pro-preview",
    "vertex/gemini-3.1-pro-preview"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 3.1 Pro Preview在Gemini 3 Pro的基础上增强了推理能力，并增加了中等思维水平支持。",
    "zh-TW": "Gemini 3.1 Pro Preview 在 Gemini 3 Pro 的基礎上增強了推理能力，並新增了中等思考層級支持。",
    "ja-JP": "Gemini 3.1 Pro Previewは、Gemini 3 Proの推論能力を強化し、中程度の思考レベルサポートを追加しています。",
    "ru-RU": "Gemini 3.1 Pro Preview улучшает Gemini 3 Pro с расширенными возможностями рассуждений и добавляет поддержку среднего уровня мышления."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-customtools",
   "model_name": "gemini-3.1-pro-preview-customtools",
   "display_name": "Gemini 3.1 Pro Preview Custom Tools",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.00012"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "2.5",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "2.5",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "2.5",
        "google_search_grounding": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "cache_write": "1.25",
        "web_search": "2.5",
        "google_search_grounding": "1",
        "maps": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.77"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.68"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview-customtools"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview-customtools"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview-customtools",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview-customtools"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000002"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview-customtools",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview-customtools",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
   "released_at": "2026-02-19",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-pro",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/models#gemini-3.1-pro-preview",
   "model_type": "image_generation",
   "rate_limits": {
    "rpm": 2000,
    "tpm": 800000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "google/gemini-3.1-pro-preview-customtools"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-customtools-gt-128k",
   "model_name": "gemini-3.1-pro-preview-customtools-gt-128k",
   "display_name": "gemini-3.1-pro-preview-customtools-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-pro-preview-customtools-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-customtools-gt-200k",
   "model_name": "gemini-3.1-pro-preview-customtools-gt-200k",
   "display_name": "gemini-3.1-pro-preview-customtools-gt-200k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-pro-preview-customtools-gt-200k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-customtools-lte-128k",
   "model_name": "gemini-3.1-pro-preview-customtools-lte-128k",
   "display_name": "gemini-3.1-pro-preview-customtools-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-pro-preview-customtools-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-customtools-lte-200k",
   "model_name": "gemini-3.1-pro-preview-customtools-lte-200k",
   "display_name": "gemini-3.1-pro-preview-customtools-lte-200k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-pro-preview-customtools-lte-200k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-gt-128k",
   "model_name": "gemini-3.1-pro-preview-gt-128k",
   "display_name": "gemini-3.1-pro-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-pro-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-gt-200k",
   "model_name": "gemini-3.1-pro-preview-gt-200k",
   "display_name": "gemini-3.1-pro-preview-gt-200k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-pro-preview-gt-200k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-high",
   "model_name": "gemini-3.1-pro-preview-high",
   "display_name": "Gemini 3.1 Pro (Preview High)",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview-high"
    }
   ],
   "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
   "released_at": "2026-02-21",
   "max_input_tokens": 1048756,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-3.1-pro-preview-high"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.1 Pro (Preview High)"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-low",
   "model_name": "gemini-3.1-pro-preview-low",
   "display_name": "Gemini 3.1 Pro (Preview Low)",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-3.1-pro-preview-low"
    }
   ],
   "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
   "released_at": "2026-02-21",
   "max_input_tokens": 1048756,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-3.1-pro-preview-low"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.1 Pro (Preview Low)"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-lte-128k",
   "model_name": "gemini-3.1-pro-preview-lte-128k",
   "display_name": "gemini-3.1-pro-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-pro-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-lte-200k",
   "model_name": "gemini-3.1-pro-preview-lte-200k",
   "display_name": "gemini-3.1-pro-preview-lte-200k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-pro-preview-lte-200k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview-search",
   "model_name": "gemini-3.1-pro-preview-search",
   "display_name": "gemini-3.1-pro-preview-search",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.1-pro-preview-search"
    }
   ]
  },
  {
   "slug": "google/gemini-3.1-pro-preview:flex",
   "model_name": "gemini-3.1-pro-preview:flex",
   "display_name": "vertex/gemini-3.1-pro-preview:flex",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     },
     "provider_model_id": "vertex/gemini-3.1-pro-preview:flex"
    }
   ],
   "released_at": "2026-02-19",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-3.1-pro-preview:flex"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-3.1-pro-preview:flex"
    }
   ]
  },
  {
   "slug": "google/gemini-3.5-flash",
   "model_name": "gemini-3.5-flash",
   "display_name": "Gemini 3.5 Flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "gemini-3-5-flash",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.014"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "cache_read": "0.55"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "1.98",
        "completion": "1.98",
        "cache_read": "1.98"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "0.55",
        "completion": "0.55",
        "cache_read": "0.55"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "enterprise_web_search": {
       "unit": "per_request",
       "price": "0.014"
      },
      "maps": {
       "unit": "per_request",
       "price": "0.014"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "google_search_grounding": "1",
        "enterprise_web_search": "1",
        "maps": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.533333"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.331"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.987"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.133"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.425"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.55"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "gemini-3-5-flash"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0000015"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5152"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.0909"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1515"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.583"
      }
     },
     "provider_model_id": "vertex/gemini-3.5-flash"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.45"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.155"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.086"
      }
     },
     "provider_model_id": "gemini-3-5-flash"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_maps_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.533333"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "video_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash"
    }
   ],
   "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
   "released_at": "2026-05-19",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "docs_url": "https://ai.google.dev/pricing/gemini-3",
   "model_type": "deep_thinking",
   "rate_limits": {
    "rpm": 2000,
    "tpm": 800000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 256
   },
   "benchmarks": {
    "intelligence_index": 50.2,
    "coding_index": 70.1,
    "agentic_index": 37.4
   },
   "aliases": [
    "gemini-3-5-flash",
    "google/gemini-3.5-flash",
    "vertex/gemini-3.5-flash"
   ],
   "intro_i18n": {
    "zh-CN": "Gemini 的最智能模型，专为速度而设计，结合前沿智能与卓越的搜索和基础能力。",
    "zh-TW": "Gemini 最智能的模型，專為速度而設計，結合前沿智能與卓越的搜索和基礎能力。",
    "ja-JP": "最先端の知能と優れた検索・基盤技術を組み合わせた、スピード重視のGeminiの最も知的なモデル。",
    "ru-RU": "Самая интеллектуальная модель Gemini, созданная для скорости, объединяющая передовой интеллект с превосходным поиском и обоснованием."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-3.5-flash-gt-128k",
   "model_name": "gemini-3.5-flash-gt-128k",
   "display_name": "gemini-3.5-flash-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.5-flash-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.5-flash-lte-128k",
   "model_name": "gemini-3.5-flash-lte-128k",
   "display_name": "gemini-3.5-flash-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-3.5-flash-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-3.5-flash-thinking",
   "model_name": "gemini-3.5-flash-thinking",
   "display_name": "Gemini 3.5 Flash Thinking",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-3.5-flash-thinking"
    }
   ],
   "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
   "released_at": "2026-05-19",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-3.5-flash-thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.5 Flash Thinking"
    }
   ]
  },
  {
   "slug": "google/gemini-3.5-flash@eu",
   "model_name": "gemini-3.5-flash@eu",
   "display_name": "vertex/gemini-3.5-flash@eu",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.583"
      }
     },
     "provider_model_id": "vertex/gemini-3.5-flash@eu"
    }
   ],
   "released_at": "2026-05-19",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-3.5-flash@eu"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-3.5-flash@eu"
    }
   ]
  },
  {
   "slug": "google/gemini-3.5-flash@us",
   "model_name": "gemini-3.5-flash@us",
   "display_name": "vertex/gemini-3.5-flash@us",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.583"
      }
     },
     "provider_model_id": "vertex/gemini-3.5-flash@us"
    }
   ],
   "released_at": "2026-05-19",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "vertex/gemini-3.5-flash@us"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vertex/gemini-3.5-flash@us"
    }
   ]
  },
  {
   "slug": "google/gemini-3.5-live-translate-preview",
   "model_name": "gemini-3.5-live-translate-preview",
   "display_name": "Gemini 3.5 Live Translate Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "21"
      }
     }
    }
   ],
   "released_at": "2026-06-01",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "audio",
     "text"
    ]
   },
   "capabilities": {
    "pdf_input": true,
    "audio_input": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "realtime_speech_translation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 3.5 Live Translate Preview"
    }
   ]
  },
  {
   "slug": "google/gemini-deep-research",
   "model_name": "gemini-deep-research",
   "display_name": "gemini-deep-research",
   "vendor": "google",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.6"
      }
     },
     "provider_model_id": "google/gemini-deep-research"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-12-11",
   "max_input_tokens": 1048576,
   "max_output_tokens": 0,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-deep-research"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-deep-research"
    }
   ]
  },
  {
   "slug": "google/gemini-embedding-001",
   "model_name": "gemini-embedding-001",
   "display_name": "Gemini Embedding 001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "asia-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "asia-east2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "asia-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "asia-northeast3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "asia-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "asia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "australia-southeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "europe-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "europe-north1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "europe-southwest1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "europe-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "europe-west2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "europe-west3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "europe-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "europe-west6",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "europe-west8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "europe-west9",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "me-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "me-central2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "me-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "northamerica-northeast1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "southamerica-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "us-east1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "us-east4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "us-south1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "us-west1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemini-embedding-001",
     "region": "us-west4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-embedding-001"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-embedding-001"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-embedding-001"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-embedding-001"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-embedding-001"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2025-05-20",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 2048,
   "max_output_tokens": 1,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "docs_url": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions",
   "model_type": "text_embedding",
   "rate_limits": {
    "rpm": 10000,
    "tpm": 10000000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-embedding-001"
   ],
   "intro_i18n": {
    "zh-CN": "一款先进的嵌入模型，在英文、多语言和代码任务中表现出色。",
    "zh-TW": "一款最先進的嵌入模型，在英文、多語言與程式任務中表現優異。",
    "ja-JP": "英語、多言語、コードタスクにおいて高性能を発揮する最先端の埋め込みモデルです。",
    "ru-RU": "Современная модель встраивания с высокой производительностью для задач на английском языке, в многоязычной среде и в программировании."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-embedding-001-gt-128k",
   "model_name": "gemini-embedding-001-gt-128k",
   "display_name": "gemini-embedding-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-embedding-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-embedding-001-lte-128k",
   "model_name": "gemini-embedding-001-lte-128k",
   "display_name": "gemini-embedding-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-embedding-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-embedding-2",
   "model_name": "gemini-embedding-2",
   "display_name": "gemini-embedding-2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00012"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "6.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00012"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "6.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-embedding-2",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "google/gemini-embedding-2"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-embedding-2"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-embedding-2"
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "max_input_tokens": 8192,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "rate_limits": {
    "rpm": 10000,
    "tpm": 10000000
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "embedding"
    ]
   },
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2026-03-10",
   "max_output_tokens": 0,
   "family": "gemini-embedding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-embedding-2"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-embedding-2-preview",
   "model_name": "gemini-embedding-2-preview",
   "display_name": "gemini-embedding-2-preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00012"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "6.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00012"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "6.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-embedding-2-preview",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "6.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-embedding-2-preview",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "6.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-embedding-2-preview",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "6.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-embedding-2-preview",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-embedding-2-preview"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-embedding-2-preview"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "max_input_tokens": 8192,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true,
    "stream": true
   },
   "rate_limits": {
    "rpm": 10000,
    "tpm": 10000000
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "embedding"
    ]
   },
   "released_at": "2026-03-11",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-embedding-2-preview"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-embedding-2-preview-gt-128k",
   "model_name": "gemini-embedding-2-preview-gt-128k",
   "display_name": "gemini-embedding-2-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-embedding-2-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-embedding-2-preview-lte-128k",
   "model_name": "gemini-embedding-2-preview-lte-128k",
   "display_name": "gemini-embedding-2-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-embedding-2-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-embedding-exp-03-07",
   "model_name": "gemini-embedding-exp-03-07",
   "display_name": "gemini-embedding-exp-03-07",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-embedding-exp-03-07"
    }
   ]
  },
  {
   "slug": "google/gemini-exp-1114",
   "model_name": "gemini-exp-1114",
   "display_name": "gemini-exp-1114",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "google/gemini-exp-1114"
    }
   ],
   "docs_url": "https://ai.google.dev/pricing",
   "max_input_tokens": 1048576,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "rate_limits": {
    "rpm": 1000,
    "tpm": 4000000
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-exp-1114"
   ]
  },
  {
   "slug": "google/gemini-exp-1121",
   "model_name": "gemini-exp-1121",
   "display_name": "gemini-exp-1121",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-exp-1121"
    }
   ]
  },
  {
   "slug": "google/gemini-exp-1206",
   "model_name": "gemini-exp-1206",
   "display_name": "gemini-exp-1206",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.258"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.998"
      }
     }
    }
   ],
   "docs_url": "https://ai.google.dev/pricing",
   "max_input_tokens": 2097152,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "rate_limits": {
    "rpm": 1000,
    "tpm": 4000000
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-12-06",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-flash-1.5",
   "model_name": "gemini-flash-1.5",
   "display_name": "Gemini 1.5 Flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01875"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0748"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "google/gemini-flash-1.5"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01875"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1583"
      }
     },
     "provider_model_id": "google/gemini-flash-1.5"
    }
   ],
   "intro": "Gemini 1.5 Flash is a foundation model that performs well at a variety of multimodal tasks such as visual understanding, classification, summarization, and creating content from image, audio and video. It's adept at processing visual and text inputs such as photographs, documents, infographics, and screenshots.",
   "capabilities": {},
   "released_at": "2024-05-14",
   "max_input_tokens": 2000000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-flash-1.5"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini 1.5 Flash"
    }
   ]
  },
  {
   "slug": "google/gemini-flash-1.5-8b",
   "model_name": "gemini-flash-1.5-8b",
   "display_name": "gemini-flash-1.5-8b",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0583"
      }
     },
     "provider_model_id": "google/gemini-flash-1.5-8b"
    }
   ],
   "intro": "A faster, more cost-effective variant of Gemini 1.5 that maintains strong capabilities while optimizing for performance and cost efficiency. Suitable for production deployments requiring high throughput.",
   "max_input_tokens": 1000000,
   "capabilities": {
    "function_calling": true,
    "vision": true
   },
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-flash-1.5-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-flash-1.5-8b"
    }
   ]
  },
  {
   "slug": "google/gemini-flash-experimental",
   "model_name": "gemini-flash-experimental",
   "display_name": "gemini-flash-experimental",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "max_input_tokens": 1000000,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-flash-experimental"
    }
   ]
  },
  {
   "slug": "google/gemini-flash-latest",
   "model_name": "gemini-flash-latest",
   "display_name": "Gemini Flash Latest",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.833333",
        "completion": "0.6"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.383"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08333333333333334"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "~google/gemini-flash-latest"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-flash-latest"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemini-flash-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.083333"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0000005"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "~google/gemini-flash-latest"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "google/gemini-flash-latest"
    }
   ],
   "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
   "released_at": "2025-09-25",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash",
   "reasoning_config": {
    "budget_min": 0
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/",
   "model_type": "deep_thinking",
   "rate_limits": {
    "rpm": 15,
    "tpm": 250000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "google/gemini-flash-latest",
    "~google/gemini-flash-latest"
   ],
   "intro_i18n": {
    "zh-CN": "指向 gemini-3-flash-preview",
    "zh-TW": "指向 gemini-3-flash-preview",
    "ja-JP": "gemini-3-flash-previewを指します。",
    "ru-RU": "Указывает на gemini-3-flash-preview"
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-flash-latest-gt-128k",
   "model_name": "gemini-flash-latest-gt-128k",
   "display_name": "gemini-flash-latest-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-flash-latest-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-flash-latest-lte-128k",
   "model_name": "gemini-flash-latest-lte-128k",
   "display_name": "gemini-flash-latest-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-flash-latest-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-flash-lite-latest",
   "model_name": "gemini-flash-lite-latest",
   "display_name": "Gemini Flash-Lite Latest",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+litellm+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.25",
        "completion": "1.875"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/gemini-flash-lite-latest"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/gemini-flash-lite-latest"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/gemini-flash-lite-latest"
    }
   ],
   "intro": "Low-latency Gemini model for high-volume multimodal and agent workloads",
   "released_at": "2025-09-25",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemini-flash-lite",
   "reasoning_config": {
    "budget_min": 512
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/",
   "model_type": "deep_thinking",
   "rate_limits": {
    "rpm": 15,
    "tpm": 250000
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "google/gemini-flash-lite-latest"
   ],
   "intro_i18n": {
    "zh-CN": "指向 gemini-3.1-flash-lite",
    "zh-TW": "指向 gemini-3.1-flash-lite",
    "ja-JP": "gemini-3.1-flash-liteを指します。",
    "ru-RU": "Указывает на gemini-3.1-flash-lite"
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-flash-lite-latest-gt-128k",
   "model_name": "gemini-flash-lite-latest-gt-128k",
   "display_name": "gemini-flash-lite-latest-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-flash-lite-latest-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-flash-lite-latest-lte-128k",
   "model_name": "gemini-flash-lite-latest-lte-128k",
   "display_name": "gemini-flash-lite-latest-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-flash-lite-latest-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-gemma-2-27b-it",
   "model_name": "gemini-gemma-2-27b-it",
   "display_name": "gemini-gemma-2-27b-it",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.05"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "rate_limits": {
    "rpm": 10,
    "tpm": 250000
   },
   "capabilities": {
    "vision": true,
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   }
  },
  {
   "slug": "google/gemini-gemma-2-9b-it",
   "model_name": "gemini-gemma-2-9b-it",
   "display_name": "gemini-gemma-2-9b-it",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.05"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "rate_limits": {
    "rpm": 10,
    "tpm": 250000
   },
   "capabilities": {
    "vision": true,
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   }
  },
  {
   "slug": "google/gemini-live-2.5-flash-native-audio",
   "model_name": "gemini-live-2.5-flash-native-audio",
   "display_name": "gemini-live-2.5-flash-native-audio",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "google/gemini-live-2.5-flash-native-audio"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "model_type": "realtime_omni",
   "capabilities": {
    "function_calling": true,
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-live-2.5-flash-native-audio"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-live-2.5-flash-native-audio"
    }
   ]
  },
  {
   "slug": "google/gemini-live-2.5-flash-preview",
   "model_name": "gemini-live-2.5-flash-preview",
   "display_name": "gemini-live-2.5-flash-preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "realtime_omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-live-2.5-flash-preview"
    }
   ]
  },
  {
   "slug": "google/gemini-omni-flash",
   "model_name": "gemini-omni-flash",
   "display_name": "Gemini-Omni-Flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5152"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17.6768"
      }
     }
    }
   ],
   "released_at": "2026-07-01",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini-Omni-Flash"
    }
   ]
  },
  {
   "slug": "google/gemini-omni-flash-preview",
   "model_name": "gemini-omni-flash-preview",
   "display_name": "Gemini Omni Flash Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17.5"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "google/gemini-omni-flash-preview",
     "region": "global"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "google/gemini-omni-flash-preview"
    }
   ],
   "intro": "Video generation and editing model for fast, conversational text- and image-to-video workflows",
   "released_at": "2026-06-30",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "family": "gemini",
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "pdf_input": true
   },
   "model_type": "omni",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-omni-flash-preview"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-08",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-08",
     "kind": "limit",
     "new": "57920",
     "note": "max_output_tokens"
    },
    {
     "date": "2026-07-08",
     "kind": "limit",
     "old": "1048576",
     "new": "131072",
     "note": "max_input_tokens"
    },
    {
     "date": "2026-07-08",
     "kind": "limit",
     "old": "57920",
     "new": "65536",
     "note": "max_output_tokens"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "google",
     "charge": "completion",
     "old": "9",
     "new": "17.5"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini Omni Flash Preview"
    }
   ]
  },
  {
   "slug": "google/gemini-omni-flash-preview-gt-128k",
   "model_name": "gemini-omni-flash-preview-gt-128k",
   "display_name": "gemini-omni-flash-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-omni-flash-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-omni-flash-preview-lte-128k",
   "model_name": "gemini-omni-flash-preview-lte-128k",
   "display_name": "gemini-omni-flash-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-omni-flash-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-pro",
   "model_name": "gemini-pro",
   "display_name": "gemini-pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "0.666667"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.125"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "google/gemini-pro"
    }
   ],
   "intro": "Google's first-generation advanced multimodal model that can understand text, code, and images. It provides strong reasoning capabilities and follows instructions effectively.",
   "max_input_tokens": 32768,
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-pro"
    }
   ]
  },
  {
   "slug": "google/gemini-pro-1.5",
   "model_name": "gemini-pro-1.5",
   "display_name": "gemini-pro-1.5",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3125"
      }
     },
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.00265"
      }
     },
     "provider_model_id": "google/gemini-pro-1.5"
    }
   ],
   "intro": "Google's latest multimodal model, supports image and video[0] in text or chat prompts.",
   "max_input_tokens": 2000000,
   "capabilities": {
    "function_calling": true,
    "vision": true
   },
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-pro-1.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-pro-1.5"
    }
   ]
  },
  {
   "slug": "google/gemini-pro-latest",
   "model_name": "gemini-pro-latest",
   "display_name": "gemini-pro-latest",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8",
        "completion": "0.6"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200000000K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "5",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "~google/gemini-pro-latest"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemini-pro-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000002"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "~google/gemini-pro-latest"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      }
     },
     "provider_model_id": "google/gemini-pro-latest"
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "model_type": "vision_understanding",
   "rate_limits": {
    "rpm": 2000,
    "tpm": 800000
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "modalities": {
    "input": [
     "audio",
     "image",
     "pdf"
    ],
    "output": []
   },
   "knowledge_cutoff": "2025-01",
   "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis",
   "released_at": "2026-02-27",
   "family": "gemini",
   "aliases": [
    "google/gemini-pro-latest",
    "~google/gemini-pro-latest"
   ],
   "intro_i18n": {
    "zh-CN": "指向 gemini-3.1-pro-preview",
    "zh-TW": "指向 gemini-3.1-pro-preview",
    "ja-JP": "gemini-3.1-pro-previewを指します。",
    "ru-RU": "Указывает на gemini-3.1-pro-preview"
   }
  },
  {
   "slug": "google/gemini-pro-latest-gt-128k",
   "model_name": "gemini-pro-latest-gt-128k",
   "display_name": "gemini-pro-latest-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-pro-latest-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-pro-latest-lte-128k",
   "model_name": "gemini-pro-latest-lte-128k",
   "display_name": "gemini-pro-latest-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "google_search_grounding": {
       "unit": "per_k_calls",
       "price": "14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-pro-latest-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-pro-vision",
   "model_name": "gemini-pro-vision",
   "display_name": "gemini-pro-vision",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "google/gemini-pro-vision"
    }
   ],
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "vision": true
   },
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-pro-vision"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-pro-vision"
    }
   ]
  },
  {
   "slug": "google/gemini-robotics-er-1.5-preview",
   "model_name": "gemini-robotics-er-1.5-preview",
   "display_name": "gemini-robotics-er-1.5-preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "docs_url": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "rate_limits": {
    "rpm": 10,
    "tpm": 250000
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-11-14",
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "google/gemini-robotics-er-1.5-preview-gt-128k",
   "model_name": "gemini-robotics-er-1.5-preview-gt-128k",
   "display_name": "gemini-robotics-er-1.5-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-robotics-er-1.5-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-robotics-er-1.5-preview-lte-128k",
   "model_name": "gemini-robotics-er-1.5-preview-lte-128k",
   "display_name": "gemini-robotics-er-1.5-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemini-robotics-er-1.5-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/gemini-robotics-er-1.6-preview",
   "model_name": "gemini-robotics-er-1.6-preview",
   "display_name": "Gemini Robotics-ER 1.6 Preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "google/gemini-robotics-er-1.6-preview"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true
   },
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2025-01",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemini-robotics-er-1.6-preview"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemini Robotics-ER 1.6 Preview"
    }
   ]
  },
  {
   "slug": "google/gemma",
   "model_name": "gemma",
   "display_name": "gemma",
   "vendor": "google",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.285409875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57081975"
      }
     }
    }
   ],
   "released_at": "2026-04-02",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.57185374",
     "new": "0.57081975"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28592687",
     "new": "0.285409875"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.571632985",
     "new": "0.57185374"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2858164925",
     "new": "0.28592687"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.572070715",
     "new": "0.571632985"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2860353575",
     "new": "0.2858164925"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.57184042",
     "new": "0.572070715"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28592021",
     "new": "0.2860353575"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.571998935",
     "new": "0.57184042"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2859994675",
     "new": "0.28592021"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.5690485",
     "new": "0.571998935"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28452425",
     "new": "0.2859994675"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma"
    }
   ]
  },
  {
   "slug": "google/gemma-2-27b",
   "model_name": "gemma-2-27b",
   "display_name": "Gemma 2 27B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "knowledge_cutoff": "2024-02",
   "max_input_tokens": 8192,
   "family": "Gemma",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Gemma 2 是 Google 推出的高效模型家族，适用于从小型应用到复杂数据处理的多种场景。",
    "zh-TW": "Gemma 2 是 Google 推出的高效模型家族，適用於從小型應用到複雜資料處理的各種場景。",
    "ja-JP": "Gemma 2は、軽量アプリから複雑なデータ処理まで対応するGoogleの効率的なモデルファミリーです。",
    "ru-RU": "Gemma 2 — семейство эффективных моделей от Google, подходящее как для небольших приложений, так и для сложной обработки данных."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 2 27B"
    }
   ]
  },
  {
   "slug": "google/gemma-2-27b-it",
   "model_name": "gemma-2-27b-it",
   "display_name": "Google: Gemma 2 27B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "google/gemma-2-27b-it"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "provider_model_id": "google/gemma-2-27b-it"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "provider_model_id": "google/gemma-2-27b-it"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "google/gemma-2-27b-it"
    }
   ],
   "intro": "Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of text generation and instruction-following tasks.",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "released_at": "2024-06-24",
   "max_input_tokens": 8192,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2024-06",
   "family": "gemma",
   "deprecated": true,
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-2-27b-it"
   ],
   "intro_i18n": {
    "zh-CN": "Gemma 2 27B 是一款通用大型语言模型，在多种场景下表现优异。",
    "zh-TW": "Gemma 2 27B 是一款通用大型語言模型，在多種場景中表現出色。",
    "ja-JP": "Gemma 2 27Bは、さまざまなシナリオで高性能を発揮する汎用LLMです。",
    "ru-RU": "Gemma 2 27B — универсальная языковая модель с высокой производительностью в различных сценариях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Google: Gemma 2 27B"
    }
   ]
  },
  {
   "slug": "google/gemma-2-2b-it",
   "model_name": "gemma-2-2b-it",
   "display_name": "Gemma 2 2b It",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.002"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/gemma-2-2b-it"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-2-2b-it"
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2024-07-16",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2024-06",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-2-2b-it"
   ],
   "intro_i18n": {
    "zh-CN": "一款专为边缘应用设计的先进小型语言模型。",
    "zh-TW": "一款專為邊緣應用設計的先進小型語言模型。",
    "ja-JP": "エッジアプリケーション向けに設計された高度な小型言語モデルです。",
    "ru-RU": "Продвинутая компактная языковая модель, предназначенная для использования на периферийных устройствах."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 2 2b It"
    }
   ]
  },
  {
   "slug": "google/gemma-2-9b-it",
   "model_name": "gemma-2-9b-it",
   "display_name": "Google Gemma 2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "google/gemma-2-9b-it:free"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "unsloth/gemma-2-9b-it"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "google/gemma-2-9b-it"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemma-2-9b-it"
    }
   ],
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "intro": "Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, with open weights for both pre-trained variants and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone.",
   "knowledge_cutoff": "2024-06",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "released_at": "2024-06-28",
   "family": "gemma",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemma-2-9b-it:free",
    "google/gemma-2-9b-it",
    "google/gemma-2-9b-it:free",
    "unsloth/gemma-2-9b-it"
   ],
   "intro_i18n": {
    "zh-CN": "Gemma 2 9B 是 Google 开发的高效模型，具备良好的指令遵循能力和整体性能。",
    "zh-TW": "由 Google 開發的 Gemma 2 9B，具備高效的指令遵循能力與穩健的整體表現。",
    "ja-JP": "Googleが開発したGemma 2 9Bは、効率的な指示追従と堅実な全体性能を提供します。",
    "ru-RU": "Gemma 2 9B, разработанная Google, обеспечивает эффективное выполнение инструкций и общую высокую производительность."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Google Gemma 2"
    }
   ]
  },
  {
   "slug": "google/gemma-2-9b-it-fast",
   "model_name": "gemma-2-9b-it-fast",
   "display_name": "Gemma-2-9b-it (Fast)",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      }
     },
     "provider_model_id": "google/gemma-2-9b-it-fast"
    }
   ],
   "released_at": "2024-06-27",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-2-9b-it-fast"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma-2-9b-it (Fast)"
    }
   ]
  },
  {
   "slug": "google/gemma-2b",
   "model_name": "gemma-2b",
   "display_name": "gemma-2b",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google/gemma-2b"
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-2b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma-2b"
    }
   ]
  },
  {
   "slug": "google/gemma-2b-it",
   "model_name": "gemma-2b-it",
   "display_name": "Gemma 2B Instruct",
   "vendor": "google",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-2b-it"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/gemma-2b-it"
   ],
   "intro_i18n": {
    "zh-CN": "Gemma Instruct（2B）为轻量级应用提供基础指令处理能力。",
    "zh-TW": "Gemma Instruct (2B) 提供基礎指令處理能力，適用於輕量應用。",
    "ja-JP": "Gemma Instruct（2B）は、軽量アプリケーション向けの基本的な指示処理を提供します。",
    "ru-RU": "Gemma Instruct (2B) обеспечивает базовую обработку инструкций для лёгких приложений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 2B Instruct"
    }
   ]
  },
  {
   "slug": "google/gemma-3",
   "model_name": "gemma-3",
   "display_name": "Google Gemma 3",
   "vendor": "google",
   "pricing": [
    {
     "provider": "inference",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "google/gemma-3"
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 125000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Google Gemma 3"
    }
   ]
  },
  {
   "slug": "google/gemma-3-12b",
   "model_name": "gemma-3-12b",
   "display_name": "Gemma 3 12B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "intro": "Google's open-weight Gemma 3 vision-language model for text and image understanding",
   "released_at": "2025-03-13",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "listed",
     "note": "Gemma 3 12B"
    }
   ]
  },
  {
   "slug": "google/gemma-3-12b-it",
   "model_name": "gemma-3-12b-it",
   "display_name": "Gemma 3 12B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "unsloth/gemma-3-12b-it"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+computeprices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.049999999999999996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09999999999999999"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0927"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2987"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0927"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2987"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "google.gemma-3-12b-it",
     "region": "us-west-2"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "unsloth/gemma-3-12b-it"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     },
     "provider_model_id": "workers-ai/@cf/google/gemma-3-12b-it"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     },
     "provider_model_id": "@cf/google/gemma-3-12b-it"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google/gemma-3-12b-it"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-3-12b-it"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.049999999999999996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09999999999999999"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemma-3-12b-it"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google/gemma-3-12b-it"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "google/gemma-3-12b-it"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.272"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.272"
      }
     },
     "provider_model_id": "unsloth/gemma-3-12b-it"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google/gemma-3-12b-it"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google/gemma-3-12b-it"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/gemma-3-12b-it"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "deepinfra/google/gemma-3-12b-it"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true,
    "prompt_caching": true,
    "structured_output": true,
    "function_calling": true,
    "reasoning": true
   },
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-03-13",
   "family": "gemma",
   "knowledge_cutoff": "2024-12",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 5.5,
    "coding_index": 5.8,
    "agentic_index": 0.3
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "@cf/google/gemma-3-12b-it",
    "accounts/fireworks/models/gemma-3-12b-it",
    "deepinfra/google/gemma-3-12b-it",
    "gemma-3-12b-it:free",
    "google.gemma-3-12b-it",
    "google/gemma-3-12b-it",
    "google/gemma-3-12b-it:free",
    "unsloth/gemma-3-12b-it",
    "workers-ai/@cf/google/gemma-3-12b-it"
   ],
   "intro_i18n": {
    "zh-CN": "Gemma 3 12B 是 Google 推出的开源语言模型，在效率和性能方面树立了新标杆。",
    "zh-TW": "Gemma 3 12B 是 Google 推出的開源語言模型，在效率與效能上樹立新標竿。",
    "ja-JP": "Gemma 3 12Bは、効率と性能の新たな基準を打ち立てるGoogleのオープンソース言語モデルです。",
    "ru-RU": "Gemma 3 12B — языковая модель с открытым исходным кодом от Google, устанавливающая новый стандарт эффективности и производительности."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 3 12B"
    }
   ]
  },
  {
   "slug": "google/gemma-3-1b-it",
   "model_name": "gemma-3-1b-it",
   "display_name": "Gemma 3 1B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-3-1b-it"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/gemma-3-1b-it"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 3 1B"
    }
   ]
  },
  {
   "slug": "google/gemma-3-270m-it-lora",
   "model_name": "gemma-3-270m-it-lora",
   "display_name": "gemma-3-270m-it-lora",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-3-270m-it-lora"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-3-270m-it-lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma-3-270m-it-lora"
    }
   ]
  },
  {
   "slug": "google/gemma-3-27b",
   "model_name": "gemma-3-27b",
   "display_name": "Gemma 3 27B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.521739",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "privatemode-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-03-12",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 3 27B"
    }
   ]
  },
  {
   "slug": "google/gemma-3-27b-it",
   "model_name": "gemma-3-27b-it",
   "display_name": "gemma-3-27b-it",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "unsloth/gemma-3-27b-it"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.46"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2369"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3914"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.46"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.46"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2369"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3914"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.46"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "google.gemma-3-27b-it",
     "region": "us-west-2"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "unsloth/gemma-3-27b-it"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.089"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.268"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-3-27b-it"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.119"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "TEE/gemma-3-27b-it"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.119"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.119"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "nebius/google/gemma-3-27b-it"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "stackit",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.76"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "deepinfra/google/gemma-3-27b-it"
    }
   ],
   "docs_url": "https://aistudio.google.com",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "open_weights": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-05-17",
   "family": "gemma",
   "knowledge_cutoff": "2025-10",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 7.4,
    "coding_index": 10.1,
    "agentic_index": 0.3
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "TEE/gemma-3-27b-it",
    "accounts/fireworks/models/gemma-3-27b-it",
    "deepinfra/google/gemma-3-27b-it",
    "gemma-3-27b-it:free",
    "google.gemma-3-27b-it",
    "google/gemma-3-27b-it",
    "google/gemma-3-27b-it:free",
    "nebius/google/gemma-3-27b-it",
    "unsloth/gemma-3-27b-it"
   ],
   "intro_i18n": {
    "zh-CN": "Gemma 3 27B 是 Google 推出的开源语言模型，在效率和性能方面树立了新标杆。",
    "zh-TW": "Gemma 3 27B 是 Google 推出的開源語言模型，在效率與效能上樹立新標竿。",
    "ja-JP": "Gemma 3 27Bは、効率と性能の新たな基準を打ち立てるGoogleのオープンソース言語モデルです。",
    "ru-RU": "Gemma 3 27B — языковая модель с открытым исходным кодом от Google, устанавливающая новый стандарт эффективности и производительности."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "stackit",
     "charge": "completion",
     "old": "0.71",
     "new": "0.76"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "stackit",
     "charge": "prompt",
     "old": "0.49",
     "new": "0.53"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "google/gemma-3-27b-it-fast",
   "model_name": "gemma-3-27b-it-fast",
   "display_name": "Gemma-3-27b-it (Fast)",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it-fast"
    }
   ],
   "released_at": "2026-01-20",
   "knowledge_cutoff": "2025-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-3-27b-it-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma-3-27b-it (Fast)"
    }
   ]
  },
  {
   "slug": "google/gemma-3-27b-it-lora",
   "model_name": "gemma-3-27b-it-lora",
   "display_name": "gemma-3-27b-it-lora",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-3-27b-it-lora"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-3-27b-it-lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma-3-27b-it-lora"
    }
   ]
  },
  {
   "slug": "google/gemma-3-4b-it",
   "model_name": "gemma-3-4b-it",
   "display_name": "Gemma 3 4B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+computeprices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0824"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0824"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "google.gemma-3-4b-it",
     "region": "us-west-2"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "unsloth/gemma-3-4b-it"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "google/gemma-3-4b-it"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-3-4b-it"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google/gemma-3-4b-it"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "google/gemma-3-4b-it"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      }
     },
     "provider_model_id": "unsloth/gemma-3-4b-it"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "google/gemma-3-4b-it"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "deepinfra/google/gemma-3-4b-it"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true,
    "open_weights": true,
    "pdf_input": true,
    "structured_output": true,
    "stream": true,
    "prompt_caching": true,
    "reasoning": true
   },
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-03-13",
   "family": "gemma",
   "knowledge_cutoff": "2024-08",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": null,
    "coding_index": 2.7,
    "agentic_index": null
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/gemma-3-4b-it",
    "deepinfra/google/gemma-3-4b-it",
    "gemma-3-4b-it:free",
    "google.gemma-3-4b-it",
    "google/gemma-3-4b-it",
    "google/gemma-3-4b-it:free",
    "unsloth/gemma-3-4b-it"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 3 4B"
    }
   ]
  },
  {
   "slug": "google/gemma-3n-e2b-it",
   "model_name": "gemma-3n-e2b-it",
   "display_name": "Gemma 3n E2B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-3n-e2b-it"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gemma-3n-e2b-it:free"
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text",
     "audio",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-06-12",
   "knowledge_cutoff": "2024-06",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemma-3n-e2b-it:free",
    "google/gemma-3n-e2b-it",
    "google/gemma-3n-e2b-it:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 3n E2B"
    }
   ]
  },
  {
   "slug": "google/gemma-3n-E4B-it",
   "model_name": "gemma-3n-E4B-it",
   "display_name": "Gemma 3n E4B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "provider_model_id": "gemma-3n-e4b-it"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "gemma-3n-e4b-it"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.060000000000000005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12000000000000001"
      }
     },
     "provider_model_id": "google/gemma-3n-E4B-it"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "google/gemma-3n-e4b-it"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-3n-e4b-it"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "google/gemma-3n-e4b-it"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "google/gemma-3n-E4B-it"
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "audio",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "video_input": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-06-03",
   "knowledge_cutoff": "2024-06",
   "family": "gemma",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": null,
    "coding_index": 3.2,
    "agentic_index": null
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemma-3n-e4b-it",
    "gemma-3n-e4b-it:free",
    "google/gemma-3n-E4B-it",
    "google/gemma-3n-e4b-it",
    "google/gemma-3n-e4b-it:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 3n E4B"
    }
   ]
  },
  {
   "slug": "google/gemma-4",
   "model_name": "gemma-4",
   "display_name": "Gemma 4",
   "vendor": "google",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.285409875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57081975"
      }
     },
     "provider_model_id": "google/gemma-4"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "llmtr/gemma-4"
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2026-04-22",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-4",
    "llmtr/gemma-4"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.57185374",
     "new": "0.57081975"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28592687",
     "new": "0.285409875"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.571632985",
     "new": "0.57185374"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2858164925",
     "new": "0.28592687"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.572070715",
     "new": "0.571632985"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2860353575",
     "new": "0.2858164925"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.57184042",
     "new": "0.572070715"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28592021",
     "new": "0.2860353575"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.571998935",
     "new": "0.57184042"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2859994675",
     "new": "0.28592021"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.5690485",
     "new": "0.571998935"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28452425",
     "new": "0.2859994675"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4"
    }
   ]
  },
  {
   "slug": "google/gemma-4-26b-a4b",
   "model_name": "gemma-4-26b-a4b",
   "display_name": "Gemma-4-26B-A4B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "provider_model_id": "google.gemma-4-26b-a4b",
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google.gemma-4-26b-a4b",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google.gemma-4-26b-a4b",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google.gemma-4-26b-a4b",
     "region": "us-west-2"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1313"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.404"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "released_at": "2026-04-02",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google.gemma-4-26b-a4b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma-4-26B-A4B"
    }
   ]
  },
  {
   "slug": "google/gemma-4-26b-a4b-el",
   "model_name": "gemma-4-26b-a4b-el",
   "display_name": "Gemma-4-26B-A4B-EL",
   "vendor": "google",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0505"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2929"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0253"
      }
     }
    }
   ],
   "released_at": "2026-05-17",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma-4-26B-A4B-EL"
    }
   ]
  },
  {
   "slug": "google/gemma-4-26b-a4b-it",
   "model_name": "gemma-4-26b-a4b-it",
   "display_name": "Gemma 4 26B A4B IT",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+pydantic-prices+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39998"
      }
     }
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "@cf/google/gemma-4-26b-a4b-it"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "google/gemma-4-26B-A4B-it"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.575"
      }
     },
     "provider_model_id": "google/gemma-4-26B-A4B-it"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-4-26b-a4b-it"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-26B-A4B-it"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.426"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.426"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     }
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.51495962"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.51495962"
      }
     },
     "provider_model_id": "gemma-4-26B-A4B-it"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "deepinfra/google/gemma-4-26B-A4B-it"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-26B-A4B-it"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-4-26B-A4B-it"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33000000000000007"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it"
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2026-04-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2025-01",
   "status": "beta",
   "benchmarks": {
    "intelligence_index": 25.7,
    "coding_index": 39.3,
    "agentic_index": 11
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95,
     "top_k": 64
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "@cf/google/gemma-4-26b-a4b-it",
    "accounts/fireworks/models/gemma-4-26b-a4b-it",
    "deepinfra/google/gemma-4-26B-A4B-it",
    "gemma-4-26B-A4B-it",
    "google/gemma-4-26B-A4B-it",
    "google/gemma-4-26b-a4b-it",
    "google/gemma-4-26b-a4b-it:free",
    "google/gemma-4-26b-a4b-it:thinking",
    "novita/google/gemma-4-26b-a4b-it",
    "parasail/google/gemma-4-26B-A4B-it"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.061",
     "new": "0.06"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "0.428",
     "new": "0.426"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.122",
     "new": "0.12"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.061",
     "new": "0.06"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.428",
     "new": "0.426"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.122",
     "new": "0.12"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.51520588",
     "new": "0.51495962"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.51520588",
     "new": "0.51495962"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.058",
     "new": "0.061"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "0.408",
     "new": "0.428"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.116",
     "new": "0.122"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.058",
     "new": "0.061"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.408",
     "new": "0.428"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.116",
     "new": "0.122"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.51556379",
     "new": "0.51520588"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.51556379",
     "new": "0.51520588"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.061",
     "new": "0.058"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "0.428",
     "new": "0.408"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.122",
     "new": "0.116"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.061",
     "new": "0.058"
    }
   ]
  },
  {
   "slug": "google/gemma-4-26b-a4b-it-maas",
   "model_name": "gemma-4-26b-a4b-it-maas",
   "display_name": "gemma-4-26b-a4b-it-maas",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "google/gemma-4-26b-a4b-it-maas",
     "region": "global"
    }
   ],
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "max_input_tokens": 262144,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-4-26b-a4b-it-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma-4-26b-a4b-it-maas"
    }
   ]
  },
  {
   "slug": "google/gemma-4-26b-a4b-uncensored",
   "model_name": "gemma-4-26b-a4b-uncensored",
   "display_name": "Gemma 4 26B A4B Uncensored TEE",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "TEE/gemma-4-26b-a4b-uncensored"
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2026-05-23",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "TEE/gemma-4-26b-a4b-uncensored"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 26B A4B Uncensored TEE"
    }
   ]
  },
  {
   "slug": "google/gemma-4-31b",
   "model_name": "gemma-4-31b",
   "display_name": "Gemma 4 31B IT",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "provider_model_id": "google.gemma-4-31b",
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google.gemma-4-31b",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google.gemma-4-31b",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google.gemma-4-31b",
     "region": "us-west-2"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.285409875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57081975"
      }
     }
    },
    {
     "provider": "cerebras",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.49"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-4-31b"
    }
   ],
   "intro": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
   "released_at": "2026-04-02",
   "max_input_tokens": 131072,
   "max_output_tokens": 40960,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "status": "beta",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google.gemma-4-31b",
    "google/gemma-4-31b"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.57185374",
     "new": "0.57081975"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28592687",
     "new": "0.285409875"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.571632985",
     "new": "0.57185374"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2858164925",
     "new": "0.28592687"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.572070715",
     "new": "0.571632985"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2860353575",
     "new": "0.2858164925"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.57184042",
     "new": "0.572070715"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28592021",
     "new": "0.2860353575"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.571998935",
     "new": "0.57184042"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2859994675",
     "new": "0.28592021"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.5690485",
     "new": "0.571998935"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28452425",
     "new": "0.2859994675"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B IT"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled",
   "model_name": "Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled",
   "display_name": "Gemma 4 31B Claude 4.6 Opus Reasoning Distilled",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0306"
      }
     }
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2026-05-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B Claude 4.6 Opus Reasoning Distilled"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-Cognitive-Unshackled",
   "model_name": "Gemma-4-31B-Cognitive-Unshackled",
   "display_name": "Gemma 4 31B Cognitive Unshackled",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B Cognitive Unshackled"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-DarkIdol",
   "model_name": "Gemma-4-31B-DarkIdol",
   "display_name": "Gemma 4 31B DarkIdol",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B DarkIdol"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-Fabled",
   "model_name": "Gemma-4-31B-Fabled",
   "display_name": "Gemma 4 31B Fabled",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "gemma-4-31B-Fabled"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemma-4-31B-Fabled"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "listed",
     "note": "Gemma 4 31B Fabled"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-Garnet",
   "model_name": "Gemma-4-31B-Garnet",
   "display_name": "Gemma 4 31B Garnet",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "gemma-4-31B-Garnet"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemma-4-31B-Garnet"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "listed",
     "note": "Gemma 4 31B Garnet"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-GarnetV2",
   "model_name": "Gemma-4-31B-GarnetV2",
   "display_name": "Gemma 4 31B Garnet V2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B Garnet V2"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-Gemopus",
   "model_name": "Gemma-4-31B-Gemopus",
   "display_name": "Gemma 4 31B Gemopus",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B Gemopus"
    }
   ]
  },
  {
   "slug": "google/gemma-4-31b-it",
   "model_name": "gemma-4-31b-it",
   "display_name": "Gemma 4 31B IT",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "models-dev+pydantic-prices+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39998"
      }
     }
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.065"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "google/gemma-4-31B-it"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0199999995"
      }
     },
     "provider_model_id": "google/gemma-4-31B-it"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gemma-4-31B-it"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-4-31b-it"
    },
    {
     "provider": "friendli",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-31B-it"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-31B-it"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "lilac",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "Gemma-4-31B-it"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.026"
      }
     },
     "provider_model_id": "google/gemma-4-31B-it"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "deepinfra/google/gemma-4-31B-it"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "route/gemma-4-31b-it"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "gemma-4-31B-it"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-31B-it"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      }
     },
     "provider_model_id": "google/gemma-4-31B-it"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/gemma-4-31b-it"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "google/gemma-4-31B-it"
    }
   ],
   "intro": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
   "released_at": "2026-04-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2025-01",
   "docs_url": "https://cloud.sambanova.ai/plans/pricing",
   "benchmarks": {
    "intelligence_index": 29.4,
    "coding_index": 43.4,
    "agentic_index": 14.4
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95,
     "top_k": 64
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "Gemma-4-31B-it",
    "TEE/gemma-4-31b-it",
    "accounts/fireworks/models/gemma-4-31b-it",
    "deepinfra/google/gemma-4-31B-it",
    "gemma-4-31B-it",
    "google/gemma-4-31B-it",
    "google/gemma-4-31b-it",
    "google/gemma-4-31b-it:free",
    "google/gemma-4-31b-it:thinking",
    "pearl-ai/gemma-4-31b-it",
    "route/gemma-4-31b-it"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "google/gemma-4-31B-it-lora",
   "model_name": "gemma-4-31B-it-lora",
   "display_name": "gemma-4-31B-it-lora",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-4-31B-it-lora"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-4-31B-it-lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma-4-31B-it-lora"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-it-pearl",
   "model_name": "Gemma-4-31B-it-pearl",
   "display_name": "pearl-ai/Gemma-4-31B-it-pearl",
   "vendor": "google",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27999999999999997"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     },
     "provider_model_id": "pearl-ai/Gemma-4-31B-it-pearl"
    }
   ],
   "released_at": "2026-04-29",
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "pearl-ai/Gemma-4-31B-it-pearl"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "function_calling: true→false"
    },
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "pearl-ai/Gemma-4-31B-it-pearl"
    }
   ]
  },
  {
   "slug": "google/gemma-4-31B-it-turbo",
   "model_name": "gemma-4-31B-it-turbo",
   "display_name": "google/gemma-4-31B-it-turbo",
   "vendor": "google",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.37"
      }
     },
     "provider_model_id": "google/gemma-4-31B-it-turbo"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true,
    "reasoning": true,
    "pdf_input": true
   },
   "max_output_tokens": 262144,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-4-31B-it-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "google/gemma-4-31B-it-turbo"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-K1-v5",
   "model_name": "Gemma-4-31B-K1-v5",
   "display_name": "Gemma 4 31B K1 v5",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "gemma-4-31B-K1-v5"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemma-4-31B-K1-v5"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "listed",
     "note": "Gemma 4 31B K1 v5"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-Larkspur-v0.5",
   "model_name": "Gemma-4-31B-Larkspur-v0.5",
   "display_name": "Gemma 4 31B Larkspur v0.5",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "gemma-4-31B-Larkspur-v0.5"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemma-4-31B-Larkspur-v0.5"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "listed",
     "note": "Gemma 4 31B Larkspur v0.5"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-MeroMero",
   "model_name": "Gemma-4-31B-MeroMero",
   "display_name": "Gemma 4 31B MeroMero",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "gemma-4-31B-MeroMero"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "gemma-4-31B-MeroMero"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "listed",
     "note": "Gemma 4 31B MeroMero"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-Musica-v1",
   "model_name": "Gemma-4-31B-Musica-v1",
   "display_name": "Gemma 4 31B Musica v1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "music_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B Musica v1"
    }
   ]
  },
  {
   "slug": "google/gemma-4-31b-n",
   "model_name": "gemma-4-31b-n",
   "display_name": "Gemma-4-31B-N",
   "vendor": "google",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1414"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.404"
      }
     }
    }
   ],
   "released_at": "2026-04-02",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma-4-31B-N"
    }
   ]
  },
  {
   "slug": "google/Gemma-4-31B-Queen",
   "model_name": "Gemma-4-31B-Queen",
   "display_name": "Gemma 4 31B Queen",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B Queen"
    }
   ]
  },
  {
   "slug": "google/gemma-4-31B-turbo-TEE",
   "model_name": "gemma-4-31B-turbo-TEE",
   "display_name": "gemma 4 31B turbo TEE",
   "vendor": "google",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.37"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "google/gemma-4-31B-turbo-TEE"
    }
   ],
   "intro": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
   "released_at": "2026-04-02",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-4-31B-turbo-TEE"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma 4 31B turbo TEE"
    }
   ]
  },
  {
   "slug": "google/gemma-4-E2B-it",
   "model_name": "gemma-4-E2B-it",
   "display_name": "gemma-4-E2B-it",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-4-E2B-it"
    }
   ],
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-4-E2B-it"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma-4-E2B-it"
    }
   ]
  },
  {
   "slug": "google/gemma-4-E4B-it",
   "model_name": "gemma-4-E4B-it",
   "display_name": "gemma-4-E4B-it",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/gemma-4-E4B-it"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma-4-E4B-it"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma-4-E4B-it"
    }
   ]
  },
  {
   "slug": "google/gemma-4-E4B-it-IQ4_XS",
   "model_name": "gemma-4-E4B-it-IQ4_XS",
   "display_name": "Gemma 4 E4B Instruct (IQ4_XS)",
   "vendor": "google",
   "pricing": [
    {
     "provider": "atomic-chat",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2026-04-02",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 E4B Instruct (IQ4_XS)"
    }
   ]
  },
  {
   "slug": "google/gemma-4-E4B-it-MLX-4bit",
   "model_name": "gemma-4-E4B-it-MLX-4bit",
   "display_name": "Gemma 4 E4B Instruct (MLX 4-bit)",
   "vendor": "google",
   "pricing": [
    {
     "provider": "atomic-chat",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2026-04-02",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 E4B Instruct (MLX 4-bit)"
    }
   ]
  },
  {
   "slug": "google/gemma-4-uncensored",
   "model_name": "gemma-4-uncensored",
   "display_name": "Gemma 4 Uncensored",
   "vendor": "google",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2026-04-13",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 Uncensored"
    }
   ]
  },
  {
   "slug": "google/gemma-7b",
   "model_name": "gemma-7b",
   "display_name": "Gemma 7B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-7b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/gemma-7b"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/gemma-7b",
    "google/gemma-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 7B"
    }
   ]
  },
  {
   "slug": "google/gemma-7b-it",
   "model_name": "gemma-7b-it",
   "display_name": "Gemma 7B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma-7b-it"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/gemma-7b-it"
   ],
   "intro_i18n": {
    "zh-CN": "Gemma 7B 是一款适用于中小规模任务的高性价比模型。",
    "zh-TW": "Gemma 7B 是一款適合中小型任務的高性價比模型。",
    "ja-JP": "Gemma 7B は、小規模から中規模のタスクに最適なコストパフォーマンスを提供します。",
    "ru-RU": "Gemma 7B — экономичное решение для задач малого и среднего масштаба."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 7B"
    }
   ]
  },
  {
   "slug": "google/Gemma-SEA-LION-v4-27B-IT",
   "model_name": "Gemma-SEA-LION-v4-27B-IT",
   "display_name": "Gemma Sea Lion V4 27B It",
   "vendor": "google",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     },
     "provider_model_id": "workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.351"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.555"
      }
     },
     "provider_model_id": "@cf/aisingapore/gemma-sea-lion-v4-27b-it"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "aisingapore/Gemma-SEA-LION-v4-27B-IT"
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-09-23",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "@cf/aisingapore/gemma-sea-lion-v4-27b-it",
    "aisingapore/Gemma-SEA-LION-v4-27B-IT",
    "workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma Sea Lion V4 27B It"
    }
   ]
  },
  {
   "slug": "google/gemma2-9b-it",
   "model_name": "gemma2-9b-it",
   "display_name": "Google Gemma 2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gemma2-9b-it"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2024-06-25",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/gemma2-9b-it"
   ],
   "intro_i18n": {
    "zh-CN": "Gemma 2 9B 针对特定任务与工具集成进行了优化。",
    "zh-TW": "Gemma 2 9B 專為特定任務與工具整合進行優化。",
    "ja-JP": "Gemma 2 9B は、特定タスクやツール統合に最適化されたモデルです。",
    "ru-RU": "Gemma 2 9B оптимизирована для выполнения конкретных задач и интеграции с инструментами."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Google Gemma 2"
    }
   ]
  },
  {
   "slug": "google/gemma3:12b",
   "model_name": "gemma3:12b",
   "display_name": "gemma3:12b",
   "vendor": "google",
   "pricing": [],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2024-12-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma3:12b"
    }
   ]
  },
  {
   "slug": "google/gemma3:27b",
   "model_name": "gemma3:27b",
   "display_name": "gemma3:27b",
   "vendor": "google",
   "pricing": [],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-07-27",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma3:27b"
    }
   ]
  },
  {
   "slug": "google/gemma3:4b",
   "model_name": "gemma3:4b",
   "display_name": "gemma3:4b",
   "vendor": "google",
   "pricing": [],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2024-12-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma3:4b"
    }
   ]
  },
  {
   "slug": "google/gemma4",
   "model_name": "gemma4",
   "display_name": "gemma4",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "google/gemma4"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.285409875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57081975"
      }
     },
     "provider_model_id": "google/gemma4"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true,
    "open_weights": true
   },
   "released_at": "2026-04-02",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/gemma4"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.57185374",
     "new": "0.57081975"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28592687",
     "new": "0.285409875"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.571632985",
     "new": "0.57185374"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2858164925",
     "new": "0.28592687"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.572070715",
     "new": "0.571632985"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2860353575",
     "new": "0.2858164925"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.57184042",
     "new": "0.572070715"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28592021",
     "new": "0.2860353575"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.571998935",
     "new": "0.57184042"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2859994675",
     "new": "0.28592021"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.5690485",
     "new": "0.571998935"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28452425",
     "new": "0.2859994675"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma4"
    }
   ]
  },
  {
   "slug": "google/gemma4-31b",
   "model_name": "gemma4-31b",
   "display_name": "Gemma 4 31B IT",
   "vendor": "google",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.285409875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57081975"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "TEE/gemma4-31b"
    },
    {
     "provider": "tinfoil",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "intro": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
   "released_at": "2026-04-02",
   "max_input_tokens": 256000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "TEE/gemma4-31b",
    "TEE/gemma4-31b:thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.57185374",
     "new": "0.57081975"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28592687",
     "new": "0.285409875"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.571632985",
     "new": "0.57185374"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2858164925",
     "new": "0.28592687"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.572070715",
     "new": "0.571632985"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2860353575",
     "new": "0.2858164925"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.57184042",
     "new": "0.572070715"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28592021",
     "new": "0.2860353575"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.571998935",
     "new": "0.57184042"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2859994675",
     "new": "0.28592021"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.5690485",
     "new": "0.571998935"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.28452425",
     "new": "0.2859994675"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Gemma 4 31B IT"
    }
   ]
  },
  {
   "slug": "google/gemma4:31b",
   "model_name": "gemma4:31b",
   "display_name": "gemma4:31b",
   "vendor": "google",
   "pricing": [],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2026-04-02",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma4:31b"
    }
   ]
  },
  {
   "slug": "google/gmn-2.5-fls-lt-pw-06-17",
   "model_name": "gmn-2.5-fls-lt-pw-06-17",
   "display_name": "Google Gemini 2.5 Flash",
   "vendor": "google",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "pa/gmn-2.5-fls-lt-pw-06-17"
    }
   ],
   "intro": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, allowing fine-tuned control over its reasoning process.",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "pa/gmn-2.5-fls-lt-pw-06-17"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Google Gemini 2.5 Flash"
    }
   ]
  },
  {
   "slug": "google/google-gemma-2-27b",
   "model_name": "google-gemma-2-27b",
   "display_name": "gemma-2-27b",
   "vendor": "google",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18000000000000002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18000000000000002"
      }
     }
    }
   ],
   "released_at": "2025-08-06",
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gemma-2-27b"
    }
   ]
  },
  {
   "slug": "google/google-gemma-3-12b-it",
   "model_name": "google-gemma-3-12b-it",
   "display_name": "google-gemma-3-12b-it",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "google-gemma-3-12b-it"
    }
   ]
  },
  {
   "slug": "google/google-gemma-3-27b-it",
   "model_name": "google-gemma-3-27b-it",
   "display_name": "Google Gemma 3 27B Instruct",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2025-11-04",
   "max_input_tokens": 198000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-07",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Google Gemma 3 27B Instruct"
    }
   ]
  },
  {
   "slug": "google/google-gemma-3-4b-it",
   "model_name": "google-gemma-3-4b-it",
   "display_name": "google-gemma-3-4b-it",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "google-gemma-3-4b-it"
    }
   ]
  },
  {
   "slug": "google/google-gemma-4-26b-a4b-it",
   "model_name": "google-gemma-4-26b-a4b-it",
   "display_name": "Google Gemma 4 26B A4B Instruct",
   "vendor": "google",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments",
   "released_at": "2026-04-02",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Google Gemma 4 26B A4B Instruct"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "completion",
     "old": "0.5",
     "new": "0.4"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "prompt",
     "old": "0.1625",
     "new": "0.13"
    }
   ]
  },
  {
   "slug": "google/google-gemma-4-31b-it",
   "model_name": "google-gemma-4-31b-it",
   "display_name": "Google Gemma 4 31B Instruct",
   "vendor": "google",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     }
    }
   ],
   "intro": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
   "released_at": "2026-04-03",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gemma",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Google Gemma 4 31B Instruct"
    }
   ]
  },
  {
   "slug": "google/google-paligemma",
   "model_name": "google-paligemma",
   "display_name": "paligemma",
   "vendor": "google",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/google-paligemma"
    }
   ],
   "intro": "Gemini multimodal model for text, image, audio, video, and document tasks",
   "released_at": "2024-05-14",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/google-paligemma"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "paligemma"
    }
   ]
  },
  {
   "slug": "google/google.gemma-4-e2b",
   "model_name": "google.gemma-4-e2b",
   "display_name": "google.gemma-4-e2b",
   "vendor": "google",
   "pricing": [
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "google.gemma-4-e2b"
    }
   ]
  },
  {
   "slug": "google/imagen-3",
   "model_name": "imagen-3",
   "display_name": "Imagen-3",
   "vendor": "google",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-10-15",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "imagen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-3"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Imagen-3"
    }
   ]
  },
  {
   "slug": "google/imagen-3-fast",
   "model_name": "imagen-3-fast",
   "display_name": "Imagen-3-Fast",
   "vendor": "google",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-10-17",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "imagen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-3-fast"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Imagen-3-Fast"
    }
   ]
  },
  {
   "slug": "google/imagen-3.0-capability-001",
   "model_name": "imagen-3.0-capability-001",
   "display_name": "imagen-3.0-capability-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-east2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "australia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "eu"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-north1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-southwest1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west6"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west8"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "southamerica-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east5"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-west4"
    }
   ],
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-3.0-capability-001"
    }
   ]
  },
  {
   "slug": "google/imagen-3.0-capability-002",
   "model_name": "imagen-3.0-capability-002",
   "display_name": "imagen-3.0-capability-002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-3.0-capability-002"
    }
   ]
  },
  {
   "slug": "google/imagen-3.0-fast-generate-001",
   "model_name": "imagen-3.0-fast-generate-001",
   "display_name": "imagen-3.0-fast-generate-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-east2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "australia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-north1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-southwest1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west6"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west8"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "me-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "me-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "me-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "southamerica-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-east4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-east5"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-west4"
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "google/imagen-3.0-generate-001",
   "model_name": "imagen-3.0-generate-001",
   "display_name": "imagen-3.0-generate-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-east2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "australia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "eu"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-north1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-southwest1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west6"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west8"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "southamerica-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east5"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-west4"
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "google/imagen-3.0-generate-002",
   "model_name": "imagen-3.0-generate-002",
   "display_name": "imagen-3.0-generate-002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-east2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "australia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-north1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-southwest1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west6"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west8"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "southamerica-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east5"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-west4"
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "deprecated": true,
   "model_type": "image_generation",
   "deprecation_date": "2025-11-10",
   "capabilities": {
    "image_output": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "google/imagen-4",
   "model_name": "imagen-4",
   "display_name": "Imagen-4",
   "vendor": "google",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-05-22",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "imagen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-4"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Imagen-4"
    }
   ]
  },
  {
   "slug": "google/imagen-4-fast",
   "model_name": "imagen-4-fast",
   "display_name": "Imagen-4-Fast",
   "vendor": "google",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-06-25",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "imagen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-4-fast"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Imagen-4-Fast"
    }
   ]
  },
  {
   "slug": "google/imagen-4-ultra",
   "model_name": "imagen-4-ultra",
   "display_name": "Imagen-4-Ultra",
   "vendor": "google",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-05-24",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "imagen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-4-ultra"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Imagen-4-Ultra"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-fast",
   "model_name": "imagen-4.0-fast",
   "display_name": "Imagen 4 Fast",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "provider_model_id": "google/imagen-4.0-fast"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-05-20",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "imagen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-4.0-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Imagen 4 Fast"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-fast-generate-001",
   "model_name": "imagen-4.0-fast-generate-001",
   "display_name": "imagen-4.0-fast-generate-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-east2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "australia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "eu"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-north1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-southwest1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west6"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west8"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "me-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "me-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "me-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "southamerica-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-east4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-east5"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "region": "us-west4"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "provider_model_id": "google/imagen-4.0-fast-generate-001"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "max_input_tokens": 480,
   "released_at": "2025-08-15",
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "family": "imagen",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-4.0-fast-generate-001"
   ],
   "intro_i18n": {
    "zh-CN": "Imagen 第四代文本生成图像模型系列 Fast 版本",
    "zh-TW": "Imagen 第四代文字轉圖像模型系列的快速版本",
    "ja-JP": "Imagen第4世代テキスト→画像モデルシリーズの高速版です。",
    "ru-RU": "Серия моделей генерации изображений Imagen 4-го поколения, версия Fast."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-02",
     "kind": "limit",
     "old": "0",
     "new": "8192",
     "note": "max_output_tokens"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-fast-generate-001-gt-128k",
   "model_name": "imagen-4.0-fast-generate-001-gt-128k",
   "display_name": "imagen-4.0-fast-generate-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-fast-generate-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-fast-generate-001-lte-128k",
   "model_name": "imagen-4.0-fast-generate-001-lte-128k",
   "display_name": "imagen-4.0-fast-generate-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-fast-generate-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-fast-generate-preview-06-06",
   "model_name": "imagen-4.0-fast-generate-preview-06-06",
   "display_name": "imagen-4.0-fast-generate-preview-06-06",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-fast-generate-preview-06-06"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-generate-001",
   "model_name": "imagen-4.0-generate-001",
   "display_name": "imagen-4.0-generate-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-east2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "australia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-north1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-southwest1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west6"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west8"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "me-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "southamerica-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-east5"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "region": "us-west4"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "google/imagen-4.0-generate-001"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "max_input_tokens": 480,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "max_output_tokens": 8192,
   "released_at": "2025-08-15",
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "family": "imagen",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-4.0-generate-001"
   ],
   "intro_i18n": {
    "zh-CN": "Imagen 第四代文本生成图像模型系列",
    "zh-TW": "Imagen 第四代文字轉圖像模型系列",
    "ja-JP": "Imagen第4世代テキスト→画像モデルシリーズです。",
    "ru-RU": "Серия моделей генерации изображений Imagen 4-го поколения."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-02",
     "kind": "limit",
     "old": "0",
     "new": "8192",
     "note": "max_output_tokens"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-generate-001-gt-128k",
   "model_name": "imagen-4.0-generate-001-gt-128k",
   "display_name": "imagen-4.0-generate-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-generate-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-generate-001-lte-128k",
   "model_name": "imagen-4.0-generate-001-lte-128k",
   "display_name": "imagen-4.0-generate-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-generate-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-generate-preview-05-20",
   "model_name": "imagen-4.0-generate-preview-05-20",
   "display_name": "imagen-4.0-generate-preview-05-20",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-generate-preview-05-20"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-generate-preview-06-06",
   "model_name": "imagen-4.0-generate-preview-06-06",
   "display_name": "imagen-4.0-generate-preview-06-06",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-generate-preview-06-06"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-preview",
   "model_name": "imagen-4.0-preview",
   "display_name": "imagen-4.0-preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "google/imagen-4.0-preview"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-4.0-preview"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-preview"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-ultra",
   "model_name": "imagen-4.0-ultra",
   "display_name": "Imagen 4 Ultra",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "provider_model_id": "google/imagen-4.0-ultra"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-05-20",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "imagen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-4.0-ultra"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Imagen 4 Ultra"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-ultra-generate-001",
   "model_name": "imagen-4.0-ultra-generate-001",
   "display_name": "imagen-4.0-ultra-generate-001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "asia-east2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "asia-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "australia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "europe-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "europe-north1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "europe-southwest1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "europe-west6"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "europe-west8"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "me-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "me-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "me-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "southamerica-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "us-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "us-east4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "us-east5"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "us-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "us-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "region": "us-west4"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "provider_model_id": "google/imagen-4.0-ultra-generate-001"
    },
    {
     "provider": "vertexai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "max_input_tokens": 480,
   "released_at": "2025-08-15",
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "family": "imagen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/imagen-4.0-ultra-generate-001"
   ],
   "intro_i18n": {
    "zh-CN": "Imagen 第四代文本生成图像模型系列 Ultra 版本",
    "zh-TW": "Imagen 第四代文字轉圖像模型系列的超高版本",
    "ja-JP": "Imagen第4世代テキスト→画像モデルシリーズのUltraバージョンです。",
    "ru-RU": "Серия моделей генерации изображений Imagen 4-го поколения, версия Ultra."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-02",
     "kind": "limit",
     "old": "0",
     "new": "8192",
     "note": "max_output_tokens"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-ultra-generate-001-gt-128k",
   "model_name": "imagen-4.0-ultra-generate-001-gt-128k",
   "display_name": "imagen-4.0-ultra-generate-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-ultra-generate-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-ultra-generate-001-lte-128k",
   "model_name": "imagen-4.0-ultra-generate-001-lte-128k",
   "display_name": "imagen-4.0-ultra-generate-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-ultra-generate-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-ultra-generate-preview-05-20",
   "model_name": "imagen-4.0-ultra-generate-preview-05-20",
   "display_name": "imagen-4.0-ultra-generate-preview-05-20",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-ultra-generate-preview-05-20"
    }
   ]
  },
  {
   "slug": "google/imagen-4.0-ultra-generate-preview-06-06",
   "model_name": "imagen-4.0-ultra-generate-preview-06-06",
   "display_name": "imagen-4.0-ultra-generate-preview-06-06",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-4.0-ultra-generate-preview-06-06"
    }
   ]
  },
  {
   "slug": "google/imagen-product-recontext-preview-06-30",
   "model_name": "imagen-product-recontext-preview-06-30",
   "display_name": "imagen-product-recontext-preview-06-30",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.12"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagen-product-recontext-preview-06-30"
    }
   ]
  },
  {
   "slug": "google/imagen4/preview",
   "model_name": "imagen4/preview",
   "display_name": "Imagen 4",
   "vendor": "google",
   "pricing": [
    {
     "provider": "fal",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.05"
      }
     },
     "provider_model_id": "fal-ai/imagen4/preview"
    }
   ],
   "released_at": "2025-05-21",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "fal-ai/imagen4/preview"
   ],
   "intro_i18n": {
    "zh-CN": "来自 Google 的高质量图像生成模型。",
    "zh-TW": "來自 Google 的高品質圖像生成模型。",
    "ja-JP": "Google による高品質な画像生成モデルです。",
    "ru-RU": "Модель генерации изображений высокого качества от Google."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Imagen 4"
    }
   ]
  },
  {
   "slug": "google/language-v1-analyze-entity-sentiment",
   "model_name": "language-v1-analyze-entity-sentiment",
   "display_name": "language-v1-analyze-entity-sentiment",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "2"
      }
     },
     "provider_model_id": "google/language-v1-analyze-entity-sentiment"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/language-v1-analyze-entity-sentiment"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "language-v1-analyze-entity-sentiment"
    }
   ]
  },
  {
   "slug": "google/language-v1-analyze-syntax",
   "model_name": "language-v1-analyze-syntax",
   "display_name": "language-v1-analyze-syntax",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.5"
      }
     },
     "provider_model_id": "google/language-v1-analyze-syntax"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/language-v1-analyze-syntax"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "language-v1-analyze-syntax"
    }
   ]
  },
  {
   "slug": "google/learnlm-1.5-pro-experimental",
   "model_name": "learnlm-1.5-pro-experimental",
   "display_name": "learnlm-1.5-pro-experimental",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.502"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.506"
      }
     }
    }
   ],
   "docs_url": "https://aistudio.google.com",
   "max_input_tokens": 32767,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-05-14",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   }
  },
  {
   "slug": "google/lyria",
   "model_name": "lyria",
   "display_name": "Lyria",
   "vendor": "google",
   "pricing": [],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-06-04",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "lyria",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "audio_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/lyria"
   ],
   "model_type": "music_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Lyria"
    }
   ]
  },
  {
   "slug": "google/lyria-3-clip-preview",
   "model_name": "lyria-3-clip-preview",
   "display_name": "lyria-3-clip-preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      },
      "request": {
       "unit": "per_request",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/lyria-3-clip-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "request": {
       "unit": "per_request",
       "price": "0.04"
      }
     },
     "provider_model_id": "google/lyria-3-clip-preview"
    }
   ],
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "music_generation",
   "capabilities": {
    "vision": true,
    "audio_output": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2026-03-30",
   "family": "lyria",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/lyria-3-clip-preview"
   ]
  },
  {
   "slug": "google/lyria-3-pro-preview",
   "model_name": "lyria-3-pro-preview",
   "display_name": "lyria-3-pro-preview",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "request": {
       "unit": "per_request",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/lyria-3-pro-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "request": {
       "unit": "per_request",
       "price": "0.08"
      }
     },
     "provider_model_id": "google/lyria-3-pro-preview"
    }
   ],
   "docs_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "music_generation",
   "capabilities": {
    "vision": true,
    "audio_output": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "audio",
     "text"
    ]
   },
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2026-03-30",
   "family": "lyria",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/lyria-3-pro-preview"
   ]
  },
  {
   "slug": "google/medgemma-4b",
   "model_name": "medgemma-4b",
   "display_name": "MedGemma 4B",
   "vendor": "google",
   "pricing": [
    {
     "provider": "llmtr",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "llmtr/medgemma-4b"
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2026-04-26",
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "llmtr/medgemma-4b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MedGemma 4B"
    }
   ]
  },
  {
   "slug": "google/multimodalembedding",
   "model_name": "multimodalembedding",
   "display_name": "multimodalembedding",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "input_video_plus": {
       "unit": "per_request",
       "price": "0.002"
      },
      "input_video_standard": {
       "unit": "per_request",
       "price": "0.001"
      },
      "input_video_essential": {
       "unit": "per_request",
       "price": "0.0005"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "audio_input": {
       "unit": "per_second",
       "price": "0.0005"
      }
     },
     "provider_model_id": "google/multimodalembedding",
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "audio_input": {
       "unit": "per_second",
       "price": "0.0005"
      }
     },
     "provider_model_id": "google/multimodalembedding",
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "audio_input": {
       "unit": "per_second",
       "price": "0.0005"
      }
     },
     "provider_model_id": "google/multimodalembedding",
     "region": "us-central1"
    }
   ],
   "capabilities": {
    "vision": true,
    "video_input": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "multimodal_embedding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/multimodalembedding"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "multimodalembedding"
    }
   ]
  },
  {
   "slug": "google/nano-banana",
   "model_name": "nano-banana",
   "display_name": "Nano-Banana",
   "vendor": "google",
   "pricing": [
    {
     "provider": "fal",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.039"
      }
     },
     "provider_model_id": "fal-ai/nano-banana"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.021"
      }
     },
     "provider_model_id": "google/nano-banana"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-08-21",
   "max_input_tokens": 65536,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "nano-banana",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "fal-ai/nano-banana",
    "google/nano-banana"
   ],
   "intro_i18n": {
    "zh-CN": "Nano Banana 是 Google 最新、最快、最高效的原生多模态模型，支持通过对话生成与编辑图像。",
    "zh-TW": "Nano Banana 是 Google 最新、最快且最高效的原生多模態模型，支援透過對話進行圖像生成與編輯。",
    "ja-JP": "Nano Banana は Google による最新・最速・最も効率的なネイティブマルチモーダルモデルで、会話を通じた画像生成と編集が可能です。",
    "ru-RU": "Nano Banana — новейшая, самая быстрая и эффективная нативная мультимодальная модель от Google, поддерживающая генерацию и редактирование изображений в диалоговом режиме."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nano-Banana"
    }
   ]
  },
  {
   "slug": "google/nano-banana-2",
   "model_name": "nano-banana-2",
   "display_name": "nano-banana-2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "130"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "251.8"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5051"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.0303"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "image_output": true
   },
   "max_input_tokens": 65536,
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nano-Banana-2"
    }
   ]
  },
  {
   "slug": "google/nano-banana-2-lite",
   "model_name": "nano-banana-2-lite",
   "display_name": "Nano-Banana-2-Lite",
   "vendor": "google",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2525"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5152"
      }
     }
    }
   ],
   "released_at": "2026-06-30",
   "max_input_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nano-Banana-2-Lite"
    }
   ]
  },
  {
   "slug": "google/nano-banana-pro",
   "model_name": "nano-banana-pro",
   "display_name": "Nano-Banana-Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "130"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "251.8"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "google/nano-banana-pro"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-11-19",
   "max_input_tokens": 65536,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "nano-banana",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/nano-banana-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nano-Banana-Pro"
    }
   ]
  },
  {
   "slug": "google/nano-banana-pro-preview",
   "model_name": "nano-banana-pro-preview",
   "display_name": "Nano Banana Pro",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+llmdb",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0011"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nano Banana Pro"
    }
   ]
  },
  {
   "slug": "google/object-detector",
   "model_name": "object-detector",
   "display_name": "object-detector",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0016667"
      }
     },
     "provider_model_id": "google/object-detector"
    }
   ],
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/object-detector"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "object-detector"
    }
   ]
  },
  {
   "slug": "google/palm-2-chat-bison",
   "model_name": "palm-2-chat-bison",
   "display_name": "palm-2-chat-bison",
   "vendor": "google",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "google/palm-2-chat-bison"
    }
   ],
   "max_input_tokens": 9216,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/palm-2-chat-bison"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "palm-2-chat-bison"
    }
   ]
  },
  {
   "slug": "google/palm-2-codechat-bison",
   "model_name": "palm-2-codechat-bison",
   "display_name": "palm-2-codechat-bison",
   "vendor": "google",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "google/palm-2-codechat-bison"
    }
   ],
   "max_input_tokens": 7168,
   "max_output_tokens": 20070,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/palm-2-codechat-bison"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "palm-2-codechat-bison"
    }
   ]
  },
  {
   "slug": "google/parasail-gemma3-27b-it",
   "model_name": "parasail-gemma3-27b-it",
   "display_name": "parasail/parasail-gemma3-27b-it",
   "vendor": "google",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "parasail/parasail-gemma3-27b-it"
    }
   ],
   "released_at": "2025-03-14",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "parasail/parasail-gemma3-27b-it"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "parasail/parasail-gemma3-27b-it"
    }
   ]
  },
  {
   "slug": "google/people-blur",
   "model_name": "people-blur",
   "display_name": "people-blur",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0016666666666666668"
      }
     },
     "provider_model_id": "google/people-blur"
    }
   ],
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/people-blur"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "people-blur"
    }
   ]
  },
  {
   "slug": "google/ppe-detector",
   "model_name": "ppe-detector",
   "display_name": "ppe-detector",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00166667"
      }
     },
     "provider_model_id": "google/ppe-detector"
    }
   ],
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/ppe-detector"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ppe-detector"
    }
   ]
  },
  {
   "slug": "google/product-recognizer",
   "model_name": "product-recognizer",
   "display_name": "product-recognizer",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.000025"
      }
     },
     "provider_model_id": "google/product-recognizer"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/product-recognizer"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "product-recognizer"
    }
   ]
  },
  {
   "slug": "google/tag-recognizer",
   "model_name": "tag-recognizer",
   "display_name": "tag-recognizer",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.000025"
      }
     },
     "provider_model_id": "google/tag-recognizer"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/tag-recognizer"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "tag-recognizer"
    }
   ]
  },
  {
   "slug": "google/text-bison",
   "model_name": "text-bison",
   "display_name": "text-bison",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      }
     }
    }
   ],
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-bison"
    }
   ]
  },
  {
   "slug": "google/text-bison@001",
   "model_name": "text-bison@001",
   "display_name": "text-bison@001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-bison@001"
    }
   ]
  },
  {
   "slug": "google/text-bison@002",
   "model_name": "text-bison@002",
   "display_name": "text-bison@002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-bison@002"
    }
   ]
  },
  {
   "slug": "google/text-detector",
   "model_name": "text-detector",
   "display_name": "text-detector",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0015"
      }
     },
     "provider_model_id": "google/text-detector"
    }
   ],
   "modalities": {
    "input": [
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/text-detector"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-detector"
    }
   ]
  },
  {
   "slug": "google/text-embedding-005",
   "model_name": "text-embedding-005",
   "display_name": "Text Embedding 005",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-embedding-005"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-embedding-005"
    }
   ],
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2024-08-01",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "text-embedding",
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/text-embedding-005"
   ],
   "intro_i18n": {
    "zh-CN": "一款专注于英文任务的文本嵌入模型，针对代码和英文任务进行了优化。",
    "zh-TW": "一款專注於英文的文字嵌入模型，針對程式與英文任務進行最佳化。",
    "ja-JP": "コードおよび英語タスクに最適化された英語中心のテキスト埋め込みモデルです。",
    "ru-RU": "Модель встраивания текста, ориентированная на английский язык, оптимизирована для задач на английском и программировании."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Text Embedding 005"
    }
   ]
  },
  {
   "slug": "google/text-multilingual-embedding-002",
   "model_name": "text-multilingual-embedding-002",
   "display_name": "Text Multilingual Embedding 002",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "asia-east2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "asia-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "australia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "eu"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "europe-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "europe-north1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "europe-southwest1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "europe-west6"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "europe-west8"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "me-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "me-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "me-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "southamerica-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "us"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "us-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "us-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "us-east4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "us-east5"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "us-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "us-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002",
     "region": "us-west4"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "google/text-multilingual-embedding-002"
    }
   ],
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2024-03-01",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "text-embedding",
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/text-multilingual-embedding-002"
   ],
   "intro_i18n": {
    "zh-CN": "一款多语言文本嵌入模型，针对跨语言任务进行了优化，支持多种语言。",
    "zh-TW": "一款多語言文字嵌入模型，針對跨語言任務進行最佳化，支援多種語言。",
    "ja-JP": "多言語間タスクに最適化された多言語テキスト埋め込みモデルです。",
    "ru-RU": "Многоязычная модель встраивания текста, оптимизированная для кросс-языковых задач на множестве языков."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Text Multilingual Embedding 002"
    }
   ]
  },
  {
   "slug": "google/text-translation",
   "model_name": "text-translation",
   "display_name": "text-translation",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "20"
      }
     },
     "provider_model_id": "google/text-translation"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_understanding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/text-translation"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-translation"
    }
   ]
  },
  {
   "slug": "google/textembedding-gecko",
   "model_name": "textembedding-gecko",
   "display_name": "textembedding-gecko",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.2"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "textembedding-gecko"
    }
   ]
  },
  {
   "slug": "google/textembedding-gecko-multilingual",
   "model_name": "textembedding-gecko-multilingual",
   "display_name": "textembedding-gecko-multilingual",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "textembedding-gecko-multilingual"
    }
   ]
  },
  {
   "slug": "google/textembedding-gecko-multilingual@001",
   "model_name": "textembedding-gecko-multilingual@001",
   "display_name": "textembedding-gecko-multilingual@001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "textembedding-gecko-multilingual@001"
    }
   ]
  },
  {
   "slug": "google/textembedding-gecko@001",
   "model_name": "textembedding-gecko@001",
   "display_name": "textembedding-gecko@001",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "textembedding-gecko@001"
    }
   ]
  },
  {
   "slug": "google/textembedding-gecko@003",
   "model_name": "textembedding-gecko@003",
   "display_name": "textembedding-gecko@003",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.2"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "textembedding-gecko@003"
    }
   ]
  },
  {
   "slug": "google/translate-llm",
   "model_name": "translate-llm",
   "display_name": "translate-llm",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "10"
      }
     },
     "provider_model_id": "google/translate-llm"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/translate-llm"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "translate-llm"
    }
   ]
  },
  {
   "slug": "google/veo-2",
   "model_name": "veo-2",
   "display_name": "Veo-2",
   "vendor": "google",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2024-12-02",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "veo",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-2"
   ],
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo-2"
    }
   ]
  },
  {
   "slug": "google/veo-2.0",
   "model_name": "veo-2.0",
   "display_name": "veo-2.0",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "2.5"
      }
     },
     "provider_model_id": "google/veo-2.0"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-2.0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-2.0"
    }
   ]
  },
  {
   "slug": "google/veo-2.0-generate-001",
   "model_name": "veo-2.0-generate-001",
   "display_name": "Veo 2",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.35"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "video_output": {
       "unit": "per_second",
       "price": "0.35"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "asia-east2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "asia-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "australia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "europe-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "europe-north1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "europe-southwest1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "europe-west6"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "europe-west8"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "me-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "me-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "me-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "southamerica-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "us-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "us-east4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "us-east5"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "us-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "us-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "region": "us-west4"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "max_input_tokens": 480,
   "max_output_tokens": 8192,
   "released_at": "2025-04-09",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "我们最先进的视频生成模型，供Gemini API付费用户使用。",
    "zh-TW": "我們最先進的影像生成模型，供Gemini API付費層的開發者使用。",
    "ja-JP": "Gemini APIの有料ティアで開発者が利用可能な最先端のビデオ生成モデル。",
    "ru-RU": "Наша передовая модель генерации видео, доступная разработчикам на платной основе через API Gemini."
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo 2"
    }
   ]
  },
  {
   "slug": "google/veo-2.0-generate-001-gt-128k",
   "model_name": "veo-2.0-generate-001-gt-128k",
   "display_name": "veo-2.0-generate-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-2.0-generate-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/veo-2.0-generate-001-lte-128k",
   "model_name": "veo-2.0-generate-001-lte-128k",
   "display_name": "veo-2.0-generate-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.35"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-2.0-generate-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/veo-3",
   "model_name": "veo-3",
   "display_name": "Veo-3",
   "vendor": "google",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-05-21",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "veo",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3"
   ],
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo-3"
    }
   ]
  },
  {
   "slug": "google/veo-3-fast",
   "model_name": "veo-3-fast",
   "display_name": "Veo-3-Fast",
   "vendor": "google",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-10-13",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "veo",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3-fast"
   ],
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo-3-Fast"
    }
   ]
  },
  {
   "slug": "google/veo-3.0",
   "model_name": "veo-3.0",
   "display_name": "veo-3.0",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "1.6"
      }
     },
     "provider_model_id": "google/veo-3.0"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.0"
    }
   ]
  },
  {
   "slug": "google/veo-3.0-audio",
   "model_name": "veo-3.0-audio",
   "display_name": "veo-3.0-audio",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "3.2"
      }
     },
     "provider_model_id": "google/veo-3.0-audio"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video",
     "audio"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.0-audio"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.0-audio"
    }
   ]
  },
  {
   "slug": "google/veo-3.0-fast",
   "model_name": "veo-3.0-fast",
   "display_name": "veo-3.0-fast",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.8"
      }
     },
     "provider_model_id": "google/veo-3.0-fast"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.0-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.0-fast"
    }
   ]
  },
  {
   "slug": "google/veo-3.0-fast-audio",
   "model_name": "veo-3.0-fast-audio",
   "display_name": "veo-3.0-fast-audio",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "1.2"
      }
     },
     "provider_model_id": "google/veo-3.0-fast-audio"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video",
     "audio"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.0-fast-audio"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.0-fast-audio"
    }
   ]
  },
  {
   "slug": "google/veo-3.0-fast-generate-001",
   "model_name": "veo-3.0-fast-generate-001",
   "display_name": "Veo 3 fast",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "video_output": {
       "unit": "per_second",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/veo-3.0-fast-generate-001",
     "region": "global"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_720p_audio": {
       "unit": "per_second",
       "price": "0.15"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_1080p_audio": {
       "unit": "per_second",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/veo-3.0-fast-generate-001"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video",
     "audio"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "audio_output": true
   },
   "max_input_tokens": 480,
   "max_output_tokens": 8192,
   "released_at": "2025-11-11",
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "family": "veo",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.0-fast-generate-001"
   ],
   "intro_i18n": {
    "zh-CN": "我们稳定的视频生成模型，供Gemini API付费用户使用。",
    "zh-TW": "我們穩定的影像生成模型，供Gemini API付費層的開發者使用。",
    "ja-JP": "Gemini APIの有料ティアで開発者が利用可能な安定したビデオ生成モデル。",
    "ru-RU": "Наша стабильная модель генерации видео, доступная разработчикам на платной основе через API Gemini."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo 3 fast"
    }
   ]
  },
  {
   "slug": "google/veo-3.0-fast-generate-001-gt-128k",
   "model_name": "veo-3.0-fast-generate-001-gt-128k",
   "display_name": "veo-3.0-fast-generate-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.0-fast-generate-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/veo-3.0-fast-generate-001-lte-128k",
   "model_name": "veo-3.0-fast-generate-001-lte-128k",
   "display_name": "veo-3.0-fast-generate-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.0-fast-generate-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/veo-3.0-generate-001",
   "model_name": "veo-3.0-generate-001",
   "display_name": "Veo 3",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "video_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "asia-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "asia-east2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "asia-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "australia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "europe-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "europe-north1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "europe-southwest1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "europe-west6"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "europe-west8"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "global"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "me-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "me-central2"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "me-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "southamerica-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "us-east1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "us-east4"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "us-east5"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "us-south1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "us-west1"
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "region": "us-west4"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.2"
      },
      "video_output_720p_audio": {
       "unit": "per_second",
       "price": "0.4"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.2"
      },
      "video_output_1080p_audio": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/veo-3.0-generate-001"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video",
     "audio"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "audio_output": true
   },
   "max_input_tokens": 480,
   "max_output_tokens": 8192,
   "released_at": "2025-11-11",
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "family": "veo",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.0-generate-001"
   ],
   "intro_i18n": {
    "zh-CN": "我们稳定的视频生成模型，供Gemini API付费用户使用。",
    "zh-TW": "我們穩定的影像生成模型，供Gemini API付費層的開發者使用。",
    "ja-JP": "Gemini APIの有料ティアで開発者が利用可能な安定したビデオ生成モデル。",
    "ru-RU": "Наша стабильная модель генерации видео, доступная разработчикам на платной основе через API Gemini."
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo 3"
    }
   ]
  },
  {
   "slug": "google/veo-3.0-generate-001-gt-128k",
   "model_name": "veo-3.0-generate-001-gt-128k",
   "display_name": "veo-3.0-generate-001-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.4"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.0-generate-001-gt-128k"
    }
   ]
  },
  {
   "slug": "google/veo-3.0-generate-001-lte-128k",
   "model_name": "veo-3.0-generate-001-lte-128k",
   "display_name": "veo-3.0-generate-001-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.4"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.0-generate-001-lte-128k"
    }
   ]
  },
  {
   "slug": "google/veo-3.1",
   "model_name": "veo-3.1",
   "display_name": "Veo-3.1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.4"
      }
     },
     "provider_model_id": "google/veo-3.1"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/veo-3.1"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-10-15",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "veo",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "audio_output": true,
    "pdf_input": true
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo-3.1"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-fast",
   "model_name": "veo-3.1-fast",
   "display_name": "Veo-3.1-Fast",
   "vendor": "google",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.15"
      }
     },
     "provider_model_id": "google/veo-3.1-fast"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-10-15",
   "max_input_tokens": 480,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "veo",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "audio_output": true,
    "pdf_input": true
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.1-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo-3.1-Fast"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-fast-generate-001",
   "model_name": "veo-3.1-fast-generate-001",
   "display_name": "Veo 3.1 Fast Generate",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_720p_audio": {
       "unit": "per_second",
       "price": "0.15"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_1080p_audio": {
       "unit": "per_second",
       "price": "0.15"
      },
      "video_output_4k": {
       "unit": "per_second",
       "price": "0.3"
      },
      "video_output_4k_audio": {
       "unit": "per_second",
       "price": "0.35"
      }
     },
     "provider_model_id": "google/veo-3.1-fast-generate-001"
    }
   ],
   "capabilities": {},
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-10-15",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "veo",
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.1-fast-generate-001"
   ],
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "vision: true→false"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo 3.1 Fast Generate"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-fast-generate-preview",
   "model_name": "veo-3.1-fast-generate-preview",
   "display_name": "Veo 3.1 fast",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "video_output": {
       "unit": "per_second",
       "price": "0.35"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "capabilities": {},
   "max_input_tokens": 480,
   "max_output_tokens": 8192,
   "released_at": "2026-01-13",
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "我们最新的视频生成模型，供Gemini API付费用户使用。",
    "zh-TW": "我們最新的影像生成模型，供Gemini API付費層的開發者使用。",
    "ja-JP": "Gemini APIの有料ティアで開発者が利用可能な最新のビデオ生成モデル。",
    "ru-RU": "Наша последняя модель генерации видео, доступная разработчикам на платной основе через API Gemini."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo 3.1 fast"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-fast-generate-preview-gt-128k",
   "model_name": "veo-3.1-fast-generate-preview-gt-128k",
   "display_name": "veo-3.1-fast-generate-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.1-fast-generate-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-fast-generate-preview-lte-128k",
   "model_name": "veo-3.1-fast-generate-preview-lte-128k",
   "display_name": "veo-3.1-fast-generate-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.1-fast-generate-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-generate-001",
   "model_name": "veo-3.1-generate-001",
   "display_name": "Veo 3.1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.2"
      },
      "video_output_720p_audio": {
       "unit": "per_second",
       "price": "0.4"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.2"
      },
      "video_output_1080p_audio": {
       "unit": "per_second",
       "price": "0.4"
      },
      "video_output_4k": {
       "unit": "per_second",
       "price": "0.4"
      },
      "video_output_4k_audio": {
       "unit": "per_second",
       "price": "0.6"
      }
     },
     "provider_model_id": "google/veo-3.1-generate-001"
    }
   ],
   "capabilities": {},
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-10-15",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "veo",
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.1-generate-001"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo 3.1"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-generate-preview",
   "model_name": "veo-3.1-generate-preview",
   "display_name": "Veo 3.1",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "video_output": {
       "unit": "per_second",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "capabilities": {},
   "max_input_tokens": 480,
   "max_output_tokens": 8192,
   "released_at": "2026-01-13",
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "intro_i18n": {
    "zh-CN": "我们最新的视频生成模型，供Gemini API付费用户使用。",
    "zh-TW": "我們最新的影像生成模型，供Gemini API付費層的開發者使用。",
    "ja-JP": "Gemini APIの有料ティアで開発者が利用可能な最新のビデオ生成モデル。",
    "ru-RU": "Наша последняя модель генерации видео, доступная разработчикам на платной основе через API Gemini."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo 3.1"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-generate-preview-gt-128k",
   "model_name": "veo-3.1-generate-preview-gt-128k",
   "display_name": "veo-3.1-generate-preview-gt-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.4"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.1-generate-preview-gt-128k"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-generate-preview-lte-128k",
   "model_name": "veo-3.1-generate-preview-lte-128k",
   "display_name": "veo-3.1-generate-preview-lte-128k",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google",
     "official": true,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.4"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.1-generate-preview-lte-128k"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-lite",
   "model_name": "veo-3.1-lite",
   "display_name": "veo-3.1-lite",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/veo-3.1-lite"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.1-lite"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.1-lite"
    }
   ]
  },
  {
   "slug": "google/veo-3.1-test-debug",
   "model_name": "veo-3.1-test-debug",
   "display_name": "veo-3.1-test-debug",
   "vendor": "google",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "google/veo-3.1-test-debug"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo-3.1-test-debug"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.1-test-debug"
    }
   ]
  },
  {
   "slug": "google/veo3.1",
   "model_name": "veo3.1",
   "display_name": "Veo 3.1",
   "vendor": "google",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-05-01",
   "max_input_tokens": 400000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "veo",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo3.1"
   ],
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo 3.1"
    }
   ]
  },
  {
   "slug": "google/veo3.1-fast",
   "model_name": "veo3.1-fast",
   "display_name": "Veo 3.1 Fast",
   "vendor": "google",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-05-01",
   "max_input_tokens": 400000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "veo",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo3.1-fast"
   ],
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo 3.1 Fast"
    }
   ]
  },
  {
   "slug": "google/veo3.1-lite",
   "model_name": "veo3.1-lite",
   "display_name": "Veo 3.1 Lite",
   "vendor": "google",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-05-01",
   "max_input_tokens": 400000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "veo",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/veo3.1-lite"
   ],
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veo 3.1 Lite"
    }
   ]
  },
  {
   "slug": "google/video-speech-transcription",
   "model_name": "video-speech-transcription",
   "display_name": "video-speech-transcription",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0008"
      }
     },
     "provider_model_id": "google/video-speech-transcription"
    }
   ],
   "modalities": {
    "input": [
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/video-speech-transcription"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "video-speech-transcription"
    }
   ]
  },
  {
   "slug": "google/video-text-detection",
   "model_name": "video-text-detection",
   "display_name": "video-text-detection",
   "vendor": "google",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0025"
      }
     },
     "provider_model_id": "google/video-text-detection"
    }
   ],
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "google-gemini",
     "openai-compatible"
    ],
    "outbound": [
     "google-gemini"
    ]
   },
   "aliases": [
    "google/video-text-detection"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "video-text-detection"
    }
   ]
  },
  {
   "slug": "ibm/granite-13b-chat-v2",
   "model_name": "granite-13b-chat-v2",
   "display_name": "granite-13b-chat-v2",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-13b-chat-v2"
    }
   ]
  },
  {
   "slug": "ibm/granite-13b-instruct-v2",
   "model_name": "granite-13b-instruct-v2",
   "display_name": "granite-13b-instruct-v2",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-13b-instruct-v2"
    }
   ]
  },
  {
   "slug": "ibm/granite-3-3-8b-instruct",
   "model_name": "granite-3-3-8b-instruct",
   "display_name": "granite-3-3-8b-instruct",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-3-3-8b-instruct"
    }
   ]
  },
  {
   "slug": "ibm/granite-3-8b-instruct",
   "model_name": "granite-3-8b-instruct",
   "display_name": "granite-3-8b-instruct",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-3-8b-instruct"
    }
   ]
  },
  {
   "slug": "ibm/granite-4-0-h-micro",
   "model_name": "granite-4-0-h-micro",
   "display_name": "Granite 4.0 H Micro",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.017"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "workers-ai/@cf/ibm-granite/granite-4.0-h-micro"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.017"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.112"
      }
     },
     "provider_model_id": "@cf/ibm-granite/granite-4.0-h-micro"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.017"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "ibm-granite/granite-4.0-h-micro"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.017"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.112"
      }
     },
     "provider_model_id": "ibm-granite/granite-4.0-h-micro"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-10-07",
   "max_input_tokens": 131000,
   "max_output_tokens": 131000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "granite",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/ibm-granite/granite-4.0-h-micro",
    "ibm-granite/granite-4.0-h-micro",
    "workers-ai/@cf/ibm-granite/granite-4.0-h-micro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Granite 4.0 H Micro"
    }
   ]
  },
  {
   "slug": "ibm/granite-4-1-8b",
   "model_name": "granite-4-1-8b",
   "display_name": "Granite 4.1 8B",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "ibm-granite/granite-4.1-8b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "ibm-granite/granite-4.1-8b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "ibm-granite/granite-4.1-8b"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "ibm-granite/granite-4.1-8b"
    }
   ],
   "intro": "Granite 4.1 8B is a long-context instruct model capable of enhanced tool calling, instruction following, and chat capabilities.",
   "released_at": "2026-04-29",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "granite",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "benchmarks": {
    "intelligence_index": null,
    "coding_index": 9.5,
    "agentic_index": null
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ibm-granite/granite-4.1-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "IBM: Granite 4.1 8B"
    }
   ]
  },
  {
   "slug": "ibm/granite-4-h-small",
   "model_name": "granite-4-h-small",
   "display_name": "granite-4-h-small",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    }
   ],
   "max_input_tokens": 20480,
   "max_output_tokens": 20480,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-4-h-small"
    }
   ]
  },
  {
   "slug": "ibm/granite-guardian-3-2-2b",
   "model_name": "granite-guardian-3-2-2b",
   "display_name": "granite-guardian-3-2-2b",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "safety_detection",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-guardian-3-2-2b"
    }
   ]
  },
  {
   "slug": "ibm/granite-guardian-3-3-8b",
   "model_name": "granite-guardian-3-3-8b",
   "display_name": "granite-guardian-3-3-8b",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "safety_detection",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-guardian-3-3-8b"
    }
   ]
  },
  {
   "slug": "ibm/granite-ttm-1024-96-r2",
   "model_name": "granite-ttm-1024-96-r2",
   "display_name": "granite-ttm-1024-96-r2",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     }
    }
   ],
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-ttm-1024-96-r2"
    }
   ]
  },
  {
   "slug": "ibm/granite-ttm-1536-96-r2",
   "model_name": "granite-ttm-1536-96-r2",
   "display_name": "granite-ttm-1536-96-r2",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     }
    }
   ],
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-ttm-1536-96-r2"
    }
   ]
  },
  {
   "slug": "ibm/granite-ttm-512-96-r2",
   "model_name": "granite-ttm-512-96-r2",
   "display_name": "granite-ttm-512-96-r2",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     }
    }
   ],
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-ttm-512-96-r2"
    }
   ]
  },
  {
   "slug": "ibm/granite-vision-3-2-2b",
   "model_name": "granite-vision-3-2-2b",
   "display_name": "granite-vision-3-2-2b",
   "vendor": "ibm",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "granite-vision-3-2-2b"
    }
   ]
  },
  {
   "slug": "ideogram/ideogram",
   "model_name": "ideogram",
   "display_name": "Ideogram",
   "vendor": "ideogram",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-04-03",
   "max_input_tokens": 150,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "ideogram",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ideogramai/ideogram"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ideogram"
    }
   ]
  },
  {
   "slug": "ideogram/ideogram-3.0",
   "model_name": "ideogram-3.0",
   "display_name": "ideogram-3.0",
   "vendor": "ideogram",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "provider_model_id": "ideogram/ideogram-3.0"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ideogram/ideogram-3.0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ideogram-3.0"
    }
   ]
  },
  {
   "slug": "ideogram/ideogram-4.0",
   "model_name": "ideogram-4.0",
   "display_name": "ideogram-4.0",
   "vendor": "ideogram",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.06"
      }
     },
     "provider_model_id": "ideogram/ideogram-4.0"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ideogram/ideogram-4.0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ideogram-4.0"
    }
   ]
  },
  {
   "slug": "ideogram/ideogram-v2",
   "model_name": "ideogram-v2",
   "display_name": "Ideogram-v2",
   "vendor": "ideogram",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-08-21",
   "max_input_tokens": 150,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "ideogram",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ideogramai/ideogram-v2"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ideogram-v2"
    }
   ]
  },
  {
   "slug": "ideogram/ideogram-v2a",
   "model_name": "ideogram-v2a",
   "display_name": "Ideogram-v2a",
   "vendor": "ideogram",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-02-27",
   "max_input_tokens": 150,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "ideogram",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ideogramai/ideogram-v2a"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ideogram-v2a"
    }
   ]
  },
  {
   "slug": "ideogram/ideogram-v2a-turbo",
   "model_name": "ideogram-v2a-turbo",
   "display_name": "Ideogram-v2a-Turbo",
   "vendor": "ideogram",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-02-27",
   "max_input_tokens": 150,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "ideogram",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ideogramai/ideogram-v2a-turbo"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ideogram-v2a-Turbo"
    }
   ]
  },
  {
   "slug": "ideogram/ideogram-v4-fp8",
   "model_name": "ideogram-v4-fp8",
   "display_name": "ideogram-v4-fp8",
   "vendor": "ideogram",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "ideogram-v4-fp8"
    }
   ]
  },
  {
   "slug": "ideogram/ideogram-v4-nf4",
   "model_name": "ideogram-v4-nf4",
   "display_name": "ideogram-v4-nf4",
   "vendor": "ideogram",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "ideogram-v4-nf4"
    }
   ]
  },
  {
   "slug": "inception/mercury",
   "model_name": "mercury",
   "display_name": "Mercury",
   "vendor": "inception",
   "pricing": [
    {
     "provider": "inception",
     "official": true,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "inception/mercury"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "inception/mercury"
    }
   ],
   "released_at": "2025-06-26",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "mercury",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inception/mercury"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mercury"
    }
   ]
  },
  {
   "slug": "inception/mercury-2",
   "model_name": "mercury-2",
   "display_name": "Mercury 2",
   "vendor": "inception",
   "pricing": [
    {
     "provider": "inception",
     "official": true,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "inception/mercury-2"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "inception/mercury-2"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03125"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.024999999999999998"
      }
     },
     "provider_model_id": "inception/mercury-2"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-02-24",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 50000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mercury",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools"
    ],
    "defaults": {
     "temperature": 0.75
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inception/mercury-2"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "inception/mercury-coder",
   "model_name": "mercury-coder",
   "display_name": "Mercury Coder",
   "vendor": "inception",
   "pricing": [
    {
     "provider": "inception",
     "official": true,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "inception/mercury-coder"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "inception/mercury-coder"
    }
   ],
   "released_at": "2025-02-26",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "mercury",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "stream": true,
    "structured_output": true
   },
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inception/mercury-coder"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mercury Coder"
    }
   ]
  },
  {
   "slug": "inception/mercury-coder-small",
   "model_name": "mercury-coder-small",
   "display_name": "Mercury Coder Small Beta",
   "vendor": "inception",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "inception/mercury-coder-small"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "inception/mercury-coder-small"
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2025-02-26",
   "max_input_tokens": 32000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mercury",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "knowledge_cutoff": "2024-10",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inception/mercury-coder-small"
   ],
   "intro_i18n": {
    "zh-CN": "Mercury Coder Small 是一款适用于代码生成、调试与重构的低延迟模型。",
    "zh-TW": "Mercury Coder Small 是一款適用於程式碼生成、除錯與重構的低延遲模型。",
    "ja-JP": "Mercury Coder Smallは、コード生成、デバッグ、リファクタリングに最適で、低遅延で動作します。",
    "ru-RU": "Mercury Coder Small идеально подходит для генерации, отладки и рефакторинга кода с минимальной задержкой."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mercury Coder Small Beta"
    }
   ]
  },
  {
   "slug": "inception/mercury-edit",
   "model_name": "mercury-edit",
   "display_name": "Mercury Edit",
   "vendor": "inception",
   "pricing": [
    {
     "provider": "inception",
     "official": true,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "inception/mercury-edit"
    }
   ],
   "released_at": "2026-02-24",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-01",
   "family": "mercury",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inception/mercury-edit"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mercury Edit"
    }
   ]
  },
  {
   "slug": "inception/mercury-edit-2",
   "model_name": "mercury-edit-2",
   "display_name": "Mercury Edit 2",
   "vendor": "inception",
   "pricing": [
    {
     "provider": "inception",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-03-30",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation"
  },
  {
   "slug": "inflection/inflection-3-pi",
   "model_name": "inflection-3-pi",
   "display_name": "Inflection: Inflection 3 Pi",
   "vendor": "inflection",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "inflection/inflection-3-pi"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.499"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.996"
      }
     },
     "provider_model_id": "inflection/inflection-3-pi"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "inflection/inflection-3-pi"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2024-10-11",
   "max_input_tokens": 8000,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "knowledge_cutoff": "2024-10",
   "family": "gpt",
   "deprecated": true,
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inflection/inflection-3-pi"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Inflection: Inflection 3 Pi"
    }
   ]
  },
  {
   "slug": "inflection/inflection-3-productivity",
   "model_name": "inflection-3-productivity",
   "display_name": "Inflection: Inflection 3 Productivity",
   "vendor": "inflection",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "inflection/inflection-3-productivity"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.499"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.996"
      }
     },
     "provider_model_id": "inflection/inflection-3-productivity"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "inflection/inflection-3-productivity"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2024-10-11",
   "max_input_tokens": 8000,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "knowledge_cutoff": "2024-10",
   "family": "gpt",
   "deprecated": true,
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inflection/inflection-3-productivity"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Inflection: Inflection 3 Productivity"
    }
   ]
  },
  {
   "slug": "jina/jina-clip-v2",
   "model_name": "jina-clip-v2",
   "display_name": "jina-clip-v2",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-clip-v2"
    }
   ]
  },
  {
   "slug": "jina/jina-colbert-v2",
   "model_name": "jina-colbert-v2",
   "display_name": "jina-colbert-v2",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-colbert-v2"
    }
   ]
  },
  {
   "slug": "jina/jina-deepsearch-v1",
   "model_name": "jina-deepsearch-v1",
   "display_name": "Jina DeepSearch v1",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "jina",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "model_type": "vision_understanding",
   "capabilities": {
    "reasoning": true,
    "web_search": true,
    "vision": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "DeepSearch 结合了网页搜索、阅读与推理，适用于深入研究任务。它就像一个智能代理，接收你的研究任务后，进行多轮广泛搜索，最终才生成答案。整个过程包含持续的信息检索、逻辑推理和多角度问题解决，区别于仅依赖预训练数据的传统大模型或一次性检索的RAG系统。",
    "zh-TW": "DeepSearch 結合網頁搜尋、閱讀與推理，進行深入調查。它如同一位代理人，接收你的研究任務後，進行多輪廣泛搜尋，最終才產出答案。整個過程包含持續研究、推理與多角度問題解決，與僅依賴預訓練資料的標準 LLM 或一次性檢索的傳統 RAG 系統截然不同。",
    "ja-JP": "DeepSearch は、ウェブ検索、読解、推論を組み合わせて徹底的な調査を行うエージェントのようなモデルです。調査タスクを受け取り、複数回の広範な検索を行った後に回答を生成します。継続的な調査と多角的な問題解決を行う点で、従来の LLM や一度きりの検索に依存する RAG システムとは根本的に異なります。",
    "ru-RU": "DeepSearch объединяет веб-поиск, чтение и логический анализ для глубокого исследования. Представьте себе агента, который берет вашу исследовательскую задачу, проводит многократный поиск, анализирует и только потом выдает ответ. Этот процесс включает непрерывное исследование, логическое мышление и многогранное решение задач, что принципиально отличается от стандартных LLM, отвечающих на основе предобученных данных или традиционных RAG-систем с одноразовым поиском."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Jina DeepSearch v1"
    }
   ]
  },
  {
   "slug": "jina/jina-embeddings-v2-base-code",
   "model_name": "jina-embeddings-v2-base-code",
   "display_name": "jina-embeddings-v2-base-code",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-embeddings-v2-base-code"
    }
   ]
  },
  {
   "slug": "jina/jina-embeddings-v3",
   "model_name": "jina-embeddings-v3",
   "display_name": "jina-embeddings-v3",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-embeddings-v3"
    }
   ]
  },
  {
   "slug": "jina/jina-embeddings-v4",
   "model_name": "jina-embeddings-v4",
   "display_name": "jina-embeddings-v4",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "multimodal_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-embeddings-v4"
    }
   ]
  },
  {
   "slug": "jina/jina-embeddings-v5-text-nano",
   "model_name": "jina-embeddings-v5-text-nano",
   "display_name": "jina-embeddings-v5-text-nano",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-embeddings-v5-text-nano"
    }
   ]
  },
  {
   "slug": "jina/jina-embeddings-v5-text-small",
   "model_name": "jina-embeddings-v5-text-small",
   "display_name": "jina-embeddings-v5-text-small",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-embeddings-v5-text-small"
    }
   ]
  },
  {
   "slug": "jina/jina-reader",
   "model_name": "jina-reader",
   "display_name": "jina-reader",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-reader"
    }
   ]
  },
  {
   "slug": "jina/jina-reranker-m0",
   "model_name": "jina-reranker-m0",
   "display_name": "jina-reranker-m0",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-reranker-m0"
    }
   ]
  },
  {
   "slug": "jina/jina-reranker-v3",
   "model_name": "jina-reranker-v3",
   "display_name": "jina-reranker-v3",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "max_input_tokens": 131000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-reranker-v3"
    }
   ]
  },
  {
   "slug": "jina/jina-search",
   "model_name": "jina-search",
   "display_name": "jina-search",
   "vendor": "jina",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jina-search"
    }
   ]
  },
  {
   "slug": "kling/kling-1.6-pro",
   "model_name": "kling-1.6-pro",
   "display_name": "kling-1.6-pro",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.32"
      }
     },
     "provider_model_id": "kwaivgI/kling-1.6-pro"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kwaivgI/kling-1.6-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kling-1.6-pro"
    }
   ]
  },
  {
   "slug": "kling/kling-1.6-standard",
   "model_name": "kling-1.6-standard",
   "display_name": "kling-1.6-standard",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.19"
      }
     },
     "provider_model_id": "kwaivgI/kling-1.6-standard"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kwaivgI/kling-1.6-standard"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kling-1.6-standard"
    }
   ]
  },
  {
   "slug": "kling/kling-2.0-master",
   "model_name": "kling-2.0-master",
   "display_name": "kling-2.0-master",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.92"
      }
     },
     "provider_model_id": "kwaivgI/kling-2.0-master"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kwaivgI/kling-2.0-master"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kling-2.0-master"
    }
   ]
  },
  {
   "slug": "kling/kling-2.1-master",
   "model_name": "kling-2.1-master",
   "display_name": "kling-2.1-master",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.92"
      }
     },
     "provider_model_id": "kwaivgI/kling-2.1-master"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kwaivgI/kling-2.1-master"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kling-2.1-master"
    }
   ]
  },
  {
   "slug": "kling/kling-2.1-pro",
   "model_name": "kling-2.1-pro",
   "display_name": "kling-2.1-pro",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.32"
      }
     },
     "provider_model_id": "kwaivgI/kling-2.1-pro"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kwaivgI/kling-2.1-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kling-2.1-pro"
    }
   ]
  },
  {
   "slug": "kling/kling-2.1-standard",
   "model_name": "kling-2.1-standard",
   "display_name": "kling-2.1-standard",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.18"
      }
     },
     "provider_model_id": "kwaivgI/kling-2.1-standard"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kwaivgI/kling-2.1-standard"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kling-2.1-standard"
    }
   ]
  },
  {
   "slug": "kling/kling-3.0-turbo",
   "model_name": "kling-3.0-turbo",
   "display_name": "kling-3.0-turbo",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kling-3.0-turbo"
    }
   ]
  },
  {
   "slug": "kling/kling-v2-6",
   "model_name": "kling-v2-6",
   "display_name": "Kling-V2 6",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.36"
      }
     }
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-01-13",
   "max_input_tokens": 99999999,
   "max_output_tokens": 99999999,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling-V2 6"
    }
   ]
  },
  {
   "slug": "kling/kling-v2.5-turbo-i2v",
   "model_name": "kling-v2.5-turbo-i2v",
   "display_name": "Kling v2.5 Turbo Image-to-Video",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_std": {
       "unit": "per_second",
       "price": "0.042"
      },
      "video_output_pro": {
       "unit": "per_second",
       "price": "0.07"
      }
     },
     "provider_model_id": "klingai/kling-v2.5-turbo-i2v"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-09-23",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "ling",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "klingai/kling-v2.5-turbo-i2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling v2.5 Turbo Image-to-Video"
    }
   ]
  },
  {
   "slug": "kling/kling-v2.5-turbo-t2v",
   "model_name": "kling-v2.5-turbo-t2v",
   "display_name": "Kling v2.5 Turbo Text-to-Video",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_std": {
       "unit": "per_second",
       "price": "0.042"
      },
      "video_output_pro": {
       "unit": "per_second",
       "price": "0.07"
      }
     },
     "provider_model_id": "klingai/kling-v2.5-turbo-t2v"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-09-23",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "ling",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "klingai/kling-v2.5-turbo-t2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling v2.5 Turbo Text-to-Video"
    }
   ]
  },
  {
   "slug": "kling/kling-v2.6-i2v",
   "model_name": "kling-v2.6-i2v",
   "display_name": "Kling v2.6 Image-to-Video",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_std": {
       "unit": "per_second",
       "price": "0.042"
      },
      "video_output_pro": {
       "unit": "per_second",
       "price": "0.07"
      },
      "video_output_pro_audio": {
       "unit": "per_second",
       "price": "0.14"
      }
     },
     "provider_model_id": "klingai/kling-v2.6-i2v"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-12-03",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "ling",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "klingai/kling-v2.6-i2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling v2.6 Image-to-Video"
    }
   ]
  },
  {
   "slug": "kling/kling-v2.6-motion-control",
   "model_name": "kling-v2.6-motion-control",
   "display_name": "Kling v2.6 Motion Control",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_std": {
       "unit": "per_second",
       "price": "0.07"
      },
      "video_output_pro": {
       "unit": "per_second",
       "price": "0.112"
      }
     },
     "provider_model_id": "klingai/kling-v2.6-motion-control"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-12-18",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "ling",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "klingai/kling-v2.6-motion-control"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling v2.6 Motion Control"
    }
   ]
  },
  {
   "slug": "kling/kling-v2.6-t2v",
   "model_name": "kling-v2.6-t2v",
   "display_name": "Kling v2.6 Text-to-Video",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_std": {
       "unit": "per_second",
       "price": "0.042"
      },
      "video_output_pro": {
       "unit": "per_second",
       "price": "0.07"
      },
      "video_output_pro_audio": {
       "unit": "per_second",
       "price": "0.14"
      }
     },
     "provider_model_id": "klingai/kling-v2.6-t2v"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-12-03",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "ling",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "klingai/kling-v2.6-t2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling v2.6 Text-to-Video"
    }
   ]
  },
  {
   "slug": "kling/kling-v3",
   "model_name": "kling-v3",
   "display_name": "kling-v3",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.36"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kling-v3"
    }
   ]
  },
  {
   "slug": "kling/kling-v3-image-generation",
   "model_name": "kling-v3-image-generation",
   "display_name": "Kling V3 Image Generation",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     },
     "provider_model_id": "kling/kling-v3-image-generation"
    }
   ],
   "released_at": "2026-03-26",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kling/kling-v3-image-generation"
   ],
   "intro_i18n": {
    "zh-CN": "支持最多10张参考图像，允许锁定主体、元素和色调以确保风格一致。结合风格迁移、肖像/角色参考、多图像融合和局部修复，提供灵活控制。呈现逼真的肖像细节，整体视觉精致且层次丰富，具有电影级色彩和氛围。",
    "zh-TW": "支持最多10張參考影像，允許鎖定主題、元素及色調以確保風格一致性。結合風格轉換、肖像/角色參考、多影像融合及局部修補，提供靈活控制。呈現逼真的肖像細節，整體視覺精緻且層次豐富，具有電影級色彩及氛圍。",
    "ja-JP": "最大10枚の参照画像をサポートし、被写体、要素、色調を固定して一貫したスタイルを確保します。スタイル転送、ポートレート/キャラクター参照、マルチイメージ融合、局所的なインペインティングを組み合わせ、柔軟な制御を実現します。リアルなポートレートのディテールを提供し、全体的なビジュアルは繊細で層が豊かで、映画的な色彩と雰囲気を特徴とします。",
    "ru-RU": "Поддерживает до 10 эталонных изображений, позволяя фиксировать объекты, элементы и цветовые тона для обеспечения согласованного стиля. Сочетает перенос стиля, ссылку на портреты/персонажей, слияние нескольких изображений и локальную дорисовку для гибкого управления. Обеспечивает реалистичные детали портретов, с общим визуальным оформлением, которое отличается утонченностью и богатством слоев, с кинематографическими цветами и атмосферой."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling V3 Image Generation"
    }
   ]
  },
  {
   "slug": "kling/kling-v3-omni",
   "model_name": "kling-v3-omni",
   "display_name": "kling-v3-omni",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.6"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kling-v3-omni"
    }
   ]
  },
  {
   "slug": "kling/kling-v3-omni-image-generation",
   "model_name": "kling-v3-omni-image-generation",
   "display_name": "Kling V3 Omni Image Generation",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     },
     "provider_model_id": "kling/kling-v3-omni-image-generation"
    }
   ],
   "released_at": "2026-03-26",
   "model_type": "omni",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kling/kling-v3-omni-image-generation"
   ],
   "intro_i18n": {
    "zh-CN": "通过新系列图像生成和直接2K/4K输出解锁电影叙事视觉效果。深入分析提示中的视听元素，精确执行创意指令。支持灵活的多参考输入和全面的质量升级，非常适合分镜、叙事概念艺术和场景设计。",
    "zh-TW": "解鎖電影敘事視覺效果，支持新系列影像生成及直接2K/4K輸出。深度分析提示中的視聽元素，精確執行創意指令。支持靈活的多參考輸入及全面的質量升級，非常適合故事板、敘事概念藝術及場景設計。",
    "ja-JP": "新しいシリーズ画像生成と直接2K/4K出力で映画的なストーリーテリングビジュアルを解放します。プロンプト内の視聴覚要素を深く分析し、創造的な指示を正確に実行します。柔軟なマルチ参照入力と包括的な品質アップグレードをサポートし、ストーリーボード、物語のコンセプトアート、シーンデザインに最適です。",
    "ru-RU": "Разблокируйте кинематографические визуальные эффекты повествования с помощью новой серии генерации изображений и прямого вывода в 2K/4K. Глубоко анализирует аудиовизуальные элементы в подсказках для точного выполнения творческих инструкций. Поддерживает гибкие многоссылочные входные данные и комплексные улучшения качества, идеально подходящие для раскадровок, концептуального искусства повествования и дизайна сцен."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling V3 Omni Image Generation"
    }
   ]
  },
  {
   "slug": "kling/kling-v3-omni-video-generation",
   "model_name": "kling-v3-omni-video-generation",
   "display_name": "Kling V3 Omni Video Generation",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.132353"
      }
     },
     "provider_model_id": "kling/kling-v3-omni-video-generation"
    }
   ],
   "model_type": "omni",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kling/kling-v3-omni-video-generation"
   ],
   "intro_i18n": {
    "zh-CN": "全新“全参考”功能支持3-8秒视频或多张图像锚定角色元素。可匹配原始音频和唇部动作，实现真实的角色表现。增强视频一致性和动态表达。支持视听同步和智能分镜。",
    "zh-TW": "全新“全參考”功能支持3至8秒影像或多張影像錨定角色元素。可匹配原始音頻及唇部動作，實現真實角色表現。增強影像一致性及動態表現。支持視聽同步及智能故事板設計。",
    "ja-JP": "新しい「オールインワン参照」機能は、3～8秒のビデオまたは複数の画像をサポートし、キャラクター要素を固定します。元の音声とリップムーブメントを一致させ、キャラクターの本格的な表現を実現します。ビデオの一貫性と動的表現を強化します。視聴覚の同期とインテリジェントなストーリーボードをサポートします。",
    "ru-RU": "Новая функция «Все в одной ссылке» поддерживает видео длиной 3–8 секунд или несколько изображений для закрепления элементов персонажей. Может соответствовать оригинальному аудио и движениям губ для аутентичного представления персонажей. Улучшает согласованность видео и динамическое выражение. Поддерживает синхронизацию аудио и видео, а также интеллектуальную раскадровку."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling V3 Omni Video Generation"
    }
   ]
  },
  {
   "slug": "kling/kling-v3-video-generation",
   "model_name": "kling-v3-video-generation",
   "display_name": "Kling V3 Video Generation",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.132353"
      }
     },
     "provider_model_id": "kling/kling-v3-video-generation"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kling/kling-v3-video-generation"
   ],
   "intro_i18n": {
    "zh-CN": "智能分镜理解脚本中的场景转换，自动安排摄像机位置和镜头类型。原生多模态框架确保视听一致性。移除时长限制，实现更灵活的多镜头叙事。",
    "zh-TW": "智能故事板理解腳本中的場景轉換，自動安排相機位置及鏡頭類型。原生多模態框架確保視聽一致性。移除時長限制，實現更靈活的多鏡頭敘事。",
    "ja-JP": "インテリジェントなストーリーボードは、スクリプト内のシーン遷移を理解し、カメラ位置やショットタイプを自動的に配置します。ネイティブのマルチモーダルフレームワークにより、視聴覚の一貫性を確保します。持続時間の制約を取り除き、より柔軟なマルチショットストーリーテリングを可能にします。",
    "ru-RU": "Интеллектуальная раскадровка понимает переходы между сценами в сценариях, автоматически располагая позиции камеры и типы кадров. Родная мультимодальная структура обеспечивает согласованность аудио и видео. Убирает ограничения по длительности, позволяя более гибкое повествование с несколькими кадрами."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling V3 Video Generation"
    }
   ]
  },
  {
   "slug": "kling/kling-v3.0-i2v",
   "model_name": "kling-v3.0-i2v",
   "display_name": "Kling v3.0 Image-to-Video",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_std": {
       "unit": "per_second",
       "price": "0.168"
      },
      "video_output_std_audio": {
       "unit": "per_second",
       "price": "0.252"
      },
      "video_output_pro": {
       "unit": "per_second",
       "price": "0.224"
      },
      "video_output_pro_audio": {
       "unit": "per_second",
       "price": "0.336"
      }
     },
     "provider_model_id": "klingai/kling-v3.0-i2v"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-02-05",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "ling",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "klingai/kling-v3.0-i2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling v3.0 Image-to-Video"
    }
   ]
  },
  {
   "slug": "kling/kling-v3.0-motion-control",
   "model_name": "kling-v3.0-motion-control",
   "display_name": "Kling v3.0 Motion Control",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_std": {
       "unit": "per_second",
       "price": "0.126"
      },
      "video_output_pro": {
       "unit": "per_second",
       "price": "0.168"
      }
     },
     "provider_model_id": "klingai/kling-v3.0-motion-control"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-03-04",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "ling",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "klingai/kling-v3.0-motion-control"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling v3.0 Motion Control"
    }
   ]
  },
  {
   "slug": "kling/kling-v3.0-t2v",
   "model_name": "kling-v3.0-t2v",
   "display_name": "Kling v3.0 Text-to-Video",
   "vendor": "kling",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_std": {
       "unit": "per_second",
       "price": "0.168"
      },
      "video_output_std_audio": {
       "unit": "per_second",
       "price": "0.252"
      },
      "video_output_pro": {
       "unit": "per_second",
       "price": "0.224"
      },
      "video_output_pro_audio": {
       "unit": "per_second",
       "price": "0.336"
      }
     },
     "provider_model_id": "klingai/kling-v3.0-t2v"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-02-05",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "family": "ling",
   "capabilities": {},
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "klingai/kling-v3.0-t2v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kling v3.0 Text-to-Video"
    }
   ]
  },
  {
   "slug": "kwaipilot/kat-coder-pro",
   "model_name": "kat-coder-pro",
   "display_name": "Kat Coder Pro",
   "vendor": "kwaipilot",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.207"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.828"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0414"
      }
     },
     "provider_model_id": "kwaipilot/kat-coder-pro"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "kwaipilot/kat-coder-pro"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "kwaipilot/kat-coder-pro"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0414"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.207"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.828"
      }
     },
     "provider_model_id": "kwaipilot/kat-coder-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "novita/kwaipilot/kat-coder-pro"
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2026-01-05",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kwaipilot/kat-coder-pro",
    "novita/kwaipilot/kat-coder-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kat Coder Pro"
    }
   ]
  },
  {
   "slug": "kwaipilot/KAT-Coder-Pro-V1",
   "model_name": "KAT-Coder-Pro-V1",
   "display_name": "KAT-Coder-Pro V1",
   "vendor": "kwaipilot",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.28"
      }
     },
     "provider_model_id": "kat-coder-pro-v1"
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.4"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "kwaipilot/kat-coder-pro-v1"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "kuaishou/kat-coder-pro-v1"
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2025-11-09",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 256000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kat-coder",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kat-coder-pro-v1",
    "kuaishou/kat-coder-pro-v1",
    "kwaipilot/kat-coder-pro-v1"
   ],
   "intro_i18n": {
    "zh-CN": "专为 Agentic Coding 打造，全面覆盖编程任务与应用场景。通过大规模强化学习实现智能行为涌现，在代码生成性能上显著优于同类模型。",
    "zh-TW": "專為 Agentic Coding 設計，全面覆蓋各類程式開發任務與情境，透過大規模強化學習達成智能行為湧現，在程式生成效能上遠超同級模型。",
    "ja-JP": "エージェントコーディング向けに設計され、幅広いプログラミングシナリオとタスクをカバーします。大規模強化学習により知的行動を創発し、類似モデルを大きく上回るコード生成性能を実現します。",
    "ru-RU": "Создана для Agentic Coding, охватывает все основные программные задачи и сценарии. Демонстрирует появление интеллектуального поведения благодаря крупномасштабному обучению с подкреплением и значительно превосходит аналогичные модели в написании кода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "KAT-Coder-Pro V1"
    }
   ]
  },
  {
   "slug": "kwaipilot/KAT-Coder-Pro-V2",
   "model_name": "KAT-Coder-Pro-V2",
   "display_name": "Kat Coder Pro V2",
   "vendor": "kwaipilot",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "kwaipilot/kat-coder-pro-v2"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "kwaipilot/kat-coder-pro-v2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "kwaipilot/kat-coder-pro-v2"
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.4"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "kwaipilot/kat-coder-pro-v2"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "kuaishou/kat-coder-pro-v2"
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2026-03-27",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kat-coder",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kuaishou/kat-coder-pro-v2",
    "kwaipilot/kat-coder-pro-v2"
   ],
   "intro_i18n": {
    "zh-CN": "来自快手 Kwaipilot 团队的最新高性能模型，面向复杂企业级项目与 SaaS 集成。它在代码相关场景中表现出色，兼容多类智能体框架（Claude Code、OpenCode、KiloCode），原生支持 OpenClaw，并对前端页面美学进行了专门优化。",
    "zh-TW": "由快手 Kwaipilot 團隊打造的全新高效能模型，面向複雜企業專案與 SaaS 整合。其在程式相關場景中表現卓越，兼容各類型智能體框架（Claude Code、OpenCode、KiloCode），原生支援 OpenClaw，並針對前端頁面美學進行特殊優化。",
    "ja-JP": "Kuaishou Kwaipilot チームによる最新の高性能モデルで、複雑な企業向けプロジェクトや SaaS 統合を想定して設計されています。コード関連シナリオに強く、Claude Code、OpenCode、KiloCode などの各種エージェントフレームワークに対応し、OpenClaw をネイティブサポートします。また、フロントエンドのデザイン美観にも特化して最適化されています。",
    "ru-RU": "Новейшая высокопроизводительная модель команды Kuaishou Kwaipilot, разработанная для сложных корпоративных проектов и интеграции с SaaS. Отличается выдающимися возможностями в задачах кодирования и совместима с различными типами агентных фреймворков (Claude Code, OpenCode, KiloCode), нативно поддерживает OpenClaw и специально оптимизирована для эстетики фронтенда."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kat Coder Pro V2"
    }
   ]
  },
  {
   "slug": "kwaipilot/KAT-Dev",
   "model_name": "KAT-Dev",
   "display_name": "Kwaipilot/KAT-Dev",
   "vendor": "kwaipilot",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.137"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.548"
      }
     },
     "provider_model_id": "kat-dev"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14713132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      }
     }
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Kwaipilot/KAT-Dev"
    }
   ],
   "released_at": "2025-09-27",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "kat-coder",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Kwaipilot/KAT-Dev",
    "kat-dev"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14720168",
     "new": "0.14713132"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14730394",
     "new": "0.14720168"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14745922",
     "new": "0.14730394"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14748933",
     "new": "0.14745922"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14743712",
     "new": "0.14748933"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14717895",
     "new": "0.14743712"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kwaipilot/KAT-Dev"
    }
   ]
  },
  {
   "slug": "kwaipilot/siliconflow-Kwaipilot-KAT-Dev",
   "model_name": "siliconflow-Kwaipilot-KAT-Dev",
   "display_name": "Kwaipilot/KAT-Dev",
   "vendor": "kwaipilot",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.572"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kwaipilot/KAT-Dev"
    }
   ]
  },
  {
   "slug": "liquid/lfm-2-24b-a2b",
   "model_name": "lfm-2-24b-a2b",
   "display_name": "LiquidAI: LFM2-24B-A2B",
   "vendor": "liquid",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "liquid/lfm-2-24b-a2b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "liquid/lfm-2-24b-a2b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "liquid/lfm-2-24b-a2b"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2026-02-26",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "structured_output": true,
    "open_weights": true
   },
   "family": "liquid",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "liquid/lfm-2-24b-a2b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LiquidAI: LFM2-24B-A2B"
    }
   ]
  },
  {
   "slug": "liquid/lfm-2.2-6b",
   "model_name": "lfm-2.2-6b",
   "display_name": "LiquidAI: LFM2-2.6B",
   "vendor": "liquid",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "liquid/lfm-2.2-6b"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2025-10-20",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "liquid/lfm-2.2-6b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LiquidAI: LFM2-2.6B"
    }
   ]
  },
  {
   "slug": "liquid/lfm-2.5-1.2b-instruct:free",
   "model_name": "lfm-2.5-1.2b-instruct:free",
   "display_name": "LFM2.5-1.2B-Instruct (free)",
   "vendor": "liquid",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "liquid/lfm-2.5-1.2b-instruct:free"
    }
   ],
   "intro": "Free provider route for experiments, demos, and cost-sensitive chat workloads",
   "released_at": "2026-01-20",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "liquid",
   "capabilities": {
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "liquid/lfm-2.5-1.2b-instruct:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LFM2.5-1.2B-Instruct (free)"
    }
   ]
  },
  {
   "slug": "liquid/lfm-2.5-1.2b-thinking:free",
   "model_name": "lfm-2.5-1.2b-thinking:free",
   "display_name": "LFM2.5-1.2B-Thinking (free)",
   "vendor": "liquid",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "liquid/lfm-2.5-1.2b-thinking:free"
    }
   ],
   "intro": "Free provider route for experiments, demos, and cost-sensitive chat workloads",
   "released_at": "2026-01-20",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "liquid",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "liquid/lfm-2.5-1.2b-thinking:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LFM2.5-1.2B-Thinking (free)"
    }
   ]
  },
  {
   "slug": "liquid/lfm-3b",
   "model_name": "lfm-3b",
   "display_name": "lfm-3b",
   "vendor": "liquid",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "liquid/lfm-3b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "liquid/lfm-3b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "lfm-3b"
    }
   ]
  },
  {
   "slug": "liquid/lfm-40b",
   "model_name": "lfm-40b",
   "display_name": "lfm-40b",
   "vendor": "liquid",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "liquid/lfm-40b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "liquid/lfm-40b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "lfm-40b"
    }
   ]
  },
  {
   "slug": "liquid/lfm-7b",
   "model_name": "lfm-7b",
   "display_name": "lfm-7b",
   "vendor": "liquid",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "liquid/lfm-7b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "liquid/lfm-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "lfm-7b"
    }
   ]
  },
  {
   "slug": "liquid/LFM2-24B-A2B",
   "model_name": "LFM2-24B-A2B",
   "display_name": "LFM2-24B-A2B",
   "vendor": "liquid",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "LiquidAI/LFM2-24B-A2B"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2026-02-25",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "liquid",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "LiquidAI/LFM2-24B-A2B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LFM2-24B-A2B"
    }
   ]
  },
  {
   "slug": "liquid/lfm2-8b-a1b",
   "model_name": "lfm2-8b-a1b",
   "display_name": "LiquidAI: LFM2-8B-A1B",
   "vendor": "liquid",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "liquid/lfm2-8b-a1b"
    }
   ],
   "max_input_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2025-10-20",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "liquid/lfm2-8b-a1b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LiquidAI: LFM2-8B-A1B"
    }
   ]
  },
  {
   "slug": "liquid/LFM2.5-8B-A1B",
   "model_name": "LFM2.5-8B-A1B",
   "display_name": "LFM2.5-8B-A1B",
   "vendor": "liquid",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.030000000000000002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12000000000000001"
      }
     },
     "provider_model_id": "LiquidAI/LFM2.5-8B-A1B"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "LiquidAI/LFM2.5-8B-A1B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "listed",
     "note": "LFM2.5-8B-A1B"
    }
   ]
  },
  {
   "slug": "llava/firellava-13b",
   "model_name": "firellava-13b",
   "display_name": "firellava-13b",
   "vendor": "llava",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "fireworks/firellava-13b"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fireworks/firellava-13b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "firellava-13b"
    }
   ]
  },
  {
   "slug": "longcat/LongCat-2.0",
   "model_name": "LongCat-2.0",
   "display_name": "LongCat-2.0",
   "vendor": "longcat",
   "pricing": [
    {
     "provider": "longcat",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7746"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.0984"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015492"
      }
     },
     "provider_model_id": "longcat-2.0"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "longcat-2.0"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.006"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "meituan/longcat-2.0"
    }
   ],
   "intro": "Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window",
   "released_at": "2026-06-30",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "longcat",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "longcat-2.0",
    "meituan/longcat-2.0"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-05",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-04",
     "kind": "listed",
     "note": "LongCat-2.0"
    }
   ]
  },
  {
   "slug": "longcat/LongCat-2.0-Preview",
   "model_name": "LongCat-2.0-Preview",
   "display_name": "LongCat-2.0-Preview",
   "vendor": "longcat",
   "pricing": [
    {
     "provider": "longcat",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2026-04-20",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "LongCat-2.0-Preview 的核心特性如下：专为 Agent 开发场景设计，原生支持工具调用、多步推理和长上下文任务；在代码生成、自动化流程和复杂指令执行方面表现突出；与 Claude Code、OpenClaw、OpenCode 和 Kilo Code 等生产力工具深度集成。",
    "zh-TW": "LongCat-2.0-Preview 的核心特點如下：專為代理開發場景設計，原生支援工具使用、多步推理與長上下文任務；擅長程式碼生成、自動化流程與複雜指令執行；與 Claude Code、OpenClaw、OpenCode、Kilo Code 等生產力工具深度整合。",
    "ja-JP": "LongCat-2.0-Previewの主な特徴は以下の通りです。エージェント開発シナリオ向けに設計され、ツール使用、マルチステップ推論、長いコンテキストタスクをネイティブにサポートします。コード生成、自動化ワークフロー、複雑な指示の実行に優れています。Claude Code、OpenClaw、OpenCode、Kilo Codeなどの生産性ツールと深く統合されています。",
    "ru-RU": "Ключевые особенности LongCat-2.0-Preview: создан для разработки агентов, имеет нативную поддержку инструментов, многошаговых рассуждений и задач с длинным контекстом; превосходно справляется с генерацией кода, автоматизацией рабочих процессов и выполнением сложных инструкций; тесно интегрирован с инструментами продуктивности, такими как Claude Code, OpenClaw, OpenCode и Kilo Code."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LongCat-2.0-Preview"
    }
   ]
  },
  {
   "slug": "longcat/LongCat-Flash-Chat",
   "model_name": "LongCat-Flash-Chat",
   "display_name": "Meituan/Longcat-Flash-Chat",
   "vendor": "longcat",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "meituan/longcat-flash-chat"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "meituan/longcat-flash-chat"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meituan/longcat-flash-chat"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-11-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-10",
   "family": "longcat",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meituan/longcat-flash-chat"
   ],
   "intro_i18n": {
    "zh-CN": "美团开源的基础对话模型，专为对话与智能体任务优化，擅长工具使用与复杂多轮交互。",
    "zh-TW": "來自美團的開源非思考型基礎模型，針對對話與代理任務進行最佳化，擅長工具使用與複雜多輪互動。",
    "ja-JP": "Meituanによるオープンソースの非推論ベースモデルで、対話やエージェントタスクに最適化されており、ツール使用や複雑なマルチターン対話に強みを持ちます。",
    "ru-RU": "Открытая базовая модель без рассуждений от Meituan, оптимизированная для диалогов и агентных задач, сильна в использовании инструментов и сложных многоходовых взаимодействиях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meituan/Longcat-Flash-Chat"
    }
   ]
  },
  {
   "slug": "longcat/longcat-flash-lite",
   "model_name": "longcat-flash-lite",
   "display_name": "Meituan/Longcat-Flash-Lite",
   "vendor": "longcat",
   "pricing": [],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2026-02-06",
   "max_input_tokens": 256000,
   "max_output_tokens": 320000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meituan/longcat-flash-lite"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meituan/Longcat-Flash-Lite"
    }
   ]
  },
  {
   "slug": "longcat/longcat-flash-thinking",
   "model_name": "longcat-flash-thinking",
   "display_name": "LongCat Flash Thinking",
   "vendor": "longcat",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "meituan/longcat-flash-thinking"
    }
   ],
   "released_at": "2025-09-23",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "longcat",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meituan/longcat-flash-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LongCat Flash Thinking"
    }
   ]
  },
  {
   "slug": "longcat/longcat-flash-thinking-2601",
   "model_name": "longcat-flash-thinking-2601",
   "display_name": "LongCat Flash Thinking 2601",
   "vendor": "longcat",
   "pricing": [],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2026-01-15",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "longcat",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meituan/longcat-flash-thinking-2601"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LongCat Flash Thinking 2601"
    }
   ]
  },
  {
   "slug": "longcat/meituan-longcat-flash-chat",
   "model_name": "meituan-longcat-flash-chat",
   "display_name": "LongCat-Flash-Chat",
   "vendor": "longcat",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "released_at": "2025-09-04",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LongCat-Flash-Chat"
    }
   ]
  },
  {
   "slug": "longcat/sophnet-longcat-flash-chat",
   "model_name": "sophnet-longcat-flash-chat",
   "display_name": "sophnet/LongCat-Flash-Chat",
   "vendor": "longcat",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.714"
      }
     }
    }
   ],
   "released_at": "2025-09-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/LongCat-Flash-Chat"
    }
   ]
  },
  {
   "slug": "longcat/sophnet-LongCat-Flash-Thinking",
   "model_name": "sophnet-LongCat-Flash-Thinking",
   "display_name": "sophnet/LongCat-Flash-Thinking",
   "vendor": "longcat",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.429"
      }
     }
    }
   ],
   "released_at": "2026-01-06",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/LongCat-Flash-Thinking"
    }
   ]
  },
  {
   "slug": "luma/ray2",
   "model_name": "ray2",
   "display_name": "Ray2",
   "vendor": "luma",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-02-20",
   "max_input_tokens": 5000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "ray",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "lumalabs/ray2"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ray2"
    }
   ]
  },
  {
   "slug": "meta/@cf/facebook/bart-large-cnn",
   "model_name": "@cf/facebook/bart-large-cnn",
   "display_name": "BART Large CNN",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/facebook/bart-large-cnn"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2025-04-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "bart",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "workers-ai/@cf/facebook/bart-large-cnn"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "BART Large CNN"
    }
   ]
  },
  {
   "slug": "meta/aihubmix-Llama-3-1-405B-Instruct",
   "model_name": "aihubmix-Llama-3-1-405B-Instruct",
   "display_name": "aihubmix-Llama-3-1-405B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Llama-3-1-405B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/aihubmix-Llama-3-1-70B-Instruct",
   "model_name": "aihubmix-Llama-3-1-70B-Instruct",
   "display_name": "aihubmix-Llama-3-1-70B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Llama-3-1-70B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/aihubmix-Llama-3-1-8B-Instruct",
   "model_name": "aihubmix-Llama-3-1-8B-Instruct",
   "display_name": "aihubmix-Llama-3-1-8B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Llama-3-1-8B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/aihubmix-Llama-3-2-11B-Vision",
   "model_name": "aihubmix-Llama-3-2-11B-Vision",
   "display_name": "aihubmix-Llama-3-2-11B-Vision",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Llama-3-2-11B-Vision"
    }
   ]
  },
  {
   "slug": "meta/aihubmix-Llama-3-2-90B-Vision",
   "model_name": "aihubmix-Llama-3-2-90B-Vision",
   "display_name": "aihubmix-Llama-3-2-90B-Vision",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Llama-3-2-90B-Vision"
    }
   ]
  },
  {
   "slug": "meta/aihubmix-Llama-3-70B-Instruct",
   "model_name": "aihubmix-Llama-3-70B-Instruct",
   "display_name": "aihubmix-Llama-3-70B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Llama-3-70B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/aion-rp-llama-3.1-8b",
   "model_name": "aion-rp-llama-3.1-8b",
   "display_name": "AionLabs: Aion-RP 1.0 (8B)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "aion-labs/aion-rp-llama-3.1-8b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      }
     },
     "provider_model_id": "aion-labs/aion-rp-llama-3.1-8b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "aion-labs/aion-rp-llama-3.1-8b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-02-05",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "knowledge_cutoff": "2023-12",
   "family": "llama",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "max_tokens",
     "temperature",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "aion-labs/aion-rp-llama-3.1-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AionLabs: Aion-RP 1.0 (8B)"
    }
   ]
  },
  {
   "slug": "meta/cerebras-llama-3.3-70b",
   "model_name": "cerebras-llama-3.3-70b",
   "display_name": "cerebras-llama-3.3-70b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cerebras-llama-3.3-70b"
    }
   ]
  },
  {
   "slug": "meta/cerebras-llama-4-maverick-17b-128e-instruct",
   "model_name": "cerebras-llama-4-maverick-17b-128e-instruct",
   "display_name": "Cerebras-Llama-4-Maverick-17B-128E-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "llama",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open multimodal Llama model for strong reasoning and fast responses",
   "released_at": "2025-04-05",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation"
  },
  {
   "slug": "meta/cerebras-llama-4-scout-17b-16e-instruct",
   "model_name": "cerebras-llama-4-scout-17b-16e-instruct",
   "display_name": "Cerebras-Llama-4-Scout-17B-16E-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "llama",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open multimodal Llama model for long-context analysis and efficient agents",
   "released_at": "2025-04-05",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation"
  },
  {
   "slug": "meta/code-llama-13b",
   "model_name": "code-llama-13b",
   "display_name": "Code Llama 13B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-13b"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-13b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 13B"
    }
   ]
  },
  {
   "slug": "meta/code-llama-13b-instruct",
   "model_name": "code-llama-13b-instruct",
   "display_name": "Code Llama 13B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-13b-instruct"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-13b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 13B Instruct"
    }
   ]
  },
  {
   "slug": "meta/code-llama-13b-python",
   "model_name": "code-llama-13b-python",
   "display_name": "Code Llama 13B Python",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-13b-python"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-13b-python"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 13B Python"
    }
   ]
  },
  {
   "slug": "meta/code-llama-34b",
   "model_name": "code-llama-34b",
   "display_name": "Code Llama 34B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-34b"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-34b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 34B"
    }
   ]
  },
  {
   "slug": "meta/code-llama-34b-instruct",
   "model_name": "code-llama-34b-instruct",
   "display_name": "Code Llama 34B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-34b-instruct"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-34b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 34B Instruct"
    }
   ]
  },
  {
   "slug": "meta/code-llama-34b-python",
   "model_name": "code-llama-34b-python",
   "display_name": "Code Llama 34B Python",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-34b-python"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-34b-python"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 34B Python"
    }
   ]
  },
  {
   "slug": "meta/code-llama-70b",
   "model_name": "code-llama-70b",
   "display_name": "Code Llama 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-70b"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 70B"
    }
   ]
  },
  {
   "slug": "meta/code-llama-70b-instruct",
   "model_name": "code-llama-70b-instruct",
   "display_name": "Code Llama 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-70b-instruct"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-70b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/code-llama-70b-python",
   "model_name": "code-llama-70b-python",
   "display_name": "Code Llama 70B Python",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-70b-python"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-70b-python"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 70B Python"
    }
   ]
  },
  {
   "slug": "meta/code-llama-7b",
   "model_name": "code-llama-7b",
   "display_name": "Code Llama 7B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-7b"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 7B"
    }
   ]
  },
  {
   "slug": "meta/code-llama-7b-instruct",
   "model_name": "code-llama-7b-instruct",
   "display_name": "Code Llama 7B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/code-llama-7b-instruct"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/code-llama-7b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Llama 7B Instruct"
    }
   ]
  },
  {
   "slug": "meta/code-llama-7b-python",
   "model_name": "code-llama-7b-python",
   "display_name": "code-llama-7b-python",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-llama-7b-python"
    }
   ]
  },
  {
   "slug": "meta/CodeLlama-13b-Instruct-hf",
   "model_name": "CodeLlama-13b-Instruct-hf",
   "display_name": "CodeLlama-13b-Instruct-hf",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.225"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.225"
      }
     },
     "provider_model_id": "codellama/CodeLlama-13b-Instruct-hf"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "codellama/CodeLlama-13b-Instruct-hf"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CodeLlama-13b-Instruct-hf"
    }
   ]
  },
  {
   "slug": "meta/CodeLlama-34b-Instruct-hf",
   "model_name": "CodeLlama-34b-Instruct-hf",
   "display_name": "CodeLlama-34b-Instruct-hf",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.776"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.776"
      }
     },
     "provider_model_id": "codellama/CodeLlama-34b-Instruct-hf"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "codellama/CodeLlama-34b-Instruct-hf"
   ],
   "intro_i18n": {
    "zh-CN": "Code Llama 是一款专注于代码生成与讨论的大语言模型，支持多种编程语言，适用于开发者工作流。",
    "zh-TW": "Code Llama 是一款專注於程式碼生成與討論的大型語言模型，支援多種語言，優化開發者的工作流程。",
    "ja-JP": "Code Llamaは、コード生成と議論に特化したLLMで、開発者のワークフローを支援する幅広い言語に対応しています。",
    "ru-RU": "Code Llama — LLM, ориентированная на генерацию и обсуждение кода, с широкой поддержкой языков для рабочих процессов разработчиков."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CodeLlama-34b-Instruct-hf"
    }
   ]
  },
  {
   "slug": "meta/CodeLlama-70b-Instruct-hf",
   "model_name": "CodeLlama-70b-Instruct-hf",
   "display_name": "CodeLlama-70b-Instruct-hf",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "codellama/CodeLlama-70b-Instruct-hf"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "codellama/CodeLlama-70b-Instruct-hf"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CodeLlama-70b-Instruct-hf"
    }
   ]
  },
  {
   "slug": "meta/CodeLlama-7b-Instruct-hf",
   "model_name": "CodeLlama-7b-Instruct-hf",
   "display_name": "CodeLlama-7b-Instruct-hf",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "codellama/CodeLlama-7b-Instruct-hf"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "codellama/CodeLlama-7b-Instruct-hf"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CodeLlama-7b-Instruct-hf"
    }
   ]
  },
  {
   "slug": "meta/codellama-7b-instruct-solidity",
   "model_name": "codellama-7b-instruct-solidity",
   "display_name": "AlfredPros: CodeLLaMa 7B Instruct Solidity",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "alfredpros/codellama-7b-instruct-solidity"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "alfredpros/codellama-7b-instruct-solidity"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-04-14",
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alfredpros/codellama-7b-instruct-solidity"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AlfredPros: CodeLLaMa 7B Instruct Solidity"
    }
   ]
  },
  {
   "slug": "meta/cogito-v1-preview-llama-3b",
   "model_name": "cogito-v1-preview-llama-3b",
   "display_name": "Cogito v1 Preview Llama 3B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/cogito-v1-preview-llama-3b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/cogito-v1-preview-llama-3b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cogito v1 Preview Llama 3B"
    }
   ]
  },
  {
   "slug": "meta/cogito-v1-preview-llama-70b",
   "model_name": "cogito-v1-preview-llama-70b",
   "display_name": "Cogito v1 Preview Llama 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/cogito-v1-preview-llama-70b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/cogito-v1-preview-llama-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cogito v1 Preview Llama 70B"
    }
   ]
  },
  {
   "slug": "meta/cogito-v1-preview-llama-70B-Turbo",
   "model_name": "cogito-v1-preview-llama-70B-Turbo",
   "display_name": "cogito-v1-preview-llama-70B-Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "deepcogito/cogito-v1-preview-llama-70B-Turbo"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepcogito/cogito-v1-preview-llama-70B-Turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cogito-v1-preview-llama-70B-Turbo"
    }
   ]
  },
  {
   "slug": "meta/cogito-v1-preview-llama-8b",
   "model_name": "cogito-v1-preview-llama-8b",
   "display_name": "Cogito v1 Preview Llama 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/cogito-v1-preview-llama-8b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/cogito-v1-preview-llama-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cogito v1 Preview Llama 8B"
    }
   ]
  },
  {
   "slug": "meta/databricks-llama-2-70b-chat",
   "model_name": "databricks-llama-2-70b-chat",
   "display_name": "databricks-llama-2-70b-chat",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.50001"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5000300000000002"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-llama-2-70b-chat"
    }
   ]
  },
  {
   "slug": "meta/databricks-llama-4-maverick",
   "model_name": "databricks-llama-4-maverick",
   "display_name": "databricks-llama-4-maverick",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.50001"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5000300000000002"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-llama-4-maverick"
    }
   ]
  },
  {
   "slug": "meta/databricks-meta-llama-3-1-405b-instruct",
   "model_name": "databricks-meta-llama-3-1-405b-instruct",
   "display_name": "databricks-meta-llama-3-1-405b-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.00003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.000020000000002"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-meta-llama-3-1-405b-instruct"
    }
   ]
  },
  {
   "slug": "meta/databricks-meta-llama-3-1-8b-instruct",
   "model_name": "databricks-meta-llama-3-1-8b-instruct",
   "display_name": "databricks-meta-llama-3-1-8b-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15000999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45003000000000007"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 200000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-meta-llama-3-1-8b-instruct"
    }
   ]
  },
  {
   "slug": "meta/databricks-meta-llama-3-3-70b-instruct",
   "model_name": "databricks-meta-llama-3-3-70b-instruct",
   "display_name": "databricks-meta-llama-3-3-70b-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.50001"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5000300000000002"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-meta-llama-3-3-70b-instruct"
    }
   ]
  },
  {
   "slug": "meta/databricks-meta-llama-3-70b-instruct",
   "model_name": "databricks-meta-llama-3-70b-instruct",
   "display_name": "databricks-meta-llama-3-70b-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.00002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.9999900000000002"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-meta-llama-3-70b-instruct"
    }
   ]
  },
  {
   "slug": "meta/deepinfra-llama-3.1-8b-instant",
   "model_name": "deepinfra-llama-3.1-8b-instant",
   "display_name": "deepinfra-llama-3.1-8b-instant",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.033"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.054978"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra-llama-3.1-8b-instant"
    }
   ]
  },
  {
   "slug": "meta/deepinfra-llama-3.3-70b-instant-turbo",
   "model_name": "deepinfra-llama-3.3-70b-instant-turbo",
   "display_name": "deepinfra-llama-3.3-70b-instant-turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.352"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra-llama-3.3-70b-instant-turbo"
    }
   ]
  },
  {
   "slug": "meta/deepinfra-llama-4-maverick-17b-128e-instruct",
   "model_name": "deepinfra-llama-4-maverick-17b-128e-instruct",
   "display_name": "deepinfra-llama-4-maverick-17b-128e-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.6"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra-llama-4-maverick-17b-128e-instruct"
    }
   ]
  },
  {
   "slug": "meta/deepinfra-llama-4-scout-17b-16e-instruct",
   "model_name": "deepinfra-llama-4-scout-17b-16e-instruct",
   "display_name": "deepinfra-llama-4-scout-17b-16e-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra-llama-4-scout-17b-16e-instruct"
    }
   ]
  },
  {
   "slug": "meta/dobby-mini-unhinged-plus-llama-3-1-8b",
   "model_name": "dobby-mini-unhinged-plus-llama-3-1-8b",
   "display_name": "Dobby Mini Unhinged Plus Llama 3.1 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/sentientfoundation-serverless/models/dobby-mini-unhinged-plus-llama-3-1-8b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "dobby-mini-unhinged-plus-llama-3.1-8b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/sentientfoundation-serverless/models/dobby-mini-unhinged-plus-llama-3-1-8b",
    "dobby-mini-unhinged-plus-llama-3.1-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Dobby Mini Unhinged Plus Llama 3.1 8B"
    }
   ]
  },
  {
   "slug": "meta/dobby-unhinged-llama-3-3-70b-new",
   "model_name": "dobby-unhinged-llama-3-3-70b-new",
   "display_name": "Dobby-Unhinged-Llama-3.3-70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/sentientfoundation/models/dobby-unhinged-llama-3-3-70b-new"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/sentientfoundation/models/dobby-unhinged-llama-3-3-70b-new"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Dobby-Unhinged-Llama-3.3-70B"
    }
   ]
  },
  {
   "slug": "meta/dracarys-llama-3_1-70b-instruct",
   "model_name": "dracarys-llama-3_1-70b-instruct",
   "display_name": "dracarys-llama-3.1-70b-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "abacusai/dracarys-llama-3_1-70b-instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-09-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "abacusai/dracarys-llama-3_1-70b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "dracarys-llama-3.1-70b-instruct"
    }
   ]
  },
  {
   "slug": "meta/esm2-650m",
   "model_name": "esm2-650m",
   "display_name": "esm2-650m",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/esm2-650m"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-08-29",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/esm2-650m"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "esm2-650m"
    }
   ]
  },
  {
   "slug": "meta/esmfold",
   "model_name": "esmfold",
   "display_name": "esmfold",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/esmfold"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-03-15",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/esmfold"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "esmfold"
    }
   ]
  },
  {
   "slug": "meta/eva-llama-3.33-70b",
   "model_name": "eva-llama-3.33-70b",
   "display_name": "eva-llama-3.33-70b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "eva-unit-01/eva-llama-3.33-70b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "eva-unit-01/eva-llama-3.33-70b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "eva-llama-3.33-70b"
    }
   ]
  },
  {
   "slug": "meta/EVA-LLaMA-3.33-70B-v0.0",
   "model_name": "EVA-LLaMA-3.33-70B-v0.0",
   "display_name": "EVA Llama 3.33 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.006"
      }
     },
     "provider_model_id": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-07-26",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "EVA Llama 3.33 70B"
    }
   ]
  },
  {
   "slug": "meta/EVA-LLaMA-3.33-70B-v0.1",
   "model_name": "EVA-LLaMA-3.33-70B-v0.1",
   "display_name": "EVA-LLaMA-3.33-70B-v0.1",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.006"
      }
     },
     "provider_model_id": "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-09-25",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "EVA-LLaMA-3.33-70B-v0.1"
    }
   ]
  },
  {
   "slug": "meta/fireworks/models/llama-v3-8b-instruct",
   "model_name": "fireworks/models/llama-v3-8b-instruct",
   "display_name": "Llama 3 8B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3-8b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3-8b-instruct"
    }
   ],
   "knowledge_cutoff": "2023-03",
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3-8b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Meta 开发并发布了 Meta Llama 3 大语言模型系列，包括 8B 和 70B 参数规模的预训练与指令微调文本生成模型。Llama 3 的指令微调模型专为对话场景优化，在多个行业通用基准测试中优于许多现有的开源聊天模型。",
    "zh-TW": "Meta 開發並發布了 Meta Llama 3 大型語言模型系列，涵蓋 8B 和 70B 參數的預訓練與指令微調文字生成模型。Llama 3 的指令微調模型專為對話應用優化，在多項業界常用基準測試中表現優於許多現有的開源聊天模型。",
    "ja-JP": "Metaは、8Bおよび70Bの事前学習済みおよび命令調整済みのテキスト生成モデルを含むMeta Llama 3 LLMシリーズを開発・公開しました。Llama 3の命令調整済みモデルは会話用途に最適化されており、業界標準のベンチマークにおいて多くの既存のオープンチャットモデルを上回る性能を発揮します。",
    "ru-RU": "Meta разработала и выпустила серию LLM Meta Llama 3 — набор предварительно обученных и дообученных на инструкциях моделей генерации текста с объемом 8B и 70B параметров. Модели Llama 3, дообученные на инструкциях, оптимизированы для ведения диалогов и превосходят многие существующие открытые чат-модели по общепринятым отраслевым метрикам."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 8B Instruct"
    }
   ]
  },
  {
   "slug": "meta/groq-llama-3.1-8b-instant",
   "model_name": "groq-llama-3.1-8b-instant",
   "display_name": "groq-llama-3.1-8b-instant",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.055"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.088"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "groq-llama-3.1-8b-instant"
    }
   ]
  },
  {
   "slug": "meta/groq-llama-3.3-70b-versatile",
   "model_name": "groq-llama-3.3-70b-versatile",
   "display_name": "groq-llama-3.3-70b-versatile",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.649"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.869011"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "groq-llama-3.3-70b-versatile"
    }
   ]
  },
  {
   "slug": "meta/groq-llama-4-maverick-17b-128e-instruct",
   "model_name": "groq-llama-4-maverick-17b-128e-instruct",
   "display_name": "Groq-Llama-4-Maverick-17B-128E-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "llama",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     }
    }
   ],
   "intro": "Open multimodal Llama model for strong reasoning and fast responses",
   "released_at": "2025-04-05",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation"
  },
  {
   "slug": "meta/groq-llama-4-scout-17b-16e-instruct",
   "model_name": "groq-llama-4-scout-17b-16e-instruct",
   "display_name": "groq-llama-4-scout-17b-16e-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.122"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.366"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "groq-llama-4-scout-17b-16e-instruct"
    }
   ]
  },
  {
   "slug": "meta/hermes-2-pro-llama-3-8b",
   "model_name": "hermes-2-pro-llama-3-8b",
   "display_name": "Hermes 2 Pro Llama 3 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "nousresearch/hermes-2-pro-llama-3-8b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "nousresearch/hermes-2-pro-llama-3-8b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "nousresearch/hermes-2-pro-llama-3-8b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "nousresearch/hermes-2-pro-llama-3-8b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-06-27",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-05",
   "family": "llama",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "functions",
     "max_tokens",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nousresearch/hermes-2-pro-llama-3-8b"
   ],
   "intro_i18n": {
    "zh-CN": "Hermes 2 Pro Llama 3 8B 是 Nous Hermes 2 的更新版本，采用最新内部开发的数据集训练。",
    "zh-TW": "Hermes 2 Pro Llama 3 8B 是 Nous Hermes 2 的更新版本，採用最新內部開發的資料集。",
    "ja-JP": "Hermes 2 Pro Llama 3 8Bは、Nous Hermes 2の最新版で、社内開発の最新データセットを使用しています。",
    "ru-RU": "Hermes 2 Pro Llama 3 8B — обновлённая версия Nous Hermes 2 с новейшими внутренними датасетами."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes 2 Pro Llama 3 8B"
    }
   ]
  },
  {
   "slug": "meta/llama-2-13b-chat",
   "model_name": "llama-2-13b-chat",
   "display_name": "llama-2-13b-chat",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "meta-llama/llama-2-13b-chat"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/llama-2-13b-chat"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-2-13b-chat"
    }
   ]
  },
  {
   "slug": "meta/Llama-2-13b-chat-hf",
   "model_name": "Llama-2-13b-chat-hf",
   "display_name": "Llama-2-13b-chat-hf",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.225"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.225"
      }
     },
     "provider_model_id": "meta-llama/Llama-2-13b-chat-hf"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-2-13b-chat-hf"
   ],
   "intro_i18n": {
    "zh-CN": "LLaMA-2 Chat（13B）具备强大的语言处理能力，提供出色的对话体验。",
    "zh-TW": "LLaMA-2 Chat（13B）具備強大的語言處理能力與穩定的對話體驗。",
    "ja-JP": "LLaMA-2 Chat（13B）は強力な言語処理能力と安定したチャット体験を提供します。",
    "ru-RU": "LLaMA-2 Chat (13B) обеспечивает высокое качество обработки языка и стабильный опыт общения."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-2-13b-chat-hf"
    }
   ]
  },
  {
   "slug": "meta/Llama-2-70b-chat-hf",
   "model_name": "Llama-2-70b-chat-hf",
   "display_name": "Llama-2-70b-chat-hf",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "meta-llama/Llama-2-70b-chat-hf"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-2-70b-chat-hf"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-2-70b-chat-hf"
    }
   ]
  },
  {
   "slug": "meta/Llama-2-7B-32K-Instruct",
   "model_name": "Llama-2-7B-32K-Instruct",
   "display_name": "Llama-2-7B-32K-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "togethercomputer/Llama-2-7B-32K-Instruct"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/Llama-2-7B-32K-Instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-2-7B-32K-Instruct"
    }
   ]
  },
  {
   "slug": "meta/Llama-2-7b-chat-hf",
   "model_name": "Llama-2-7b-chat-hf",
   "display_name": "Llama-2-7b-chat-hf",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "meta-llama/Llama-2-7b-chat-hf"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-2-7b-chat-hf"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-2-7b-chat-hf"
    }
   ]
  },
  {
   "slug": "meta/llama-3-1-405b",
   "model_name": "llama-3-1-405b",
   "display_name": "Llama 3.1 405B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+computeprices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "llama-3.1-405b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.1-405B",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "capabilities": {
    "function_calling": true
   },
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "knowledge_cutoff": "2023-12",
   "family": "Llama",
   "released_at": "2024-08-02",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llama-3.1-405b",
    "meta-llama/Llama-3.1-405B",
    "meta-llama/llama-3.1-405b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 405B"
    }
   ]
  },
  {
   "slug": "meta/llama-3-1-70b",
   "model_name": "llama-3-1-70b",
   "display_name": "Llama 3.1 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.44"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     },
     "provider_model_id": "llama-3.1-70b"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta/llama-3.1-70b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta/llama-3.1-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llama-3.1-70b",
    "meta/llama-3.1-70b"
   ],
   "intro_i18n": {
    "zh-CN": "更新版 Meta Llama 3 70B Instruct，支持 128K 上下文、多语言能力，并提升推理表现。",
    "zh-TW": "更新版 Meta Llama 3 70B Instruct，支援 128K 語境、多語言能力與強化推理表現。",
    "ja-JP": "128K コンテキスト、多言語対応、推論能力の向上を備えた最新の Meta Llama 3 70B Instruct。",
    "ru-RU": "Обновлённая Meta Llama 3 70B Instruct с контекстом 128K, поддержкой многоязычности и улучшенным рассуждением."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.7",
     "new": "0.4"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.7",
     "new": "0.4"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.4",
     "new": "0.7"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.4",
     "new": "0.7"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.7",
     "new": "0.4"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.7",
     "new": "0.4"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.4",
     "new": "0.7"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.4",
     "new": "0.7"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.7",
     "new": "0.4"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.7",
     "new": "0.4"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3-1-8b",
   "model_name": "llama-3-1-8b",
   "display_name": "Llama 3.1 8B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "hyperstack",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "meta/llama-3.1-8b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "meta/llama-3.1-8b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-3.1-8b"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.1 8B 支持 128K 上下文窗口，适用于实时对话和数据分析，相较于更大模型具有显著成本优势。由 Groq 在 LPU 硬件上提供服务，实现快速高效的推理。",
    "zh-TW": "Llama 3.1 8B 支援 128K 語境視窗，適合即時對話與資料分析，與大型模型相比具備顯著成本優勢。透過 Groq 的 LPU 硬體提供快速且高效的推論服務。",
    "ja-JP": "Llama 3.1 8B は 128K のコンテキストウィンドウをサポートし、リアルタイムチャットやデータ分析に最適。大規模モデルと比較して大幅なコスト削減を実現。Groq の LPU ハードウェア上で提供され、高速かつ効率的な推論を実現。",
    "ru-RU": "Llama 3.1 8B поддерживает окно контекста 128K, идеально подходит для общения в реальном времени и анализа данных, обеспечивая значительную экономию по сравнению с более крупными моделями. Предоставляется через Groq на аппаратуре LPU для быстрого и эффективного вывода."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.05",
     "new": "0.03"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.03",
     "new": "0.05"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.05",
     "new": "0.03"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.03",
     "new": "0.05"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.05",
     "new": "0.03"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 8B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3-2-11b-vision",
   "model_name": "llama-3-2-11b-vision",
   "display_name": "Llama 3.2 11B Vision",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.345"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.345"
      }
     }
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.345"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.345"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1725"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.345"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.345"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "family": "Llama",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 11B Vision"
    }
   ]
  },
  {
   "slug": "meta/llama-3-2-11b-vision-instruct",
   "model_name": "llama-3-2-11b-vision-instruct",
   "display_name": "Llama 3.2 11B Vision Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-11b-vision-instruct:free"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.37"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.37"
      }
     },
     "provider_model_id": "llama-3.2-11b-vision-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.37"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.37"
      }
     },
     "provider_model_id": "Llama-3.2-11B-Vision-Instruct"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.37"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.37"
      }
     },
     "provider_model_id": "llama-3.2-11b-vision-instruct"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.049"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-3.2-11b-vision-instruct"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0485"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.676"
      }
     },
     "provider_model_id": "@cf/meta/llama-3.2-11b-vision-instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.049"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.049"
      }
     },
     "provider_model_id": "Llama-3.2-11B-Vision-Instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.2-11b-vision-instruct"
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     }
    },
    {
     "provider": "inference",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.055"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.055"
      }
     },
     "provider_model_id": "meta/llama-3.2-11b-vision-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.049"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.049"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-11b-vision-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.2-11b-vision-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.345"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.345"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-11b-vision-instruct"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Llama-3.2-11B-Vision-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.049"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.049"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct"
    }
   ],
   "intro": "Open Llama multimodal model for image understanding and text reasoning",
   "released_at": "2024-09-25",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "knowledge_cutoff": "2023-12",
   "docs_url": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview",
   "model_type": "vision_understanding",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-3.2-11b-vision-instruct",
    "Llama-3.2-11B-Vision-Instruct",
    "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct",
    "llama-3.2-11b-vision-instruct",
    "llama-3.2-11b-vision-instruct:free",
    "meta-llama/Llama-3.2-11B-Vision-Instruct",
    "meta-llama/llama-3.2-11b-vision-instruct",
    "meta-llama/llama-3.2-11b-vision-instruct:free",
    "meta/llama-3.2-11b-vision-instruct",
    "workers-ai/@cf/meta/llama-3.2-11b-vision-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "在高分辨率图像上具备强大的图像推理能力，适用于视觉理解类应用。",
    "zh-TW": "具備高解析度圖像的強大圖像推理能力，適用於視覺理解應用。",
    "ja-JP": "高解像度画像に対する強力な画像推論能力を持ち、視覚理解アプリケーションに適しています。",
    "ru-RU": "Мощное логическое мышление по изображениям высокого разрешения, подходит для приложений визуального понимания."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 11B Vision Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3-2-1b",
   "model_name": "llama-3-2-1b",
   "display_name": "Llama 3.2 1B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.027"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.201"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "meta/llama-3.2-1b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "meta/llama-3.2-1b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-3.2-1b"
   ],
   "intro_i18n": {
    "zh-CN": "纯文本模型，适用于设备端的多语言本地检索、摘要和改写等场景。",
    "zh-TW": "純文字模型，適用於裝置端應用，如多語言本地檢索、摘要與重寫。",
    "ja-JP": "多言語ローカル検索、要約、リライトなどのオンデバイス用途向けのテキスト専用モデル。",
    "ru-RU": "Модель только для текста, предназначенная для использования на устройствах, таких как многоязычный локальный поиск, суммирование и переформулирование."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 1B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3-2-1b-instruct",
   "model_name": "llama-3-2-1b-instruct",
   "display_name": "Llama 3.2 1B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "unsloth/Llama-3.2-1B-Instruct"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.027"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-3.2-1b-instruct"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.027"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.201"
      }
     },
     "provider_model_id": "@cf/meta/llama-3.2-1b-instruct"
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "inference",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "meta/llama-3.2-1b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.027"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-1b-instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-1b-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.2-1b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.027"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.201"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-1b-instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.060000000000000005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.060000000000000005"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.2-1B-Instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-09-25",
   "max_input_tokens": 60000,
   "max_output_tokens": 60000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "knowledge_cutoff": "2023-12",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-3.2-1b-instruct",
    "llama-3.2-1b-instruct",
    "meta-llama/Llama-3.2-1B-Instruct",
    "meta-llama/llama-3.2-1b-instruct",
    "meta/llama-3.2-1b-instruct",
    "unsloth/Llama-3.2-1B-Instruct",
    "workers-ai/@cf/meta/llama-3.2-1b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 1B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3-2-3b",
   "model_name": "llama-3-2-3b",
   "display_name": "Llama 3.2 3B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "llama-3.2-3b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "meta/llama-3.2-3b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "meta/llama-3.2-3b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llama-3.2-3b",
    "meta/llama-3.2-3b"
   ],
   "intro_i18n": {
    "zh-CN": "纯文本模型，针对设备端的多语言本地检索、摘要和改写等场景进行微调。",
    "zh-TW": "純文字模型，經微調以支援裝置端應用，如多語言本地檢索、摘要與重寫。",
    "ja-JP": "多言語ローカル検索、要約、リライトなどのオンデバイス用途向けにファインチューニングされたテキスト専用モデル。",
    "ru-RU": "Модель только для текста, дообученная для использования на устройствах, таких как многоязычный локальный поиск, суммирование и переформулирование."
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "openrouter",
     "charge": "completion",
     "old": "0.335",
     "new": "0.33"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "0.0509",
     "new": "0.05"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 3B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3-2-3b-instruct",
   "model_name": "llama-3-2-3b-instruct",
   "display_name": "Llama 3.2 3B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-3b-instruct:free"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "unsloth/Llama-3.2-3B-Instruct"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.051"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-3.2-3b-instruct"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0509"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.335"
      }
     },
     "provider_model_id": "@cf/meta/llama-3.2-3b-instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "Llama-3.2-3B-Instruct"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Llama-3.2-3B-Instruct"
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "inference",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "meta/llama-3.2-3b-instruct"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-3b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.051"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-3b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "llama-3.2-3b-instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0493"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-3b-instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "llama-3.2-3b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-3b-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.2-3b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-3b-instruct"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.031765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.052941"
      }
     },
     "provider_model_id": "meta-llama/llama-3.2-3b-instruct"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "novita/meta-llama/llama-3.2-3b-instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Llama-3.2-3B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.060000000000000005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.060000000000000005"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.2-3B-Instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-09-18",
   "max_input_tokens": 32768,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "knowledge_cutoff": "2023-12",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-3.2-3b-instruct",
    "Llama-3.2-3B-Instruct",
    "deepinfra/meta-llama/Llama-3.2-3B-Instruct",
    "llama-3.2-3b-instruct",
    "llama-3.2-3b-instruct:free",
    "meta-llama/Llama-3.2-3B-Instruct",
    "meta-llama/llama-3.2-3b-instruct",
    "meta-llama/llama-3.2-3b-instruct:free",
    "meta/llama-3.2-3b-instruct",
    "novita/meta-llama/llama-3.2-3b-instruct",
    "unsloth/Llama-3.2-3B-Instruct",
    "workers-ai/@cf/meta/llama-3.2-3b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "meta-llama/llama-3.2-3b-instruct",
    "zh-TW": "meta-llama/llama-3.2-3b-instruct",
    "ja-JP": "meta-llama/llama-3.2-3b-instruct",
    "ru-RU": "meta-llama/llama-3.2-3b-instruct"
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "openrouter",
     "charge": "completion",
     "old": "0.335",
     "new": "0.33"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "0.0509",
     "new": "0.05"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 3B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3-2-90b-vision-instruct",
   "model_name": "llama-3-2-90b-vision-instruct",
   "display_name": "Llama-3.2-90B-Vision-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.2-90B-Vision-Instruct"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.04"
      }
     },
     "provider_model_id": "llama-3.2-90b-vision-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.04"
      }
     },
     "provider_model_id": "Llama-3.2-90B-Vision-Instruct"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.04"
      }
     },
     "provider_model_id": "llama-3.2-90b-vision-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.2-90b-vision-instruct"
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.2-90B-Vision-Instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.2-90b-vision-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "llama-3.2-90b-vision-instruct"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Llama-3.2-90B-Vision-Instruct"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "Llama-3.2-90B-Vision-Instruct"
    }
   ],
   "intro": "Open Llama multimodal model for image understanding and text reasoning",
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Llama-3.2-90B-Vision-Instruct",
    "deepinfra/meta-llama/Llama-3.2-90B-Vision-Instruct",
    "llama-3.2-90b-vision-instruct",
    "meta-llama/Llama-3.2-90B-Vision-Instruct",
    "meta-llama/llama-3.2-90b-vision-instruct",
    "meta/llama-3.2-90b-vision-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "为视觉理解代理应用提供高级图像推理能力。",
    "zh-TW": "為視覺理解代理應用提供先進的圖像推理能力。",
    "ja-JP": "視覚理解エージェントアプリケーション向けの高度な画像推論。",
    "ru-RU": "Продвинутое визуальное рассуждение для приложений агентов визуального понимания."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.2-90B-Vision-Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3-2-instruct-90b",
   "model_name": "llama-3-2-instruct-90b",
   "display_name": "Llama 3.2 Instruct 90B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 Instruct 90B"
    }
   ]
  },
  {
   "slug": "meta/llama-3-3-70b",
   "model_name": "llama-3-3-70b",
   "display_name": "Llama-3.3-70B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "llama-3.3-70b"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.02747555"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.02747555"
      }
     },
     "provider_model_id": "llama-3.3-70b"
    },
    {
     "provider": "cerebras",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "llama-3.3-70b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     }
    },
    {
     "provider": "hyperstack",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6066"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.0386"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3033"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.029"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.029"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.04"
      }
     }
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     },
     "provider_model_id": "llama-3.3-70b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.3-70b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta/llama-3.3-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llama-3.3-70b",
    "meta/llama-3.3-70b"
   ],
   "intro_i18n": {
    "zh-CN": "性能与效率的完美平衡。专为内容创作、企业应用和研究中的高性能对话式 AI 而构建，具备强大的语言理解能力，适用于摘要、分类、情感分析和代码生成。",
    "zh-TW": "效能與效率的完美平衡。專為高效能對話式 AI 應用於內容創作、企業應用與研究而設計，具備強大的語言理解能力，適用於摘要、分類、情感分析與程式碼生成。",
    "ja-JP": "性能と効率の完璧なバランス。コンテンツ制作、企業アプリ、研究における高性能な会話型 AI 向けに構築され、要約、分類、感情分析、コード生成において優れた言語理解を発揮。",
    "ru-RU": "Идеальный баланс производительности и эффективности. Создана для высокопроизводительного разговорного ИИ в создании контента, корпоративных приложениях и исследованиях, с высоким уровнем понимания языка для суммирования, классификации, анализа тональности и генерации кода."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.029336732",
     "new": "1.02747555"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.029336732",
     "new": "1.02747555"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.028939373",
     "new": "1.029336732"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.028939373",
     "new": "1.029336732"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "1.0274",
     "new": "1.029"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "1.0274",
     "new": "1.029"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.029727287",
     "new": "1.028939373"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.029727287",
     "new": "1.028939373"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "1.0303",
     "new": "1.0274"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "1.0303",
     "new": "1.0274"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.029312756",
     "new": "1.029727287"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.029312756",
     "new": "1.029727287"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.029598083",
     "new": "1.029312756"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.029598083",
     "new": "1.029312756"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.2763",
     "new": "0.3033"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "1.0746",
     "new": "1.0386"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.5526",
     "new": "0.6066"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.0242873",
     "new": "1.029598083"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.0242873",
     "new": "1.029598083"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.3033",
     "new": "0.2763"
    }
   ]
  },
  {
   "slug": "meta/llama-3-70b",
   "model_name": "llama-3-70b",
   "display_name": "Llama 3 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.51"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.74"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "family": "Llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 70B"
    }
   ]
  },
  {
   "slug": "meta/Llama-3-70b-chat-hf",
   "model_name": "Llama-3-70b-chat-hf",
   "display_name": "Llama-3-70b-chat-hf",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "meta-llama/Llama-3-70b-chat-hf"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-3-70b-chat-hf"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3 70B Instruct Reference 是一款强大的对话模型，适用于复杂对话场景。",
    "zh-TW": "Llama 3 70B Instruct Reference 是一款適用於複雜對話的強大聊天模型。",
    "ja-JP": "Llama 3 70B Instruct Referenceは複雑な対話に対応する強力なチャットモデルです。",
    "ru-RU": "Llama 3 70B Instruct Reference — мощная модель для сложных диалогов."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3-70b-chat-hf"
    }
   ]
  },
  {
   "slug": "meta/llama-3-70b-instruct",
   "model_name": "llama-3-70b-instruct",
   "display_name": "Llama3 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.51"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.74"
      }
     },
     "provider_model_id": "meta-llama/llama-3-70b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.51"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.74"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.51"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.74"
      }
     },
     "provider_model_id": "meta-llama/llama-3-70b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.51"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.74"
      }
     },
     "provider_model_id": "meta-llama/llama-3-70b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "provider_model_id": "meta-llama/llama-3-70b-instruct"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.51"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.74"
      }
     },
     "provider_model_id": "novita/meta-llama/llama-3-70b-instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-04-25",
   "max_input_tokens": 8192,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "deprecated": true,
   "knowledge_cutoff": "2023-12",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/llama-3-70b-instruct",
    "meta-llama/llama-3-70b-instruct:nitro",
    "novita/meta-llama/llama-3-70b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3 70B Instruct 针对高质量对话进行了优化，在人工评估中表现出色。",
    "zh-TW": "Llama 3 70B Instruct 針對高品質對話進行優化，在人類評估中表現優異。",
    "ja-JP": "Llama 3 70B Instructは高品質な対話に最適化されており、人間による評価でも高いパフォーマンスを示します。",
    "ru-RU": "Llama 3 70B Instruct оптимизирована для высококачественных диалогов и демонстрирует отличные результаты в оценках с участием людей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama3 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3-8b",
   "model_name": "llama-3-8b",
   "display_name": "Llama 3 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "family": "Llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 8B"
    }
   ]
  },
  {
   "slug": "meta/Llama-3-8b-chat-hf",
   "model_name": "Llama-3-8b-chat-hf",
   "display_name": "Meta Llama 3 8B Instruct Reference",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "meta-llama/Llama-3-8b-chat-hf"
    }
   ],
   "capabilities": {},
   "released_at": "2024-04-18",
   "max_input_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-3-8b-chat-hf"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3 8B Instruct Reference 支持多语言，具备广泛的领域知识。",
    "zh-TW": "Llama 3 8B Instruct Reference 提供多語言支援與廣泛的領域知識。",
    "ja-JP": "Llama 3 8B Instruct Referenceは多言語対応と幅広い分野の知識を提供します。",
    "ru-RU": "Llama 3 8B Instruct Reference поддерживает многоязычность и обладает широкими знаниями в различных областях."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3 8B Instruct Reference"
    }
   ]
  },
  {
   "slug": "meta/llama-3-8b-instruct",
   "model_name": "llama-3-8b-instruct",
   "display_name": "Llama 3 8B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.83"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-3-8b-instruct"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.83"
      }
     },
     "provider_model_id": "@cf/meta/llama-3-8b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "meta-llama/llama-3-8b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "meta-llama/llama-3-8b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "meta-llama/llama-3-8b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "meta-llama/llama-3-8b-instruct"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "novita/meta-llama/llama-3-8b-instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-04-25",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2023-12",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-3-8b-instruct",
    "meta-llama/llama-3-8b-instruct",
    "meta-llama/llama-3-8b-instruct:extended",
    "meta-llama/llama-3-8b-instruct:free",
    "novita/meta-llama/llama-3-8b-instruct",
    "workers-ai/@cf/meta/llama-3-8b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3 8B Instruct 针对高质量对话进行了优化，超越众多闭源模型。",
    "zh-TW": "Llama 3 8B Instruct 針對高品質對話進行優化，表現超越多數封閉模型。",
    "ja-JP": "Llama 3 8B Instructは高品質な対話に最適化されており、多くのクローズドモデルを上回る性能を発揮します。",
    "ru-RU": "Llama 3 8B Instruct оптимизирована для высококачественных диалогов, превосходя многие закрытые модели."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 8B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3-lumimaid-70b",
   "model_name": "llama-3-lumimaid-70b",
   "display_name": "llama-3-lumimaid-70b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "neversleep/llama-3-lumimaid-70b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "neversleep/llama-3-lumimaid-70b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3-lumimaid-70b"
    }
   ]
  },
  {
   "slug": "meta/llama-3-lumimaid-8b",
   "model_name": "llama-3-lumimaid-8b",
   "display_name": "llama-3-lumimaid-8b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "neversleep/llama-3-lumimaid-8b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "neversleep/llama-3-lumimaid-8b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3-lumimaid-8b"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-405b-instruct-maas",
   "model_name": "llama-3.1-405b-instruct-maas",
   "display_name": "llama-3.1-405b-instruct-maas",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      }
     },
     "provider_model_id": "meta/llama-3.1-405b-instruct-maas",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas",
   "max_input_tokens": 128000,
   "max_output_tokens": 2048,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-3.1-405b-instruct-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.1-405b-instruct-maas"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-405b-instruct:free",
   "model_name": "llama-3.1-405b-instruct:free",
   "display_name": "Llama 3.1 405B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "llama-3.1-405b-instruct"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "llama-3.1-405b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-405b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "llama-3.1-405b-instruct"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "hf:meta-llama/Llama-3.1-405B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.1-405B-Instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hf:meta-llama/Llama-3.1-405B-Instruct",
    "llama-3.1-405b-instruct",
    "meta-llama/Llama-3.1-405B-Instruct",
    "meta-llama/llama-3.1-405b-instruct",
    "meta-llama/llama-3.1-405b-instruct:free",
    "meta/llama-3.1-405b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 405B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-405b-reasoning",
   "model_name": "llama-3.1-405b-reasoning",
   "display_name": "llama-3.1-405b-reasoning",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.1-405b-reasoning"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-70b-instruct-maas",
   "model_name": "llama-3.1-70b-instruct-maas",
   "display_name": "llama-3.1-70b-instruct-maas",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.1-70b-instruct-maas"
    }
   ],
   "docs_url": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas",
   "max_input_tokens": 128000,
   "max_output_tokens": 2048,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-3.1-70b-instruct-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.1-70b-instruct-maas"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-70b-instruct:free",
   "model_name": "llama-3.1-70b-instruct:free",
   "display_name": "Llama 3.1 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-70b-instruct:free"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-70b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-70b-instruct"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.1-70B-Instruct"
    }
   ],
   "intro": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-3.1-70B-Instruct",
    "meta-llama/llama-3.1-70b-instruct",
    "meta-llama/llama-3.1-70b-instruct:free"
   ],
   "intro_i18n": {
    "zh-CN": "Meta 最新的 Llama 3.1 系列，70B 指令微调版本，专为高质量对话优化。在行业评估中表现优异，超越领先闭源模型。（仅对企业认证用户开放）",
    "zh-TW": "Meta 最新的 Llama 3.1 系列，70B 指令微調版本，針對高品質對話進行優化。在業界評估中，表現優於多數封閉模型。（僅限企業驗證用戶使用）",
    "ja-JP": "Metaの最新Llama 3.1シリーズの70B命令調整バージョンで、高品質な対話に最適化されています。業界評価において、主要なクローズドモデルに対して優れた性能を示しています。（企業認証済みの組織のみ利用可能）",
    "ru-RU": "Последняя серия Meta Llama 3.1, вариант с 70 миллиардами параметров, обученный на инструкциях и оптимизированный для высококачественных диалогов. В отраслевых оценках показывает отличные результаты по сравнению с ведущими закрытыми моделями. (Доступна только для проверенных корпоративных клиентов.)"
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-70b-versatile",
   "model_name": "llama-3.1-70b-versatile",
   "display_name": "Llama 3.1 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     }
    }
   ],
   "capabilities": {
    "function_calling": true
   },
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Llama 3.1 70B 提供更强的 AI 推理能力，适用于复杂应用，支持高效能计算与高准确率。",
    "zh-TW": "Llama 3.1 70B 提供更強的 AI 推理能力，適用於複雜應用，支援高效能運算與高準確度。",
    "ja-JP": "Llama 3.1 70B は、複雑なアプリケーション向けに強化されたAI推論を提供し、高効率かつ高精度で大規模計算をサポートします。",
    "ru-RU": "Llama 3.1 70B обеспечивает улучшенное логическое мышление для сложных приложений, поддерживая высокую вычислительную нагрузку с высокой эффективностью и точностью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 70B"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-8b-cs",
   "model_name": "llama-3.1-8b-cs",
   "display_name": "Llama-3.1-8B-CS",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "cerebras/llama-3.1-8b-cs"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-05-13",
   "max_input_tokens": 128000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cerebras/llama-3.1-8b-cs"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.1-8B-CS"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-8b-instant",
   "model_name": "llama-3.1-8b-instant",
   "display_name": "Llama 3.1 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instant"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.049999999999999996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "groq/llama-3.1-8b-instant"
    }
   ],
   "intro": "Compact Llama instruction model for fast chat and local deployment",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "groq/llama-3.1-8b-instant",
    "meta-llama/llama-3.1-8b-instant"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.1 8B 是一款高效模型，文本生成速度快，适合大规模、低成本应用。",
    "zh-TW": "Llama 3.1 8B 是一款高效率模型，具備快速文字生成能力，適合大規模、具成本效益的應用場景。",
    "ja-JP": "Llama 3.1 8B は、高速なテキスト生成を実現する高効率モデルで、大規模かつコスト効率の高いアプリケーションに最適です。",
    "ru-RU": "Llama 3.1 8B — высокоэффективная модель с быстрой генерацией текста, идеально подходящая для масштабных и экономичных приложений."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "reasoning: true→false"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "fastrouter",
     "charge": "completion",
     "old": "0.08",
     "new": "0.05"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "fastrouter",
     "charge": "prompt",
     "old": "0.05",
     "new": "0.02"
    },
    {
     "date": "2026-07-07",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 8B"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-8b-instruct-bf16",
   "model_name": "llama-3.1-8b-instruct-bf16",
   "display_name": "Llama 3.1 8B Instruct BF16",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct-bf16"
    }
   ],
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/llama-3.1-8b-instruct-bf16"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 8B Instruct BF16"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-8b-instruct-maas",
   "model_name": "llama-3.1-8b-instruct-maas",
   "display_name": "llama-3.1-8b-instruct-maas",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.1-8b-instruct-maas",
     "region": "us-central1"
    }
   ],
   "docs_url": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas",
   "max_input_tokens": 128000,
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {
    "vision": true,
    "function_calling": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-3.1-8b-instruct-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.1-8b-instruct-maas"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-8b-instruct-turbo",
   "model_name": "llama-3.1-8b-instruct-turbo",
   "display_name": "Meta Llama 3.1 8B Instruct Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    }
   ],
   "intro": "Compact Llama instruction model for fast chat and local deployment",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3.1 8B Instruct Turbo"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-8b-instruct:free",
   "model_name": "llama-3.1-8b-instruct:free",
   "display_name": "Llama 3.1 8B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct:free"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.1-8B-Instruct"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0544"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0544"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "openrouter+helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.1-8B-Instruct"
    }
   ],
   "intro": "Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "benchmarks": {
    "intelligence_index": 7.6,
    "coding_index": 5.4,
    "agentic_index": 0.5
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-3.1-8B-Instruct",
    "meta-llama/llama-3.1-8b-instruct",
    "meta-llama/llama-3.1-8b-instruct:free"
   ],
   "intro_i18n": {
    "zh-CN": "Meta 最新的 Llama 3.1 系列，8B 指令微调版本，速度快、效率高。在行业评估中表现优异，超越众多领先闭源模型。（仅对企业认证用户开放）",
    "zh-TW": "Meta 最新的 Llama 3.1 系列，8B 指令微調版本，速度快且效率高。在業界評估中表現優異，超越多數封閉模型。（僅限企業驗證用戶使用）",
    "ja-JP": "Metaの最新Llama 3.1シリーズの8B命令調整バージョンで、特に高速かつ効率的です。業界評価において、多くの主要なクローズドモデルを上回る性能を発揮します。（企業認証済みの組織のみ利用可能）",
    "ru-RU": "Последняя серия Meta Llama 3.1, вариант с 8 миллиардами параметров, обученный на инструкциях, особенно быстр и эффективен. В отраслевых оценках демонстрирует отличные результаты, превосходя многие ведущие закрытые модели. (Доступна только для проверенных корпоративных клиентов.)"
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 8B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-lumimaid-70b",
   "model_name": "llama-3.1-lumimaid-70b",
   "display_name": "llama-3.1-lumimaid-70b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "neversleep/llama-3.1-lumimaid-70b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "neversleep/llama-3.1-lumimaid-70b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.1-lumimaid-70b"
    }
   ]
  },
  {
   "slug": "meta/llama-3.1-lumimaid-8b",
   "model_name": "llama-3.1-lumimaid-8b",
   "display_name": "NeverSleep: Lumimaid v0.2 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "neversleep/llama-3.1-lumimaid-8b"
    }
   ],
   "capabilities": {},
   "released_at": "2024-09-15",
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "neversleep/llama-3.1-lumimaid-8b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NeverSleep: Lumimaid v0.2 8B"
    }
   ]
  },
  {
   "slug": "meta/Llama-3.1-Tulu-3-405B",
   "model_name": "Llama-3.1-Tulu-3-405B",
   "display_name": "Llama 3.1 Tulu 3 405B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "sambanova",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    }
   ],
   "max_input_tokens": 16000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 Tulu 3 405B"
    }
   ]
  },
  {
   "slug": "meta/llama-3.2-11b",
   "model_name": "llama-3.2-11b",
   "display_name": "Llama 3.2 11B Vision Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "meta/llama-3.2-11b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "meta/llama-3.2-11b"
    }
   ],
   "intro": "Open Llama multimodal model for image understanding and text reasoning",
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-3.2-11b"
   ],
   "intro_i18n": {
    "zh-CN": "一款指令微调的图像推理模型（文本+图像输入，文本输出），专为视觉识别、图像推理、图像描述和通用图像问答优化。",
    "zh-TW": "一款經指令微調的圖像推理模型（文字+圖像輸入，文字輸出），針對視覺辨識、圖像推理、圖說生成與一般圖像問答進行最佳化。",
    "ja-JP": "視覚認識、画像推論、キャプション生成、一般的な画像 QA に最適化された命令調整型の画像推論モデル（テキスト＋画像入力、テキスト出力）。",
    "ru-RU": "Модель с настройкой под инструкции для визуального рассуждения (ввод: текст+изображение, вывод: текст), оптимизированная для визуального распознавания, рассуждения, описания и общего визуального QA."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 11B Vision Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3.2-11b-instruct",
   "model_name": "llama-3.2-11b-instruct",
   "display_name": "Llama 3.2 11B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     }
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-09-25",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 11B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3.2-11b-text-preview",
   "model_name": "llama-3.2-11b-text-preview",
   "display_name": "llama-3.2-11b-text-preview",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.2-11b-text-preview"
    }
   ]
  },
  {
   "slug": "meta/llama-3.2-11b-vision-preview",
   "model_name": "llama-3.2-11b-vision-preview",
   "display_name": "Llama 3.2 11B Vision (Preview)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    }
   ],
   "capabilities": {
    "vision": true
   },
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Llama 3.2 专为视觉与文本结合任务设计，擅长图像描述与视觉问答，连接语言生成与视觉推理。",
    "zh-TW": "Llama 3.2 專為結合視覺與文字任務設計，擅長圖像描述與視覺問答，實現語言生成與視覺推理的橋接。",
    "ja-JP": "Llama 3.2 は視覚と言語を組み合わせたタスク向けに設計されており、画像キャプション生成や視覚的Q&Aに優れ、言語生成と視覚推論の橋渡しをします。",
    "ru-RU": "Llama 3.2 разработана для задач, сочетающих зрение и текст, превосходно справляется с описанием изображений и визуальными вопросами-ответами, объединяя генерацию языка и визуальное мышление."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 11B Vision (Preview)"
    }
   ]
  },
  {
   "slug": "meta/llama-3.2-1b-preview",
   "model_name": "llama-3.2-1b-preview",
   "display_name": "llama-3.2-1b-preview",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.2-1b-preview"
    }
   ]
  },
  {
   "slug": "meta/Llama-3.2-3B-Instruct-Turbo",
   "model_name": "Llama-3.2-3B-Instruct-Turbo",
   "display_name": "Llama-3.2-3B-Instruct-Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.2-3B-Instruct-Turbo"
    }
   ],
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-3.2-3B-Instruct-Turbo"
   ],
   "intro_i18n": {
    "zh-CN": "LLaMA 3.2 专为视觉与文本结合任务设计，擅长图像描述与视觉问答，连接语言生成与视觉推理。",
    "zh-TW": "LLaMA 3.2 專為結合視覺與文字的任務設計，擅長圖像描述與視覺問答，連結語言生成與視覺推理。",
    "ja-JP": "LLaMA 3.2は視覚とテキストを組み合わせたタスク向けに設計されており、画像キャプションや視覚的QAに優れ、言語生成と視覚推論を橋渡しします。",
    "ru-RU": "LLaMA 3.2 разработана для задач, сочетающих изображение и текст. Отлично справляется с описанием изображений и визуальными вопросами, объединяя генерацию текста и визуальное мышление."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.2-3B-Instruct-Turbo"
    }
   ]
  },
  {
   "slug": "meta/llama-3.2-3b-preview",
   "model_name": "llama-3.2-3b-preview",
   "display_name": "llama-3.2-3b-preview",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.2-3b-preview"
    }
   ]
  },
  {
   "slug": "meta/llama-3.2-90b",
   "model_name": "llama-3.2-90b",
   "display_name": "Llama 3.2 90B Vision Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta/llama-3.2-90b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta/llama-3.2-90b"
    }
   ],
   "intro": "Open Llama multimodal model for image understanding and text reasoning",
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-3.2-90b"
   ],
   "intro_i18n": {
    "zh-CN": "一款指令微调的图像推理模型（文本+图像输入，文本输出），专为视觉识别、图像推理、图像描述和通用图像问答优化。",
    "zh-TW": "一款經指令微調的圖像推理模型（文字+圖像輸入，文字輸出），針對視覺辨識、圖像推理、圖說生成與一般圖像問答進行最佳化。",
    "ja-JP": "視覚認識、画像推論、キャプション生成、一般的な画像 QA に最適化された命令調整型の画像推論モデル（テキスト＋画像入力、テキスト出力）。",
    "ru-RU": "Модель с настройкой под инструкции для визуального рассуждения (ввод: текст+изображение, вывод: текст), оптимизированная для визуального распознавания, рассуждения, описания и общего визуального QA."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 90B Vision Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-3.2-90b-text-preview",
   "model_name": "llama-3.2-90b-text-preview",
   "display_name": "llama-3.2-90b-text-preview",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.2-90b-text-preview"
    }
   ]
  },
  {
   "slug": "meta/llama-3.2-90b-vision-instruct-maas",
   "model_name": "llama-3.2-90b-vision-instruct-maas",
   "display_name": "llama-3.2-90b-vision-instruct-maas",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas",
   "max_input_tokens": 128000,
   "max_output_tokens": 2048,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.2-90b-vision-instruct-maas"
    }
   ]
  },
  {
   "slug": "meta/llama-3.2-90b-vision-preview",
   "model_name": "llama-3.2-90b-vision-preview",
   "display_name": "Llama 3.2 90B Vision (Preview)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     }
    }
   ],
   "capabilities": {
    "vision": true
   },
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Llama 3.2 专为视觉与文本结合任务设计，擅长图像描述与视觉问答，连接语言生成与视觉推理。",
    "zh-TW": "Llama 3.2 專為結合視覺與文字任務設計，擅長圖像描述與視覺問答，實現語言生成與視覺推理的橋接。",
    "ja-JP": "Llama 3.2 は視覚と言語を組み合わせたタスク向けに設計されており、画像キャプション生成や視覚的Q&Aに優れ、言語生成と視覚推論の橋渡しをします。",
    "ru-RU": "Llama 3.2 разработана для задач, сочетающих зрение и текст, превосходно справляется с описанием изображений и визуальными вопросами-ответами, объединяя генерацию языка и визуальное мышление."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 90B Vision (Preview)"
    }
   ]
  },
  {
   "slug": "meta/llama-3.3",
   "model_name": "llama-3.3",
   "display_name": "llama-3.3",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.02747555"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.02747555"
      }
     },
     "provider_model_id": "meta/llama-3.3"
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-3.3"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.029336732",
     "new": "1.02747555"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.029336732",
     "new": "1.02747555"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.028939373",
     "new": "1.029336732"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.028939373",
     "new": "1.029336732"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.029727287",
     "new": "1.028939373"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.029727287",
     "new": "1.028939373"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.029312756",
     "new": "1.029727287"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.029312756",
     "new": "1.029727287"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.029598083",
     "new": "1.029312756"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.029598083",
     "new": "1.029312756"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "1.0242873",
     "new": "1.029598083"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.0242873",
     "new": "1.029598083"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.3"
    }
   ]
  },
  {
   "slug": "meta/llama-3.3-70b-cs",
   "model_name": "llama-3.3-70b-cs",
   "display_name": "llama-3.3-70b-cs",
   "vendor": "meta",
   "pricing": [],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-05-13",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cerebras/llama-3.3-70b-cs"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.3-70b-cs"
    }
   ]
  },
  {
   "slug": "meta/llama-3.3-70b-instruct",
   "model_name": "llama-3.3-70b-instruct",
   "display_name": "Llama-3.3-70B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "llama",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "Llama-3.3-70B-Instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "Llama-3.3-70B-Instruct"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     }
    },
    {
     "provider": "berget",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.99"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "cloudferro-sherlock",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.92"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.92"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.089"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.023"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Llama-3.3-70B-Instruct"
    },
    {
     "provider": "friendli",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.3-70b-instruct"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Llama-3.3-70B-Instruct"
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "llama-3-3-70b-instruct"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.065"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     },
     "provider_model_id": "meta-llama/llama-3.3-70b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     },
     "provider_model_id": "meta-llama/llama-3.3-70b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "meta-llama/llama-3.3-70b-instruct"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+litellm+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.013"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.135"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "meta-llama/llama-3.3-70b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.135"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "meta-llama/llama-3.3-70b-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.3-70b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     },
     "provider_model_id": "meta-llama/llama-3.3-70b-instruct"
    },
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.7"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "hf:meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.04"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "meta/llama-3.3-70b-instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://nebius.com/prices-ai-studio",
   "model_type": "text_generation",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 9.4,
    "coding_index": 11.9,
    "agentic_index": 0.3
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Llama-3.3-70B-Instruct",
    "deepinfra/meta-llama/Llama-3.3-70B-Instruct",
    "hf:meta-llama/Llama-3.3-70B-Instruct",
    "llama-3-3-70b-instruct",
    "llama-3.3-70b-instruct:free",
    "meta-llama/Llama-3.3-70B-Instruct",
    "meta-llama/llama-3.3-70b-instruct",
    "meta-llama/llama-3.3-70b-instruct:free",
    "meta/llama-3.3-70b-instruct",
    "nebius/meta-llama/Llama-3.3-70B-Instruct",
    "novita/meta-llama/llama-3.3-70b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.3 是最先进的多语言开源 Llama 模型，以极低成本实现接近 405B 的性能。基于 Transformer 架构，结合 SFT 与 RLHF 提升实用性与安全性。指令微调版本针对多语言对话优化，在行业基准测试中超越众多开源与闭源模型。知识截止时间：2023 年 12 月。",
    "zh-TW": "Llama 3.3 是最先進的多語言開源 Llama 模型，以極低成本提供接近 405B 的效能。基於 Transformer 架構，並透過 SFT 與 RLHF 提升實用性與安全性。指令微調版本針對多語言對話進行優化，在業界基準測試中超越多數開源與封閉模型。知識截止時間：2023 年 12 月。",
    "ja-JP": "Llama 3.3は最も高度な多言語対応のオープンソースLlamaモデルで、非常に低コストで405Bに近い性能を提供します。Transformerベースで、SFTとRLHFにより有用性と安全性が向上。命令調整版は多言語チャットに最適化され、業界ベンチマークで多くのオープン・クローズドチャットモデルを上回ります。知識カットオフ：2023年12月。",
    "ru-RU": "Llama 3.3 — самая продвинутая многоязычная модель Llama с открытым исходным кодом, обеспечивающая производительность, близкую к 405B, при очень низкой стоимости. Основана на архитектуре Transformer и улучшена с помощью SFT и RLHF для повышения полезности и безопасности. Вариант, настроенный на инструкции, оптимизирован для многоязычного чата и превосходит многие открытые и закрытые модели в отраслевых бенчмарках. Дата отсечения знаний: декабрь 2023."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "meta/Llama-3.3-70B-Instruct-abliterated",
   "model_name": "Llama-3.3-70B-Instruct-abliterated",
   "display_name": "Llama 3.3 70B Instruct abliterated",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "huihui-ai/Llama-3.3-70B-Instruct-abliterated"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-08-08",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "huihui-ai/Llama-3.3-70B-Instruct-abliterated"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 70B Instruct abliterated"
    }
   ]
  },
  {
   "slug": "meta/Llama-3.3-70B-Instruct-fast",
   "model_name": "Llama-3.3-70B-Instruct-fast",
   "display_name": "Llama-3.3-70B-Instruct (Fast)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct-fast"
    }
   ],
   "released_at": "2025-12-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-3.3-70B-Instruct-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.3-70B-Instruct (Fast)"
    }
   ]
  },
  {
   "slug": "meta/Llama-3.3-70B-Instruct-FP8-Dynamic",
   "model_name": "Llama-3.3-70B-Instruct-FP8-Dynamic",
   "display_name": "Llama 3.3 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "stackit",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.76"
      }
     },
     "provider_model_id": "cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "limit",
     "old": "8192",
     "new": "4096",
     "note": "max_output_tokens"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "stackit",
     "charge": "completion",
     "old": "0.71",
     "new": "0.76"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "stackit",
     "charge": "prompt",
     "old": "0.49",
     "new": "0.53"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 70B"
    }
   ]
  },
  {
   "slug": "meta/Llama-3.3-70B-Instruct-FP8-Lora",
   "model_name": "Llama-3.3-70B-Instruct-FP8-Lora",
   "display_name": "Llama-3.3-70B-Instruct-FP8-Lora",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct-FP8-Lora"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-3.3-70B-Instruct-FP8-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.3-70B-Instruct-FP8-Lora"
    }
   ]
  },
  {
   "slug": "meta/llama-3.3-70b-instruct-maas",
   "model_name": "llama-3.3-70b-instruct-maas",
   "display_name": "Llama 3.3 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta/llama-3.3-70b-instruct-maas",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta/llama-3.3-70b-instruct-maas",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-04-29",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-3.3-70b-instruct-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/Llama-3.3-70B-Instruct-Turbo-test",
   "model_name": "Llama-3.3-70B-Instruct-Turbo-test",
   "display_name": "Llama-3.3-70B-Instruct-Turbo-test",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.3-70B-Instruct-Turbo-test"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-3.3-70B-Instruct-Turbo-test"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.3-70B-Instruct-Turbo-test"
    }
   ]
  },
  {
   "slug": "meta/llama-3.3-70b-specdec",
   "model_name": "llama-3.3-70b-specdec",
   "display_name": "llama-3.3-70b-specdec",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.99"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.3-70b-specdec"
    }
   ]
  },
  {
   "slug": "meta/llama-3.3-70b-versatile",
   "model_name": "llama-3.3-70b-versatile",
   "display_name": "Llama 3.3 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "provider_model_id": "meta-llama/llama-3.3-70b-versatile"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7899999999999999"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "provider_model_id": "groq/llama-3.3-70b-versatile"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "groq/llama-3.3-70b-versatile",
    "meta-llama/llama-3.3-70b-versatile"
   ],
   "intro_i18n": {
    "zh-CN": "Meta Llama 3.3 是一款多语言大语言模型，拥有 70B 参数（文本输入/输出），提供预训练与指令微调版本。指令微调的文本模型专为多语言对话场景优化，在多个行业基准测试中超越众多开源与闭源聊天模型。",
    "zh-TW": "Meta Llama 3.3 是一款多語言大型語言模型，擁有 700 億參數（文字輸入/輸出），提供預訓練與指令微調版本。文字專用指令微調模型針對多語言對話進行最佳化，在多項業界基準測試中超越多數開放與封閉對話模型。",
    "ja-JP": "Meta Llama 3.3 は、70Bパラメータを持つ多言語対応LLMで、事前学習版とインストラクションチューニング版を提供します。テキスト専用のインストラクションチューニングモデルは多言語対話に最適化されており、業界の一般的なベンチマークで多くのオープン・クローズドチャットモデルを上回ります。",
    "ru-RU": "Meta Llama 3.3 — многоязычная LLM с 70B параметров (ввод/вывод текста), доступна в вариантах предварительного обучения и настройки на инструкции. Вариант, настроенный на инструкции, оптимизирован для многоязычного диалога и превосходит многие открытые и закрытые модели чатов по отраслевым бенчмаркам."
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 70B"
    }
   ]
  },
  {
   "slug": "meta/llama-3.3-8b-instruct",
   "model_name": "llama-3.3-8b-instruct",
   "display_name": "Llama-3.3-8B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "llama",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation"
  },
  {
   "slug": "meta/Llama-3.3-Swallow-70B-Instruct-v0.4",
   "model_name": "Llama-3.3-Swallow-70B-Instruct-v0.4",
   "display_name": "Llama-3.3-Swallow-70B-Instruct-v0.4",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "max_input_tokens": 16000,
   "max_output_tokens": 3072,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.3-Swallow-70B-Instruct-v0.4"
    }
   ]
  },
  {
   "slug": "meta/llama-4-maverick",
   "model_name": "llama-4-maverick",
   "display_name": "Llama-4-Maverick-17B-128E-Instruct-FP8",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.124"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.603"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.151"
      }
     }
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "meta-llama/llama-4-maverick"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18000000000000002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "meta-llama/llama-4-maverick"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "meta-llama/llama-4-maverick"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-4-maverick"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "meta/llama-4-maverick"
    }
   ],
   "intro": "Open multimodal Llama model for strong reasoning and fast responses",
   "released_at": "2025-04-05",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "deprecated": true,
   "model_type": "vision_understanding",
   "benchmarks": {
    "intelligence_index": 14.3,
    "coding_index": 16.3,
    "agentic_index": 1.3
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/llama-4-maverick",
    "meta/llama-4-maverick"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 4 系列是原生多模态 AI 模型集，支持文本与多模态体验，采用 MoE 架构，实现领先的文本与图像理解。Llama 4 Maverick 是一款拥有 128 个专家的 170 亿参数模型，由 DeepInfra 提供服务。",
    "zh-TW": "Llama 4 系列為原生多模態 AI 模型，支援文字與多模態體驗，採用 MoE 架構以實現領先的文字與圖像理解。Llama 4 Maverick 為一款擁有 128 位專家的 17B 模型，由 DeepInfra 提供服務。",
    "ja-JP": "Llama 4 ファミリーは、MoE を活用してテキストと画像の理解をリードする、テキストおよびマルチモーダル体験をサポートするネイティブマルチモーダル AI モデル群です。Llama 4 Maverick は 128 のエキスパートを持つ 17B モデルで、DeepInfra により提供されます。",
    "ru-RU": "Семейство Llama 4 — это нативные мультимодальные модели ИИ, поддерживающие текст и мультимодальные взаимодействия, использующие MoE для передового понимания текста и изображений. Llama 4 Maverick — это модель с 17B параметрами и 128 экспертами, предоставляемая DeepInfra."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-4-Maverick-17B-128E-Instruct-FP8"
    }
   ]
  },
  {
   "slug": "meta/llama-4-maverick-17b",
   "model_name": "llama-4-maverick-17b",
   "display_name": "Llama 4 Maverick 17B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.274"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.894"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.137"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "parallel_function_calling": true
   },
   "family": "Llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 4 Maverick 17B"
    }
   ]
  },
  {
   "slug": "meta/Llama-4-Maverick-17B-128E",
   "model_name": "Llama-4-Maverick-17B-128E",
   "display_name": "Llama-4-Maverick-17B-128E",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Maverick-17B-128E"
    }
   ],
   "max_input_tokens": 1048576,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-4-Maverick-17B-128E"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-4-Maverick-17B-128E"
    }
   ]
  },
  {
   "slug": "meta/Llama-4-Maverick-17B-128E-Instruct",
   "model_name": "Llama-4-Maverick-17B-128E-Instruct",
   "display_name": "Llama 4 Maverick 17b 128e Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "llama-4-maverick-17b-128e-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-4-maverick-17b-128e-instruct"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.63"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    }
   ],
   "intro": "Open multimodal Llama model for strong reasoning and fast responses",
   "released_at": "2025-04-01",
   "knowledge_cutoff": "2024-02",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "docs_url": "https://cloud.sambanova.ai/plans/pricing",
   "parameters": {
    "supported": [
     "max_tokens",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "family": "llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llama-4-maverick-17b-128e-instruct",
    "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
    "meta-llama/llama-4-maverick-17b-128e-instruct",
    "meta/llama-4-maverick-17b-128e-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 4 Maverick 17b 128e Instruct"
    }
   ]
  },
  {
   "slug": "meta/Llama-4-Maverick-17B-128E-Instruct-FP4",
   "model_name": "Llama-4-Maverick-17B-128E-Instruct-FP4",
   "display_name": "Llama-4-Maverick-17B-128E-Instruct-FP4",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP4"
    }
   ],
   "max_input_tokens": 1048576,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-4-Maverick-17B-128E-Instruct-FP4"
    }
   ]
  },
  {
   "slug": "meta/llama-4-maverick-17b-128e-instruct-fp8",
   "model_name": "llama-4-maverick-17b-128e-instruct-fp8",
   "display_name": "Llama-4-Maverick-17B-128E-Instruct-FP8",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "llama",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Llama-4-Maverick-17B-128E-Instruct-FP8"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.41"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "Llama-4-Maverick-17B-128E-Instruct-FP8"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-4-maverick-17b-128e-instruct-fp8"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8"
    },
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "meta-llama/llama-4-maverick-17b-128e-instruct-fp8"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "Llama-4-Maverick-17B-128E-Instruct-FP8",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.111111",
        "completion": "1.411765"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Open multimodal Llama model for strong reasoning and fast responses",
   "released_at": "2025-04-05",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "docs_url": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "functions",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Llama-4-Maverick-17B-128E-Instruct-FP8",
    "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
    "hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
    "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
    "meta-llama/llama-4-maverick-17b-128e-instruct-fp8",
    "meta/llama-4-maverick-17b-128e-instruct-fp8",
    "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "meta/llama-4-maverick-17b-128e-instruct-maas",
   "model_name": "llama-4-maverick-17b-128e-instruct-maas",
   "display_name": "Llama 4 Maverick 17B 128E Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "meta/llama-4-maverick-17b-128e-instruct-maas",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "meta/llama-4-maverick-17b-128e-instruct-maas",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Open multimodal Llama model for strong reasoning and fast responses",
   "released_at": "2025-04-29",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 524288,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-4-maverick-17b-128e-instruct-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 4 Maverick 17B 128E Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-4-maverick-17b-16e-instruct-maas",
   "model_name": "llama-4-maverick-17b-16e-instruct-maas",
   "display_name": "llama-4-maverick-17b-16e-instruct-maas",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
   "max_input_tokens": 1000000,
   "max_output_tokens": 1000000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-4-maverick-17b-16e-instruct-maas"
    }
   ]
  },
  {
   "slug": "meta/llama-4-maverick-17b-instruct",
   "model_name": "llama-4-maverick-17b-instruct",
   "display_name": "Llama 4 Maverick 17B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     }
    }
   ],
   "intro": "Open multimodal Llama model for strong reasoning and fast responses",
   "released_at": "2025-04-05",
   "max_input_tokens": 1048576,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 4 Maverick 17B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-4-scout",
   "model_name": "llama-4-scout",
   "display_name": "Llama-4-Scout-17B-16E-Instruct-FP8",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "meta-llama/llama-4-scout"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.085"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.46"
      }
     },
     "provider_model_id": "meta-llama/llama-4-scout"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "meta-llama/llama-4-scout"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-4-scout"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "meta/llama-4-scout"
    }
   ],
   "intro": "Open multimodal Llama model for long-context analysis and efficient agents",
   "released_at": "2025-04-05",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "deprecated": true,
   "model_type": "vision_understanding",
   "benchmarks": {
    "intelligence_index": 10,
    "coding_index": 8.2,
    "agentic_index": 1.1
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/llama-4-scout",
    "meta/llama-4-scout"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 4 系列是原生多模态 AI 模型集，支持文本与多模态体验，采用 MoE 架构，实现领先的文本与图像理解。Llama 4 Scout 是一款拥有 16 个专家的 170 亿参数模型，由 DeepInfra 提供服务。",
    "zh-TW": "Llama 4 系列為原生多模態 AI 模型，支援文字與多模態體驗，採用 MoE 架構以實現領先的文字與圖像理解。Llama 4 Scout 為一款擁有 16 位專家的 17B 模型，由 DeepInfra 提供服務。",
    "ja-JP": "Llama 4 ファミリーは、MoE を活用してテキストと画像の理解をリードする、テキストおよびマルチモーダル体験をサポートするネイティブマルチモーダル AI モデル群です。Llama 4 Scout は 16 のエキスパートを持つ 17B モデルで、DeepInfra により提供されます。",
    "ru-RU": "Семейство Llama 4 — это нативные мультимодальные модели ИИ, поддерживающие текст и мультимодальные взаимодействия, использующие MoE для передового понимания текста и изображений. Llama 4 Scout — это модель с 17B параметрами и 16 экспертами, предоставляемая DeepInfra."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-4-Scout-17B-16E-Instruct-FP8"
    }
   ]
  },
  {
   "slug": "meta/llama-4-scout-17b-128e-instruct-maas",
   "model_name": "llama-4-scout-17b-128e-instruct-maas",
   "display_name": "llama-4-scout-17b-128e-instruct-maas",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
   "max_input_tokens": 10000000,
   "max_output_tokens": 10000000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-4-scout-17b-128e-instruct-maas"
    }
   ]
  },
  {
   "slug": "meta/Llama-4-Scout-17B-16E-Instruct",
   "model_name": "Llama-4-Scout-17B-16E-Instruct",
   "display_name": "Llama 4 Scout Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "provider_model_id": "llama-4-scout-17b-16e-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "provider_model_id": "llama-4-scout-17b-16e-instruct"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "@cf/meta/llama-4-scout-17b-16e-instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "meta-llama/llama-4-scout-17b-16e-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-4-scout-17b-16e-instruct"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "meta-llama/llama-4-scout-17b-16e-instruct",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "meta-llama/llama-4-scout-17b-16e-instruct"
    },
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "llama-4-scout-17b-16e-instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "llama-4-scout-17b-16e-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "meta-llama/llama-4-scout-17b-16e-instruct"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "hf:meta-llama/Llama-4-Scout-17B-16E-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "meta/llama-4-scout-17b-16e-instruct"
    }
   ],
   "intro": "Open multimodal Llama model for long-context analysis and efficient agents",
   "released_at": "2025-04-06",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-08",
   "family": "llama",
   "status": "beta",
   "model_type": "vision_understanding",
   "docs_url": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/",
   "deprecated": true,
   "deprecation_date": "2025-06-19",
   "parameters": {
    "supported": [
     "max_tokens",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-4-scout-17b-16e-instruct",
    "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct",
    "groq/meta-llama/llama-4-scout-17b-16e-instruct",
    "hf:meta-llama/Llama-4-Scout-17B-16E-Instruct",
    "llama-4-scout-17b-16e-instruct",
    "meta-llama/Llama-4-Scout-17B-16E-Instruct",
    "meta-llama/llama-4-scout-17b-16e-instruct",
    "meta/llama-4-scout-17b-16e-instruct",
    "workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 4 Scout Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-4-scout-17b-16e-instruct-fp8",
   "model_name": "llama-4-scout-17b-16e-instruct-fp8",
   "display_name": "Llama-4-Scout-17B-16E-Instruct-FP8",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "llama",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open multimodal Llama model for long-context analysis and efficient agents",
   "released_at": "2025-04-05",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding"
  },
  {
   "slug": "meta/Llama-4-Scout-17B-16E-Instruct-FP8-Lora",
   "model_name": "Llama-4-Scout-17B-16E-Instruct-FP8-Lora",
   "display_name": "Llama-4-Scout-17B-16E-Instruct-FP8-Lora",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct-FP8-Lora"
    }
   ],
   "max_input_tokens": 10485760,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Llama-4-Scout-17B-16E-Instruct-FP8-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-4-Scout-17B-16E-Instruct-FP8-Lora"
    }
   ]
  },
  {
   "slug": "meta/llama-4-scout-17b-16e-instruct-maas",
   "model_name": "llama-4-scout-17b-16e-instruct-maas",
   "display_name": "llama-4-scout-17b-16e-instruct-maas",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "meta/llama-4-scout-17b-16e-instruct-maas",
     "region": "us-east5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
   "max_input_tokens": 10000000,
   "max_output_tokens": 10000000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "code"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama-4-scout-17b-16e-instruct-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "structured_output: true→false"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-4-scout-17b-16e-instruct-maas"
    }
   ]
  },
  {
   "slug": "meta/llama-4-scout-17b-instruct",
   "model_name": "llama-4-scout-17b-instruct",
   "display_name": "Llama 4 Scout 17B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     }
    }
   ],
   "intro": "Open multimodal Llama model for long-context analysis and efficient agents",
   "released_at": "2025-04-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 4 Scout 17B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-guard-2-8b",
   "model_name": "llama-guard-2-8b",
   "display_name": "Meta: LlamaGuard 2 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-guard-2-8b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "meta-llama/llama-guard-2-8b"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "safety_detection",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-05-13",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-guard-2-8b",
    "meta-llama/llama-guard-2-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta: LlamaGuard 2 8B"
    }
   ]
  },
  {
   "slug": "meta/llama-guard-3-11b-vision",
   "model_name": "llama-guard-3-11b-vision",
   "display_name": "llama-guard-3-11b-vision",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "safety_detection",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-guard-3-11b-vision"
    }
   ]
  },
  {
   "slug": "meta/llama-guard-3-1b",
   "model_name": "llama-guard-3-1b",
   "display_name": "Llama Guard v3 1B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-guard-3-1b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "safety_detection",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-guard-3-1b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama Guard v3 1B"
    }
   ]
  },
  {
   "slug": "meta/Llama-Guard-3-8B",
   "model_name": "Llama-Guard-3-8B",
   "display_name": "Llama Guard 3 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-guard-3-8b"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.484"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "@cf/meta/llama-guard-3-8b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.055"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.055"
      }
     },
     "provider_model_id": "meta-llama/Llama-Guard-3-8B"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "llama-guard-3-8b"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "llama-guard-3-8b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "meta-llama/llama-guard-3-8b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.002"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "meta-llama/Llama-Guard-3-8B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "meta-llama/llama-guard-3-8b"
    }
   ],
   "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows",
   "released_at": "2025-01-22",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "model_type": "safety_detection",
   "docs_url": "https://nebius.com/prices-ai-studio",
   "deprecated": true,
   "knowledge_cutoff": "2024-04",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-guard-3-8b",
    "accounts/fireworks/models/llama-guard-3-8b",
    "llama-guard-3-8b",
    "meta-llama/Llama-Guard-3-8B",
    "meta-llama/llama-guard-3-8b",
    "workers-ai/@cf/meta/llama-guard-3-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama Guard 3 8B"
    }
   ]
  },
  {
   "slug": "meta/llama-guard-4",
   "model_name": "llama-guard-4",
   "display_name": "Meta Llama Guard 4 12B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21"
      }
     }
    }
   ],
   "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows",
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "safety_detection",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama Guard 4 12B"
    }
   ]
  },
  {
   "slug": "meta/Llama-Guard-4-12B",
   "model_name": "Llama-Guard-4-12B",
   "display_name": "Llama Guard 4 12B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "meta-llama/Llama-Guard-4-12B"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "llama-guard-4-12b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "meta-llama/Llama-Guard-4-12B"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "meta-llama/llama-guard-4-12b"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-guard-4-12b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "meta-llama/llama-guard-4-12b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "meta-llama/Llama-Guard-4-12B"
    }
   ],
   "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows",
   "released_at": "2025-04-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2024-08",
   "model_type": "safety_detection",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llama-guard-4-12b",
    "meta-llama/Llama-Guard-4-12B",
    "meta-llama/llama-guard-4-12b",
    "meta-llama/llama-guard-4-12b:free",
    "meta/llama-guard-4-12b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama Guard 4 12B"
    }
   ]
  },
  {
   "slug": "meta/llama-prompt-guard-2-22m",
   "model_name": "llama-prompt-guard-2-22m",
   "display_name": "Llama Prompt Guard 2 22M",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+truefoundry+helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "meta-llama/llama-prompt-guard-2-22m"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    }
   ],
   "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows",
   "released_at": "2025-05-29",
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "status": "beta",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "knowledge_cutoff": "2024-10",
   "model_type": "safety_detection",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/llama-prompt-guard-2-22m"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama Prompt Guard 2 22M"
    }
   ]
  },
  {
   "slug": "meta/llama-prompt-guard-2-86m",
   "model_name": "llama-prompt-guard-2-86m",
   "display_name": "Prompt Guard 2 86M",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+truefoundry+helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "meta-llama/llama-prompt-guard-2-86m"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    }
   ],
   "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows",
   "released_at": "2025-05-29",
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "status": "beta",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2024-10",
   "model_type": "safety_detection",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/llama-prompt-guard-2-86m"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Prompt Guard 2 86M"
    }
   ]
  },
  {
   "slug": "meta/Llama-Rank-V1",
   "model_name": "Llama-Rank-V1",
   "display_name": "Salesforce Llama Rank V1 (8B)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "Salesforce/Llama-Rank-V1"
    }
   ],
   "released_at": "2024-08-15",
   "max_input_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Salesforce/Llama-Rank-V1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Salesforce Llama Rank V1 (8B)"
    }
   ]
  },
  {
   "slug": "meta/llama-v2-13b",
   "model_name": "llama-v2-13b",
   "display_name": "Llama 2 13B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v2-13b"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v2-13b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 2 13B"
    }
   ]
  },
  {
   "slug": "meta/llama-v2-13b-chat",
   "model_name": "llama-v2-13b-chat",
   "display_name": "Llama 2 13B Chat",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v2-13b-chat"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v2-13b-chat"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 2 13B Chat"
    }
   ]
  },
  {
   "slug": "meta/llama-v2-70b",
   "model_name": "llama-v2-70b",
   "display_name": "Llama 2 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v2-70b"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v2-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 2 70B"
    }
   ]
  },
  {
   "slug": "meta/llama-v2-70b-chat",
   "model_name": "llama-v2-70b-chat",
   "display_name": "llama-v2-70b-chat",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "max_input_tokens": 2048,
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-v2-70b-chat"
    }
   ]
  },
  {
   "slug": "meta/llama-v2-7b",
   "model_name": "llama-v2-7b",
   "display_name": "Llama 2 7B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v2-7b"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v2-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 2 7B"
    }
   ]
  },
  {
   "slug": "meta/llama-v2-7b-chat",
   "model_name": "llama-v2-7b-chat",
   "display_name": "Llama 2 7B Chat",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v2-7b-chat"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v2-7b-chat"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 2 7B Chat"
    }
   ]
  },
  {
   "slug": "meta/llama-v3-70b-instruct",
   "model_name": "llama-v3-70b-instruct",
   "display_name": "Llama 3 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3-70b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3-70b-instruct"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3-70b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Meta 开发并发布了 Meta Llama 3 大语言模型系列，包括 8B 和 70B 参数规模的预训练与指令微调文本生成模型。Llama 3 的指令微调模型专为对话场景优化，在多个行业通用基准测试中优于许多现有的开源聊天模型。",
    "zh-TW": "Meta 開發並發布了 Meta Llama 3 大型語言模型系列，涵蓋 8B 和 70B 參數的預訓練與指令微調文字生成模型。Llama 3 的指令微調模型專為對話應用優化，在多項業界常用基準測試中表現優於許多現有的開源聊天模型。",
    "ja-JP": "Metaは、8Bおよび70Bの事前学習済みおよび命令調整済みのテキスト生成モデルを含むMeta Llama 3 LLMシリーズを開発・公開しました。Llama 3の命令調整済みモデルは会話用途に最適化されており、業界標準のベンチマークにおいて多くの既存のオープンチャットモデルを上回る性能を発揮します。",
    "ru-RU": "Meta разработала и выпустила серию LLM Meta Llama 3, включающую предварительно обученные и дообученные на инструкциях модели генерации текста с объемом 8B и 70B параметров. Модели Llama 3, дообученные на инструкциях, оптимизированы для ведения диалогов и превосходят многие существующие открытые чат-модели по общепринятым отраслевым метрикам."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-v3-70b-instruct-hf",
   "model_name": "llama-v3-70b-instruct-hf",
   "display_name": "Llama 3 70B Instruct (HF version)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3-70b-instruct-hf"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3-70b-instruct-hf"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 70B Instruct (HF version)"
    }
   ]
  },
  {
   "slug": "meta/llama-v3-8b",
   "model_name": "llama-v3-8b",
   "display_name": "Llama 3 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3-8b"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 8B"
    }
   ]
  },
  {
   "slug": "meta/llama-v3-8b-instruct-hf",
   "model_name": "llama-v3-8b-instruct-hf",
   "display_name": "Llama 3 8B Instruct (HF version)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3-8b-instruct-hf"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3-8b-instruct-hf"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-03",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3-8b-instruct-hf"
   ],
   "intro_i18n": {
    "zh-CN": "Meta Llama 3 的指令微调模型专为对话场景优化，在多个行业通用基准测试中优于许多现有的开源聊天模型。Llama 3 8B Instruct（HF 版本）是 Llama 3 8B Instruct 的原始 FP16 版本，预期结果与 Hugging Face 官方实现一致。",
    "zh-TW": "Meta Llama 3 的指令微調模型專為對話應用優化，在多項業界常用基準測試中表現優異。Llama 3 8B Instruct（HF 版本）是 Llama 3 8B Instruct 的原始 FP16 版本，預期結果與 Hugging Face 官方實作一致。",
    "ja-JP": "Meta Llama 3の命令調整済みモデルは会話用途に最適化されており、業界標準のベンチマークにおいて多くの既存のオープンチャットモデルを上回る性能を発揮します。Llama 3 8B Instruct（HF版）は、Llama 3 8B Instructの元のFP16バージョンであり、Hugging Faceの公式実装と同等の結果が期待されます。",
    "ru-RU": "Модели Meta Llama 3, дообученные на инструкциях, оптимизированы для ведения диалогов и превосходят многие существующие открытые чат-модели по общепринятым отраслевым метрикам. Llama 3 8B Instruct (версия HF) — это оригинальная версия Llama 3 8B Instruct с точностью FP16, результаты которой соответствуют официальной реализации Hugging Face."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 8B Instruct (HF version)"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p1-405b-instruct",
   "model_name": "llama-v3p1-405b-instruct",
   "display_name": "Llama 3.1 405B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p1-405b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p1-405b-instruct"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p1-405b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Meta Llama 3.1 是一个多语言大语言模型系列，提供 8B、70B 和 405B 参数规模的预训练与指令微调生成模型。指令微调模型专为多语言对话优化，在多个行业通用基准测试中优于许多开源和闭源聊天模型。405B 是 Llama 3.1 系列中最强大的模型，采用 FP8 推理，性能接近参考实现。",
    "zh-TW": "Meta Llama 3.1 是一個多語言大型語言模型系列，提供 8B、70B 和 405B 參數的預訓練與指令微調生成模型。這些指令微調模型針對多語言對話進行優化，在多項業界常用基準測試中表現優於許多開源與封閉聊天模型。405B 是 Llama 3.1 系列中最強大的模型，採用 FP8 推論，與參考實作高度一致。",
    "ja-JP": "Meta Llama 3.1は、8B、70B、405Bのサイズで構成される多言語対応のLLMファミリーで、事前学習済みおよび命令調整済みの生成モデルを提供します。命令調整済みのテキストモデルは多言語対話に最適化されており、業界標準のベンチマークにおいて多くのオープンおよびクローズドチャットモデルを上回る性能を示します。405BモデルはLlama 3.1ファミリーの中で最も高性能であり、リファレンス実装に近いFP8推論を使用しています。",
    "ru-RU": "Meta Llama 3.1 — это многоязычное семейство LLM, включающее предварительно обученные и дообученные на инструкциях модели генерации текста с объемом 8B, 70B и 405B параметров. Модели, дообученные на инструкциях, оптимизированы для многоязычного диалога и превосходят многие существующие открытые и закрытые чат-модели по общепринятым отраслевым метрикам. Модель 405B — самая мощная в семействе Llama 3.1, использует вывод FP8, максимально приближенный к эталонной реализации."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 405B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p1-405b-instruct-long",
   "model_name": "llama-v3p1-405b-instruct-long",
   "display_name": "Llama 3.1 405B Instruct Long",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p1-405b-instruct-long"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p1-405b-instruct-long"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 405B Instruct Long"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p1-70b-instruct",
   "model_name": "llama-v3p1-70b-instruct",
   "display_name": "Llama 3.1 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p1-70b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p1-70b-instruct"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p1-70b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Meta Llama 3.1 是一个多语言大语言模型系列，提供 8B、70B 和 405B 参数规模的预训练与指令微调生成模型。指令微调模型专为多语言对话优化，在多个行业通用基准测试中优于许多开源和闭源聊天模型。",
    "zh-TW": "Meta Llama 3.1 是一個多語言大型語言模型系列，提供 8B、70B 和 405B 參數的預訓練與指令微調生成模型。這些指令微調模型針對多語言對話進行優化，在多項業界常用基準測試中表現優於許多開源與封閉聊天模型。",
    "ja-JP": "Meta Llama 3.1は、8B、70B、405Bのサイズで構成される多言語対応のLLMファミリーで、事前学習済みおよび命令調整済みの生成モデルを提供します。命令調整済みのテキストモデルは多言語対話に最適化されており、業界標準のベンチマークにおいて多くのオープンおよびクローズドチャットモデルを上回る性能を示します。",
    "ru-RU": "Meta Llama 3.1 — это многоязычное семейство LLM, включающее предварительно обученные и дообученные на инструкциях модели генерации текста с объемом 8B, 70B и 405B параметров. Модели, дообученные на инструкциях, оптимизированы для многоязычного диалога и превосходят многие существующие открытые и закрытые чат-модели по общепринятым отраслевым метрикам."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p1-70b-instruct-1b",
   "model_name": "llama-v3p1-70b-instruct-1b",
   "display_name": "Llama 3.1 70B Instruct 1B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p1-70b-instruct-1b"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p1-70b-instruct-1b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 70B Instruct 1B"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p1-8b-instruct",
   "model_name": "llama-v3p1-8b-instruct",
   "display_name": "Llama 3.1 8B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p1-8b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p1-8b-instruct"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "intro": "The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes. The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.",
   "knowledge_cutoff": "2023-12",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p1-8b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Meta Llama 3.1 是一个多语言大语言模型系列，提供 8B、70B 和 405B 参数规模的预训练与指令微调生成模型。指令微调模型专为多语言对话优化，在多个行业通用基准测试中优于许多开源和闭源聊天模型。",
    "zh-TW": "Meta Llama 3.1 是一個多語言大型語言模型系列，提供 8B、70B 和 405B 參數的預訓練與指令微調生成模型。這些指令微調模型針對多語言對話進行優化，在多項業界常用基準測試中表現優於許多開源與封閉聊天模型。",
    "ja-JP": "Meta Llama 3.1は、8B、70B、405Bのサイズで構成される多言語対応のLLMファミリーで、事前学習済みおよび命令調整済みの生成モデルを提供します。命令調整済みのテキストモデルは多言語対話に最適化されており、業界標準のベンチマークにおいて多くのオープンおよびクローズドチャットモデルを上回る性能を示します。",
    "ru-RU": "Meta Llama 3.1 — это многоязычное семейство LLM, включающее предварительно обученные и дообученные на инструкциях модели генерации текста с объемом 8B, 70B и 405B параметров. Модели, дообученные на инструкциях, оптимизированы для многоязычного диалога и превосходят многие существующие открытые и закрытые чат-модели по общепринятым отраслевым метрикам."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 8B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p2-11b-vision-instruct",
   "model_name": "llama-v3p2-11b-vision-instruct",
   "display_name": "Llama 3.2 11B Vision Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p2-11b-vision-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p2-11b-vision-instruct"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p2-11b-vision-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Meta 推出的一个拥有 110 亿参数的指令微调视觉推理模型，专为图像识别、图像推理、图像描述和图像相关问答优化。该模型能够理解图表等视觉数据，并通过生成图像细节的文本描述实现视觉与语言的融合。",
    "zh-TW": "Meta 推出的 11B 參數視覺推理模型，經指令微調，專為視覺辨識、圖像推理、圖說生成與圖像相關問答優化。能理解圖表等視覺資料，並透過文字描述圖像細節，實現視覺與語言的橋接。",
    "ja-JP": "Metaによる命令調整済みの視覚推論モデルで、11Bのパラメータを持ち、視覚認識、画像推論、キャプション生成、画像関連のQ&Aに最適化されています。グラフやチャートなどの視覚データを理解し、画像の詳細をテキストで記述することで視覚と言語の橋渡しを行います。",
    "ru-RU": "Дообученная на инструкциях модель визуального рассуждения от Meta с 11 миллиардами параметров, оптимизированная для распознавания изображений, логического анализа, генерации описаний и ответов на вопросы, связанные с изображениями. Понимает визуальные данные, такие как диаграммы и графики, и объединяет зрение и язык, создавая текстовые описания деталей изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 11B Vision Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p2-1b",
   "model_name": "llama-v3p2-1b",
   "display_name": "Llama 3.2 1B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p2-1b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p2-1b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 1B"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p2-1b-instruct",
   "model_name": "llama-v3p2-1b-instruct",
   "display_name": "Llama 3.2 1B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p2-1b-instruct"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p2-1b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 1B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p2-3b",
   "model_name": "llama-v3p2-3b",
   "display_name": "Llama 3.2 3B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p2-3b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p2-3b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 3B"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p2-3b-instruct",
   "model_name": "llama-v3p2-3b-instruct",
   "display_name": "Llama 3.2 3B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p2-3b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p2-3b-instruct"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p2-3b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.2 3B Instruct 是 Meta 推出的轻量级多语言模型，具备高效运行能力，在延迟和成本方面相较于大型模型具有显著优势。典型应用包括查询/提示重写和写作辅助。",
    "zh-TW": "Llama 3.2 3B Instruct 是 Meta 推出的輕量級多語言模型，具備高效執行效能，延遲與成本明顯優於大型模型。典型應用包括查詢/提示重寫與寫作輔助。",
    "ja-JP": "Llama 3.2 3B Instructは、Metaによる軽量な多言語モデルで、実行時の効率性を重視し、大規模モデルに比べて大幅なレイテンシとコストの利点を提供します。主な用途には、クエリやプロンプトの書き換え、ライティング支援などがあります。",
    "ru-RU": "Llama 3.2 3B Instruct — это легковесная многоязычная модель от Meta, разработанная для эффективной работы с низкой задержкой и сниженной стоимостью по сравнению с более крупными моделями. Типичные сценарии использования включают переформулировку запросов и помощь в написании текстов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 3B Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p2-90b-vision-instruct",
   "model_name": "llama-v3p2-90b-vision-instruct",
   "display_name": "Llama 3.2 90B Vision Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p2-90b-vision-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p2-90b-vision-instruct"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p2-90b-vision-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Meta 推出的一个拥有 900 亿参数的指令微调视觉推理模型，专为图像识别、图像推理、图像描述和图像相关问答优化。该模型能够理解图表等视觉数据，并通过生成图像细节的文本描述实现视觉与语言的融合。注意：该模型目前作为无服务器模型实验性提供，Fireworks 可能会在短时间内终止部署，生产环境使用请注意。",
    "zh-TW": "Meta 推出的 90B 參數視覺推理模型，經指令微調，專為視覺辨識、圖像推理、圖說生成與圖像相關問答優化。能理解圖表等視覺資料，並透過文字描述圖像細節，實現視覺與語言的橋接。注意：此模型目前以無伺服器方式實驗性提供，Fireworks 可能會在短時間內終止部署，請注意生產環境使用風險。",
    "ja-JP": "Metaによる命令調整済みの視覚推論モデルで、90Bのパラメータを持ち、視覚認識、画像推論、キャプション生成、画像関連のQ&Aに最適化されています。グラフやチャートなどの視覚データを理解し、画像の詳細をテキストで記述することで視覚と言語の橋渡しを行います。注：このモデルは現在、サーバーレスモデルとして実験的に提供されています。商用利用を検討する場合、Fireworksが予告なく提供を終了する可能性がある点にご注意ください。",
    "ru-RU": "Дообученная на инструкциях модель визуального рассуждения от Meta с 90 миллиардами параметров, оптимизированная для распознавания изображений, логического анализа, генерации описаний и ответов на вопросы, связанные с изображениями. Понимает визуальные данные, такие как диаграммы и графики, и объединяет зрение и язык, создавая текстовые описания деталей изображений. Примечание: эта модель предоставляется в экспериментальном режиме как серверлесс-решение. Для использования в продакшене учтите, что Fireworks может прекратить развертывание без предварительного уведомления."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 90B Vision Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama-v3p3-70b-instruct",
   "model_name": "llama-v3p3-70b-instruct",
   "display_name": "Llama 3.3 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p3-70b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p3-70b-instruct"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p3-70b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.3 70B Instruct 是 Llama 3.1 70B 的 12 月更新版本，在工具使用、多语言文本支持、数学和编程方面相较 2024 年 7 月版本有显著提升。该模型在推理、数学和指令遵循方面达到行业领先水平，性能接近 3.1 405B，同时具备更高的速度和成本优势。",
    "zh-TW": "Llama 3.3 70B Instruct 是 Llama 3.1 70B 的 12 月更新版本，提升了工具使用、多語言文字支援、數學與程式能力，優於 2024 年 7 月版本。在推理、數學與指令遵循方面達到業界領先表現，效能接近 3.1 405B，但具備顯著的速度與成本優勢。",
    "ja-JP": "Llama 3.3 70B Instructは、Llama 3.1 70Bの2024年12月版アップデートです。ツール使用、多言語テキスト対応、数学、コーディングの性能が2024年7月版より向上しています。推論、数学、命令追従において業界最高水準の性能を発揮し、3.1 405Bに匹敵する性能を、より高速かつ低コストで提供します。",
    "ru-RU": "Llama 3.3 70B Instruct — обновление декабря для модели Llama 3.1 70B. Улучшает использование инструментов, поддержку многоязычного текста, математику и программирование по сравнению с выпуском июля 2024 года. Обеспечивает лидирующую в отрасли производительность в рассуждении, математике и следовании инструкциям, предлагая сопоставимую с 3.1 405B производительность при значительном выигрыше в скорости и стоимости."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/Llama-xLAM-2-70b-fc-r",
   "model_name": "Llama-xLAM-2-70b-fc-r",
   "display_name": "Llama-xLAM-2 70B fc-r",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "Salesforce/Llama-xLAM-2-70b-fc-r"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-04-13",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Salesforce/Llama-xLAM-2-70b-fc-r"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-xLAM-2 70B fc-r"
    }
   ]
  },
  {
   "slug": "meta/llama2-70b-4096",
   "model_name": "llama2-70b-4096",
   "display_name": "llama2-70b-4096",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama2-70b-4096"
    }
   ]
  },
  {
   "slug": "meta/llama2-70b-40960",
   "model_name": "llama2-70b-40960",
   "display_name": "llama2-70b-40960",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama2-70b-40960"
    }
   ]
  },
  {
   "slug": "meta/llama2-7b-2048",
   "model_name": "llama2-7b-2048",
   "display_name": "llama2-7b-2048",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama2-7b-2048"
    }
   ]
  },
  {
   "slug": "meta/llama3-3",
   "model_name": "llama3-3",
   "display_name": "llama3-3",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta/llama3-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama3-3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3-3"
    }
   ]
  },
  {
   "slug": "meta/llama3-3-70b",
   "model_name": "llama3-3-70b",
   "display_name": "Llama-3.3-70B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "TEE/llama3-3-70b"
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "llama3.3-70b"
    },
    {
     "provider": "tinfoil",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     }
    }
   ],
   "intro": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting",
   "released_at": "2024-12-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TEE/llama3-3-70b",
    "llama3.3-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.3-70B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/llama3-405b-instruct-maas",
   "model_name": "llama3-405b-instruct-maas",
   "display_name": "llama3-405b-instruct-maas",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3-405b-instruct-maas"
    }
   ]
  },
  {
   "slug": "meta/llama3-70b-8192",
   "model_name": "llama3-70b-8192",
   "display_name": "Meta Llama 3 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9372881357"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     }
    }
   ],
   "capabilities": {
    "function_calling": true
   },
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Meta Llama 3 70B 在处理复杂任务方面表现卓越，适用于高要求项目。",
    "zh-TW": "Meta Llama 3 70B 具備卓越的複雜任務處理能力，適用於高需求專案。",
    "ja-JP": "Meta Llama 3 70B は、要求の厳しいプロジェクトに対応する卓越した複雑性処理能力を提供します。",
    "ru-RU": "Meta Llama 3 70B обеспечивает исключительную обработку сложных задач для требовательных проектов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3 70B"
    }
   ]
  },
  {
   "slug": "meta/llama3-70b-8192(33)",
   "model_name": "llama3-70b-8192(33)",
   "display_name": "llama3-70b-8192(33)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.65"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3-70b-8192(33)"
    }
   ]
  },
  {
   "slug": "meta/llama3-70b-instruct-maas",
   "model_name": "llama3-70b-instruct-maas",
   "display_name": "llama3-70b-instruct-maas",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3-70b-instruct-maas"
    }
   ]
  },
  {
   "slug": "meta/llama3-8b-8192",
   "model_name": "llama3-8b-8192",
   "display_name": "Meta Llama 3 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    }
   ],
   "capabilities": {
    "function_calling": true
   },
   "knowledge_cutoff": "2023-03",
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Meta Llama 3 8B 在多种场景中展现出强大的推理能力。",
    "zh-TW": "Meta Llama 3 8B 在多樣化場景中展現強大的推理能力。",
    "ja-JP": "Meta Llama 3 8B は、多様なシナリオにおいて強力な推論性能を発揮します。",
    "ru-RU": "Meta Llama 3 8B демонстрирует высокую логическую производительность в различных сценариях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3 8B"
    }
   ]
  },
  {
   "slug": "meta/llama3-8b-8192(33)",
   "model_name": "llama3-8b-8192(33)",
   "display_name": "llama3-8b-8192(33)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3-8b-8192(33)"
    }
   ]
  },
  {
   "slug": "meta/llama3-8B-chat",
   "model_name": "llama3-8B-chat",
   "display_name": "meta/llama3-8B-chat",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "meta/llama3-8B-chat"
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama3-8B-chat"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "meta/llama3-8B-chat"
    }
   ]
  },
  {
   "slug": "meta/llama3-8b-instruct",
   "model_name": "llama3-8b-instruct",
   "display_name": "Llama 3.1 Instruct (8B)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta.llama3-8b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.555556",
        "completion": "0.416667"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta.llama3-8b-instruct-v1:0",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.69"
      }
     },
     "provider_model_id": "meta.llama3-8b-instruct-v1:0",
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "provider_model_id": "meta.llama3-8b-instruct-v1:0",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "meta.llama3-8b-instruct-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "meta.llama3-8b-instruct-v1:0",
     "region": "us-gov-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "meta.llama3-8b-instruct-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "meta.llama3-8b-instruct-v1:0"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.198"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.198"
      }
     }
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta.llama3-8b-instruct-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "Meta Llama 3 是一款面向开发者、研究人员和企业的开放式大语言模型，旨在帮助他们构建、实验并负责任地扩展生成式 AI 创意。作为全球社区创新的基础之一，它特别适用于计算资源有限的场景、边缘设备以及更快的训练周期。",
    "zh-TW": "Meta Llama 3 是一款開放式 LLM，專為開發者、研究人員與企業設計，協助他們構建、實驗並負責任地擴展生成式 AI 應用。適合運算資源有限的場景、邊緣設備與快速訓練需求。",
    "ja-JP": "Meta Llama 3は、開発者、研究者、企業向けのオープンLLMであり、生成AIのアイデアを構築・実験・拡張するための基盤です。限られた計算資源やエッジデバイス、短時間のトレーニングに適しており、効率的な運用が可能です。",
    "ru-RU": "Meta Llama 3 — это открытая LLM для разработчиков, исследователей и предприятий, созданная для поддержки создания, экспериментов и ответственного масштабирования идей генеративного ИИ. Являясь частью основы для глобальных инноваций сообщества, она хорошо подходит для ограниченных вычислительных ресурсов, устройств на периферии и ускоренного обучения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 Instruct (8B)"
    }
   ]
  },
  {
   "slug": "meta/llama3-8b-instruct-maas",
   "model_name": "llama3-8b-instruct-maas",
   "display_name": "llama3-8b-instruct-maas",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3-8b-instruct-maas"
    }
   ]
  },
  {
   "slug": "meta/llama3-groq-70b-8192-tool-use-preview",
   "model_name": "llama3-groq-70b-8192-tool-use-preview",
   "display_name": "Llama 3 Groq 70B Tool Use (Preview)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.00089"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.00089"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.89"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.89"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.89"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.89"
      }
     }
    }
   ],
   "capabilities": {
    "function_calling": true
   },
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Llama 3 Groq 70B Tool Use 提供强大的工具调用能力，能高效处理复杂任务。",
    "zh-TW": "Llama 3 Groq 70B Tool Use 提供強大的工具調用能力，能高效處理複雜任務。",
    "ja-JP": "Llama 3 Groq 70B Tool Use は、複雑なタスクを効率的に処理するための強力なツール呼び出し機能を提供します。",
    "ru-RU": "Llama 3 Groq 70B Tool Use обеспечивает мощный вызов инструментов для эффективной обработки сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 Groq 70B Tool Use (Preview)"
    }
   ]
  },
  {
   "slug": "meta/llama3-groq-8b-8192-tool-use-preview",
   "model_name": "llama3-groq-8b-8192-tool-use-preview",
   "display_name": "Llama 3 Groq 8B Tool Use (Preview)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.00019"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.00019"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    }
   ],
   "capabilities": {
    "function_calling": true
   },
   "max_input_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Llama 3 Groq 8B Tool Use 针对高效工具使用进行了优化，支持快速并行计算。",
    "zh-TW": "Llama 3 Groq 8B Tool Use 針對高效工具使用進行最佳化，支援快速並行運算。",
    "ja-JP": "Llama 3 Groq 8B Tool Use は、高速な並列計算による効率的なツール使用に最適化されています。",
    "ru-RU": "Llama 3 Groq 8B Tool Use оптимизирована для эффективного использования инструментов с быстрой параллельной обработкой."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 Groq 8B Tool Use (Preview)"
    }
   ]
  },
  {
   "slug": "meta/llama3.1-405b",
   "model_name": "llama3.1-405b",
   "display_name": "llama3.1-405b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.1-405b"
    }
   ]
  },
  {
   "slug": "meta/llama3.1-405b-instruct-fp8",
   "model_name": "llama3.1-405b-instruct-fp8",
   "display_name": "llama3.1-405b-instruct-fp8",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.1-405b-instruct-fp8"
    }
   ]
  },
  {
   "slug": "meta/llama3.1-70b",
   "model_name": "llama3.1-70b",
   "display_name": "llama3.1-70b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "cerebras",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.1-70b"
    }
   ]
  },
  {
   "slug": "meta/llama3.1-70b-instruct-fp8",
   "model_name": "llama3.1-70b-instruct-fp8",
   "display_name": "llama3.1-70b-instruct-fp8",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.1-70b-instruct-fp8"
    }
   ]
  },
  {
   "slug": "meta/llama3.1-8b",
   "model_name": "llama3.1-8b",
   "display_name": "Llama 3.1 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "cerebras",
     "official": false,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "parallel_function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2023-12",
   "family": "llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 8B"
    }
   ]
  },
  {
   "slug": "meta/llama3.1-typhoon2-70b-instruct",
   "model_name": "llama3.1-typhoon2-70b-instruct",
   "display_name": "llama3.1-typhoon2-70b-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "scb10x/llama3.1-typhoon2-70b-instruct"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "scb10x/llama3.1-typhoon2-70b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.1-typhoon2-70b-instruct"
    }
   ]
  },
  {
   "slug": "meta/llama3.1-typhoon2-8b-instruct",
   "model_name": "llama3.1-typhoon2-8b-instruct",
   "display_name": "llama3.1-typhoon2-8b-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "scb10x/llama3.1-typhoon2-8b-instruct"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "scb10x/llama3.1-typhoon2-8b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.1-typhoon2-8b-instruct"
    }
   ]
  },
  {
   "slug": "meta/llama3.2-11b-vision-instruct",
   "model_name": "llama3.2-11b-vision-instruct",
   "display_name": "llama3.2-11b-vision-instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.2-11b-vision-instruct"
    }
   ]
  },
  {
   "slug": "meta/llama3.3-70b-instruct-fp8",
   "model_name": "llama3.3-70b-instruct-fp8",
   "display_name": "llama3.3-70b-instruct-fp8",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.3-70b-instruct-fp8"
    }
   ]
  },
  {
   "slug": "meta/llama4",
   "model_name": "llama4",
   "display_name": "llama4",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "meta/llama4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 524288,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta/llama4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama4"
    }
   ]
  },
  {
   "slug": "meta/llama4-maverick",
   "model_name": "llama4-maverick",
   "display_name": "llama4-maverick",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama4-maverick"
    }
   ]
  },
  {
   "slug": "meta/llama4-maverick-instruct-basic",
   "model_name": "llama4-maverick-instruct-basic",
   "display_name": "Llama 4 Maverick Instruct (Basic)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama4-maverick-instruct-basic"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "open_weights": true
   },
   "intro": "The Meta Llama 3.1 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction tuned generative models in 8B, 70B and 405B sizes. The Llama 3.1 instruction tuned text only models (8B, 70B, 405B) are optimized for multilingual dialogue use cases and outperform many of the available open source and closed chat models on common industry benchmarks.",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama4-maverick-instruct-basic"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 4 Maverick Instruct (Basic)"
    }
   ]
  },
  {
   "slug": "meta/llama4-scout-instruct-basic",
   "model_name": "llama4-scout-instruct-basic",
   "display_name": "Llama 4 Scout Instruct (Basic)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama4-scout-instruct-basic"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama4-scout-instruct-basic"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 4 Scout Instruct (Basic)"
    }
   ]
  },
  {
   "slug": "meta/llamaguard-7b",
   "model_name": "llamaguard-7b",
   "display_name": "Llama Guard 7B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llamaguard-7b"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "safety_detection",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llamaguard-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama Guard 7B"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3_1-8B-Instruct-GGUF",
   "model_name": "Meta-Llama-3_1-8B-Instruct-GGUF",
   "display_name": "Meta Llama 3.1 8B Instruct (GGUF)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "atomic-chat",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "max_input_tokens": 131072,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3.1 8B Instruct (GGUF)"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3_3-70B-Instruct",
   "model_name": "Meta-Llama-3_3-70B-Instruct",
   "display_name": "Meta-Llama-3_3-70B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.74"
      }
     },
     "provider_model_id": "meta-llama-3_3-70b-instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-04-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama-3_3-70b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-3_3-70B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/meta-llama-3-1-8b-instruct",
   "model_name": "meta-llama-3-1-8b-instruct",
   "display_name": "Meta-Llama-3.1-8B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.61"
      }
     },
     "provider_model_id": "meta-llama-3.1-8b-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.61"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-8B-Instruct"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.61"
      }
     },
     "provider_model_id": "meta-llama-3.1-8b-instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-8B-Instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/meta-llama-3.1-8b-instruct"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-8B-Instruct"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.002"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-8B-Instruct"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     }
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-8B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice",
   "model_type": "text_generation",
   "deprecated": true,
   "deprecation_date": "2026-04-14",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Meta-Llama-3.1-8B-Instruct",
    "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct",
    "meta-llama-3.1-8b-instruct",
    "meta-llama/Meta-Llama-3.1-8B-Instruct",
    "meta/meta-llama-3.1-8b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.1 是一款经过指令微调的文本模型，专为多语言对话优化，在开放与闭源聊天模型中，在行业通用基准测试中表现出色。",
    "zh-TW": "Llama 3.1 是針對多語言對話優化的指令微調文字模型，在開源與封閉聊天模型中於多項業界基準測試中表現優異。",
    "ja-JP": "Llama 3.1 は、多言語チャットに最適化された命令調整済みテキストモデルで、オープン・クローズド両方のチャットモデルの中で業界ベンチマークにおいて高い性能を発揮します。",
    "ru-RU": "Llama 3.1 — модель, настроенная на выполнение инструкций, оптимизированная для многоязычного чата, демонстрирующая высокие результаты на отраслевых бенчмарках среди открытых и закрытых моделей."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "listed",
     "note": "Meta-Llama-3.1-8B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3-1-8B-Instruct-FP8",
   "model_name": "Meta-Llama-3-1-8B-Instruct-FP8",
   "display_name": "Llama 3.1 8B (decentralized)",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "stackit",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-07-23",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "family": "llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "structured_output: true→false"
    },
    {
     "date": "2026-07-06",
     "kind": "limit",
     "old": "8192",
     "new": "16384",
     "note": "max_output_tokens"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 8B"
    }
   ]
  },
  {
   "slug": "meta/meta-llama-3-3-70b-instruct",
   "model_name": "meta-llama-3-3-70b-instruct",
   "display_name": "Llama-3.3-70B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Meta-Llama-3.3-70B-Instruct"
    }
   ],
   "intro": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting",
   "released_at": "2024-12-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://cloud.sambanova.ai/plans/pricing",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Meta-Llama-3.3-70B-Instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.3 70B 是一款多用途的 Transformer 模型，适用于对话和文本生成任务。",
    "zh-TW": "Llama 3.3 70B 是一款多功能 Transformer 模型，適用於對話與生成任務。",
    "ja-JP": "Llama 3.3 70B は、チャットや生成タスクに対応する多用途な Transformer モデルです。",
    "ru-RU": "Llama 3.3 70B — это универсальная модель Transformer для задач чата и генерации."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "listed",
     "note": "Llama-3.3-70B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/meta-llama-3-70b",
   "model_name": "meta-llama-3-70b",
   "display_name": "meta-llama-3-70b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.795"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.795"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "meta-llama-3-70b"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3-70B-Instruct",
   "model_name": "Meta-Llama-3-70B-Instruct",
   "display_name": "Meta-Llama-3-70B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.54"
      }
     },
     "provider_model_id": "meta-llama-3-70b-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.37"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.54"
      }
     },
     "provider_model_id": "meta-llama-3-70b-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/meta-llama-3-70b-instruct"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-04-18",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 8192,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "parallel_function_calling": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama-3-70b-instruct",
    "meta/meta-llama-3-70b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "一款强大的 70B 参数模型，擅长推理、编程与广泛语言任务。",
    "zh-TW": "一款擁有 700 億參數的強大模型，擅長推理、程式設計與多語言任務。",
    "ja-JP": "70Bパラメータを持つ強力なモデルで、推論、コーディング、幅広い言語タスクに優れています。",
    "ru-RU": "Мощная модель с 70 миллиардами параметров, превосходно справляющаяся с рассуждениями, программированием и широким спектром языковых задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-3-70B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3-70B-Instruct-abliterated-v3.5",
   "model_name": "Meta-Llama-3-70B-Instruct-abliterated-v3.5",
   "display_name": "Llama 3 70B abliterated",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-07-26",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 70B abliterated"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3-70B-Instruct-Lite",
   "model_name": "Meta-Llama-3-70B-Instruct-Lite",
   "display_name": "Meta-Llama-3-70B-Instruct-Lite",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.54"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3-70B-Instruct-Lite"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Meta-Llama-3-70B-Instruct-Lite"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3 70B Instruct Lite 旨在在低延迟下实现高性能。",
    "zh-TW": "Llama 3 70B Instruct Lite 針對高效能與低延遲進行設計。",
    "ja-JP": "Llama 3 70B Instruct Liteは高性能かつ低レイテンシーを実現するよう設計されています。",
    "ru-RU": "Llama 3 70B Instruct Lite создана для высокой производительности с низкой задержкой."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-3-70B-Instruct-Lite"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3-70B-Instruct-Turbo",
   "model_name": "Meta-Llama-3-70B-Instruct-Turbo",
   "display_name": "Meta Llama 3 70B Instruct Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3-70B-Instruct-Turbo"
    }
   ],
   "capabilities": {},
   "max_input_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Meta-Llama-3-70B-Instruct-Turbo"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3 70B Instruct Turbo 在理解与生成方面表现强劲，适用于高负载任务。",
    "zh-TW": "Llama 3 70B Instruct Turbo 提供強大的理解與生成能力，適用於最嚴苛的工作負載。",
    "ja-JP": "Llama 3 70B Instruct Turboは、最も要求の厳しいワークロードに対応する強力な理解力と生成能力を提供します。",
    "ru-RU": "Llama 3 70B Instruct Turbo обеспечивает глубокое понимание и генерацию текста для самых требовательных задач."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3 70B Instruct Turbo"
    }
   ]
  },
  {
   "slug": "meta/meta-llama-3-8b",
   "model_name": "meta-llama-3-8b",
   "display_name": "meta-llama-3-8b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.548"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.548"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "meta-llama-3-8b"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3-8B-Instruct",
   "model_name": "Meta-Llama-3-8B-Instruct",
   "display_name": "Meta-Llama-3-8B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.61"
      }
     },
     "provider_model_id": "meta-llama-3-8b-instruct"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.61"
      }
     },
     "provider_model_id": "meta-llama-3-8b-instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3-8B-Instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/meta-llama-3-8b-instruct"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13999999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13999999999999999"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3-8B-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3-8B-Instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-04-18",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 8192,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct",
    "meta-llama-3-8b-instruct",
    "meta-llama/Meta-Llama-3-8B-Instruct",
    "meta/meta-llama-3-8b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "一款多功能的 8B 参数模型，针对对话与文本生成进行了优化。",
    "zh-TW": "一款多功能的 80 億參數模型，針對對話與文字生成進行優化。",
    "ja-JP": "チャットとテキスト生成に最適化された多用途な8Bパラメータモデルです。",
    "ru-RU": "Универсальная модель с 8 миллиардами параметров, оптимизированная для чатов и генерации текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-3-8B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3-8B-Instruct-Lite",
   "model_name": "Meta-Llama-3-8B-Instruct-Lite",
   "display_name": "Meta Llama 3 8B Instruct Lite",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3-8B-Instruct-Lite"
    }
   ],
   "intro": "Compact Llama instruction model for fast chat and local deployment",
   "released_at": "2024-04-18",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Meta-Llama-3-8B-Instruct-Lite"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3 8B Instruct Lite 在资源受限环境中实现性能平衡。",
    "zh-TW": "Llama 3 8B Instruct Lite 在資源受限環境中平衡效能與效率。",
    "ja-JP": "Llama 3 8B Instruct Liteは、リソース制約のある環境向けにパフォーマンスを最適化しています。",
    "ru-RU": "Llama 3 8B Instruct Lite сбалансирована для работы в условиях ограниченных ресурсов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3 8B Instruct Lite"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3-8B-Instruct-Turbo",
   "model_name": "Meta-Llama-3-8B-Instruct-Turbo",
   "display_name": "Meta-Llama-3-8B-Instruct-Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3-8B-Instruct-Turbo"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Meta-Llama-3-8B-Instruct-Turbo"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3 8B Instruct Turbo 是一款高性能大模型，适用于多种应用场景。",
    "zh-TW": "Llama 3 8B Instruct Turbo 是一款高效能大型語言模型，適用於多種應用場景。",
    "ja-JP": "Llama 3 8B Instruct Turboは、幅広いユースケースに対応する高性能LLMです。",
    "ru-RU": "Llama 3 8B Instruct Turbo — высокопроизводительная LLM для широкого спектра задач."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-3-8B-Instruct-Turbo"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3.1-405B-Instruct-Turbo",
   "model_name": "Meta-Llama-3.1-405B-Instruct-Turbo",
   "display_name": "Llama 3.1 405B Instruct Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"
    }
   ],
   "intro": "Compact Llama instruction model for fast chat and local deployment",
   "released_at": "2024-07-23",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo"
   ],
   "intro_i18n": {
    "zh-CN": "405B 参数的 Llama 3.1 Turbo 模型具备超大上下文处理能力，适用于大数据处理与超大规模 AI 应用。",
    "zh-TW": "405B Llama 3.1 Turbo 模型具備超大上下文容量，適用於大數據處理與超大規模 AI 應用。",
    "ja-JP": "405B Llama 3.1 Turboモデルは、大規模なデータ処理に対応する膨大なコンテキスト容量を提供し、超大規模AIアプリケーションにおいて卓越した性能を発揮します。",
    "ru-RU": "Модель Llama 3.1 Turbo с 405 миллиардами параметров обладает огромной контекстной емкостью для обработки больших данных и превосходно справляется с задачами ультра-масштабного ИИ."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 405B Instruct Turbo"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3.1-70B",
   "model_name": "Meta-Llama-3.1-70B",
   "display_name": "Meta-Llama-3.1-70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3.1-70B"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Meta-Llama-3.1-70B"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.1 是 Meta 的旗舰模型系列，参数规模高达 405B，适用于复杂对话、多语言翻译与数据分析任务。",
    "zh-TW": "Llama 3.1 是 Meta 領先的模型系列，參數規模高達 405B，適用於複雜對話、多語言翻譯與資料分析。",
    "ja-JP": "Llama 3.1はMetaの最先端モデルファミリーであり、405Bパラメータまでスケーリング可能で、複雑な対話、多言語翻訳、データ分析に対応します。",
    "ru-RU": "Llama 3.1 — флагманская модель Meta, масштабируемая до 405 миллиардов параметров, предназначена для сложных диалогов, многоязычного перевода и анализа данных."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-3.1-70B"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3.1-8B",
   "model_name": "Meta-Llama-3.1-8B",
   "display_name": "Meta Llama 3.1 8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3.1-8B"
    }
   ],
   "released_at": "2024-04-18",
   "max_input_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Meta-Llama-3.1-8B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3.1 8B"
    }
   ]
  },
  {
   "slug": "meta/meta-llama-3.1-8B-Instruct-AWQ-INT4",
   "model_name": "meta-llama-3.1-8B-Instruct-AWQ-INT4",
   "display_name": "meta-llama-3.1-8B-Instruct-AWQ-INT4",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/meta-llama-3.1-8B-Instruct-AWQ-INT4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "meta-llama-3.1-8B-Instruct-AWQ-INT4"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3.1-8B-Instruct-fast",
   "model_name": "Meta-Llama-3.1-8B-Instruct-fast",
   "display_name": "Meta Llama 3.1 8B Instruct Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct-fast"
    }
   ],
   "intro": "Optimized version of Llama 3.1 8B Instruct with 128K context window, designed for high-speed inference in multilingual chat and dialogue use cases with improved throughput and efficiency.",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "functions",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true
   },
   "released_at": "2024-07-23",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Meta-Llama-3.1-8B-Instruct-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3.1 8B Instruct Turbo"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3.1-8B-Instruct-Reference",
   "model_name": "Meta-Llama-3.1-8B-Instruct-Reference",
   "display_name": "Meta-Llama-3.1-8B-Instruct-Reference",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3.1-8B-Instruct-Reference"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Meta-Llama-3.1-8B-Instruct-Reference"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-3.1-8B-Instruct-Reference"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3.2-1B-Instruct",
   "model_name": "Meta-Llama-3.2-1B-Instruct",
   "display_name": "Meta Llama 3.2 1B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    }
   ],
   "docs_url": "https://cloud.sambanova.ai/plans/pricing",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2025-06-25",
   "capabilities": {},
   "knowledge_cutoff": "2023-12",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "前沿的小型语言模型，具备出色的语言理解、推理能力和文本生成能力。",
    "zh-TW": "前沿的小型語言模型，具備強大的語言理解、優異的推理與文字生成能力。",
    "ja-JP": "優れた言語理解、推論、テキスト生成能力を備えた最先端の小型言語モデルです。",
    "ru-RU": "Передовая компактная языковая модель с высоким уровнем понимания языка, отличной логикой и генерацией текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3.2 1B Instruct"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3.2-3B-Instruct",
   "model_name": "Meta-Llama-3.2-3B-Instruct",
   "display_name": "Meta Llama 3.2 3B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    }
   ],
   "docs_url": "https://cloud.sambanova.ai/plans/pricing",
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2025-06-25",
   "capabilities": {},
   "knowledge_cutoff": "2023-12",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "前沿的小型语言模型，具备出色的语言理解、推理能力和文本生成能力。",
    "zh-TW": "前沿的小型語言模型，具備強大的語言理解、優異的推理與文字生成能力。",
    "ja-JP": "優れた言語理解、推論、テキスト生成能力を備えた最先端の小型言語モデルです。",
    "ru-RU": "Передовая компактная языковая модель с высоким уровнем понимания языка, отличной логикой и генерацией текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3.2 3B Instruct"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-3.3-70B-Instruct-Turbo",
   "model_name": "Meta-Llama-3.3-70B-Instruct-Turbo",
   "display_name": "Meta-Llama-3.3-70B-Instruct-Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "meta-llama/Meta-Llama-3.3-70B-Instruct-Turbo"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/Meta-Llama-3.3-70B-Instruct-Turbo"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-3.3-70B-Instruct-Turbo"
    }
   ]
  },
  {
   "slug": "meta/meta-llama-4-maverick",
   "model_name": "meta-llama-4-maverick",
   "display_name": "llama-4-maverick",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-4-maverick"
    }
   ]
  },
  {
   "slug": "meta/meta-llama-4-scout",
   "model_name": "meta-llama-4-scout",
   "display_name": "llama-4-scout",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-4-scout"
    }
   ]
  },
  {
   "slug": "meta/Meta-Llama-Guard-3-8B",
   "model_name": "Meta-Llama-Guard-3-8B",
   "display_name": "Meta-Llama-Guard-3-8B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "docs_url": "https://cloud.sambanova.ai/plans/pricing",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "deprecated": true,
   "model_type": "safety_detection",
   "deprecation_date": "2025-06-25",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-Guard-3-8B"
    }
   ]
  },
  {
   "slug": "meta/meta-llama/Llama-3.3-70B-Instruct-Turbo",
   "model_name": "meta-llama/Llama-3.3-70B-Instruct-Turbo",
   "display_name": "Llama 3.3 70B Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     },
     "provider_model_id": "Llama-3.3-70B-Instruct-Turbo"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.04"
      }
     },
     "provider_model_id": "Llama-3.3-70B-Instruct-Turbo"
    }
   ],
   "intro": "Compact Llama instruction model for fast chat and local deployment",
   "released_at": "2024-12-06",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "knowledge_cutoff": "2023-12",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Llama-3.3-70B-Instruct-Turbo",
    "Llama-3.3-70B-Instruct-Turbo-Free",
    "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo",
    "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
   ],
   "intro_i18n": {
    "zh-CN": "Meta Llama 3.3 多语言大模型，70B 参数（文本输入/输出），经过预训练与指令微调。该文本模型针对多语言对话优化，在多个行业基准测试中超越众多开源与闭源模型。",
    "zh-TW": "Meta Llama 3.3 多語言大型語言模型，為 70B（文字輸入/輸出）預訓練並指令微調版本。此文字指令微調版本針對多語言對話進行優化，在開源與封閉模型中於業界基準測試表現優異。",
    "ja-JP": "Meta Llama 3.3多言語LLMは70B（テキスト入力/出力）で事前学習および命令調整されたモデルです。命令調整済みのテキスト専用バージョンは多言語チャットに最適化されており、業界標準ベンチマークで多くのオープンおよびクローズドチャットモデルを上回ります。",
    "ru-RU": "Meta Llama 3.3 — многоязычная LLM с 70 миллиардами параметров (ввод/вывод текста), обученная на инструкциях. Оптимизирована для многоязычных чатов и превосходит многие открытые и закрытые модели на отраслевых бенчмарках."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 70B Turbo"
    }
   ]
  },
  {
   "slug": "meta/meta-llama/Meta-Llama-3.1-405B-Instruct",
   "model_name": "meta-llama/Meta-Llama-3.1-405B-Instruct",
   "display_name": "Meta-Llama-3.1-405B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      }
     },
     "provider_model_id": "meta-llama-3.1-405b-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-405B-Instruct"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      }
     },
     "provider_model_id": "meta-llama-3.1-405b-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/meta-llama-3.1-405b-instruct"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-405B-Instruct"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-405B-Instruct"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-405B-Instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice",
   "model_type": "text_generation",
   "deprecated": true,
   "deprecation_date": "2025-06-25",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Meta-Llama-3.1-405B-Instruct",
    "deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct",
    "meta-llama-3.1-405b-instruct",
    "meta/meta-llama-3.1-405b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.1 是一款经过指令微调的文本模型，专为多语言对话优化，在开放与闭源聊天模型中，在行业通用基准测试中表现出色。",
    "zh-TW": "Llama 3.1 是針對多語言對話優化的指令微調文字模型，在開源與封閉聊天模型中於多項業界基準測試中表現優異。",
    "ja-JP": "Llama 3.1 は、多言語チャットに最適化された命令調整済みテキストモデルで、オープン・クローズド両方のチャットモデルの中で業界ベンチマークにおいて高い性能を発揮します。",
    "ru-RU": "Llama 3.1 — модель, настроенная на выполнение инструкций, оптимизированная для многоязычного чата, демонстрирующая высокие результаты на отраслевых бенчмарках среди открытых и закрытых моделей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-3.1-405B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/meta-llama/Meta-Llama-3.1-70B-Instruct",
   "model_name": "meta-llama/Meta-Llama-3.1-70B-Instruct",
   "display_name": "Meta-Llama-3.1-70B-Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.54"
      }
     },
     "provider_model_id": "meta-llama-3.1-70b-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.54"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-70B-Instruct"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.54"
      }
     },
     "provider_model_id": "meta-llama-3.1-70b-instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-70B-Instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/meta-llama-3.1-70b-instruct"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-70B-Instruct"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-70B-Instruct"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-70B-Instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     }
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Meta-Llama-3.1-70B-Instruct",
    "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct",
    "meta-llama-3.1-70b-instruct",
    "meta/meta-llama-3.1-70b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.1 是一款经过指令微调的文本模型，专为多语言对话优化，在开放与闭源聊天模型中，在行业通用基准测试中表现出色。",
    "zh-TW": "Llama 3.1 是針對多語言對話優化的指令微調文字模型，在開源與封閉聊天模型中於多項業界基準測試中表現優異。",
    "ja-JP": "Llama 3.1 は、多言語チャットに最適化された命令調整済みテキストモデルで、オープン・クローズド両方のチャットモデルの中で業界ベンチマークにおいて高い性能を発揮します。",
    "ru-RU": "Llama 3.1 — модель, настроенная на выполнение инструкций, оптимизированная для многоязычного чата, демонстрирующая высокие результаты на отраслевых бенчмарках среди открытых и закрытых моделей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta-Llama-3.1-70B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
   "model_name": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
   "display_name": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-70B-Instruct-Turbo"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-70B-Instruct-Turbo"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-07-21",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Meta-Llama-3.1-70B-Instruct-Turbo",
    "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.1 70B 针对高负载应用精细调优；FP8 量化实现高效计算与复杂场景下的准确性。",
    "zh-TW": "Llama 3.1 70B 為高負載應用精細調整；FP8 量化實現高效運算與複雜場景下的準確性。",
    "ja-JP": "Llama 3.1 70Bは高負荷アプリケーション向けに最適化されており、FP8量子化により複雑なシナリオでも効率的な計算と高精度を実現します。",
    "ru-RU": "Llama 3.1 70B точно настроена для высоконагруженных приложений; квантование FP8 обеспечивает эффективные вычисления и точность в сложных сценариях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"
    }
   ]
  },
  {
   "slug": "meta/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
   "model_name": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
   "display_name": "Meta Llama 3.1 8B Instruct Turbo",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-8B-Instruct-Turbo"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "Meta-Llama-3.1-8B-Instruct-Turbo"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Optimized version of Llama 3.1 8B Instruct with 128K context window, designed for high-speed inference in multilingual chat and dialogue use cases with improved throughput and efficiency.",
   "knowledge_cutoff": "2024-07",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "released_at": "2025-03-06",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Meta-Llama-3.1-8B-Instruct-Turbo",
    "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.1 8B 使用 FP8 量化，支持最多 131,072 个上下文 token，在多个基准测试中表现优异，适用于复杂任务。",
    "zh-TW": "Llama 3.1 8B 採用 FP8 量化，支援最多 131,072 個上下文 token，在多項基準測試中名列前茅，適合處理複雜任務。",
    "ja-JP": "Llama 3.1 8BはFP8量子化を採用し、最大131,072トークンのコンテキストをサポート。多くのベンチマークで複雑なタスクにおいてトップクラスのオープンモデルとして評価されています。",
    "ru-RU": "Llama 3.1 8B использует квантование FP8, поддерживает до 131 072 токенов контекста и входит в число лучших открытых моделей для сложных задач по многим бенчмаркам."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Meta Llama 3.1 8B Instruct Turbo"
    }
   ]
  },
  {
   "slug": "meta/meta-llama3-1-405b",
   "model_name": "meta-llama3-1-405b",
   "display_name": "llama3.1-405b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "released_at": "2024-07-23",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.1-405b"
    }
   ]
  },
  {
   "slug": "meta/meta-llama3-1-70b",
   "model_name": "meta-llama3-1-70b",
   "display_name": "llama3.1-70b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "released_at": "2024-07-23",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.1-70b"
    }
   ]
  },
  {
   "slug": "meta/meta-llama3-1-8b",
   "model_name": "meta-llama3-1-8b",
   "display_name": "llama3.1-8b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2024-07-23",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.1-8b"
    }
   ]
  },
  {
   "slug": "meta/meta-llama3-2-11b",
   "model_name": "meta-llama3-2-11b",
   "display_name": "llama3.2-11b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2024-09-25",
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.2-11b"
    }
   ]
  },
  {
   "slug": "meta/meta-llama3-2-90b",
   "model_name": "meta-llama3-2-90b",
   "display_name": "llama3.2-90b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "released_at": "2024-09-25",
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.2-90b"
    }
   ]
  },
  {
   "slug": "meta/meta-llama3-3-70b",
   "model_name": "meta-llama3-3-70b",
   "display_name": "llama3.3-70b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "released_at": "2024-12-06",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.3-70b"
    }
   ]
  },
  {
   "slug": "meta/meta.llama2-13b-chat-v1",
   "model_name": "meta.llama2-13b-chat-v1",
   "display_name": "meta.llama2-13b-chat-v1",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "meta.llama2-13b-chat-v1"
    }
   ]
  },
  {
   "slug": "meta/meta.llama2-70b-chat-v1",
   "model_name": "meta.llama2-70b-chat-v1",
   "display_name": "meta.llama2-70b-chat-v1",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.56"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.56"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.56"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "meta.llama2-70b-chat-v1"
    }
   ]
  },
  {
   "slug": "meta/meta.llama3-70b-instruct-v1:0",
   "model_name": "meta.llama3-70b-instruct-v1:0",
   "display_name": "Llama 3 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.416667",
        "completion": "0.416667"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.2"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.03"
      }
     },
     "region": "ca-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.55"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "region": "us-gov-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "family": "llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Meta Llama 3 是一款面向开发者、研究人员和企业的开放式大语言模型，旨在帮助他们构建、实验并负责任地扩展生成式 AI 创意。作为全球社区创新的基础之一，它非常适合内容创作、对话式 AI、语言理解、研发和企业级应用。",
    "zh-TW": "Meta Llama 3 是一款開放式 LLM，專為開發者、研究人員與企業設計，協助他們構建、實驗並負責任地擴展生成式 AI 應用。作為全球社群創新的基礎，適用於內容創作、對話式 AI、語言理解、研發與企業應用。",
    "ja-JP": "Meta Llama 3は、開発者、研究者、企業向けのオープンLLMであり、生成AIのアイデアを構築・実験・拡張するための基盤です。グローバルなコミュニティによるイノベーションの基礎として、コンテンツ生成、対話型AI、言語理解、研究開発、企業アプリケーションに最適です。",
    "ru-RU": "Meta Llama 3 — открытая LLM для разработчиков, исследователей и компаний, предназначенная для создания, тестирования и масштабирования идей генеративного ИИ. Подходит для создания контента, диалогов, понимания языка и корпоративных приложений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/meta/llama-2-7b-chat-fp16",
   "model_name": "meta/llama-2-7b-chat-fp16",
   "display_name": "Llama 2 7B Chat FP16",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.67"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-2-7b-chat-fp16"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.67"
      }
     },
     "provider_model_id": "@cf/meta/llama-2-7b-chat-fp16"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-04-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-2-7b-chat-fp16",
    "workers-ai/@cf/meta/llama-2-7b-chat-fp16"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 2 7B Chat FP16"
    }
   ]
  },
  {
   "slug": "meta/meta/llama-3-8b-instruct-awq",
   "model_name": "meta/llama-3-8b-instruct-awq",
   "display_name": "Llama 3 8B Instruct AWQ",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-3-8b-instruct-awq"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "@cf/meta/llama-3-8b-instruct-awq"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-04-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-3-8b-instruct-awq",
    "workers-ai/@cf/meta/llama-3-8b-instruct-awq"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3 8B Instruct AWQ"
    }
   ]
  },
  {
   "slug": "meta/meta/llama-3.1-8b-instruct-awq",
   "model_name": "meta/llama-3.1-8b-instruct-awq",
   "display_name": "Llama 3.1 8B Instruct AWQ",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-3.1-8b-instruct-awq"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "@cf/meta/llama-3.1-8b-instruct-awq"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-04-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-3.1-8b-instruct-awq",
    "workers-ai/@cf/meta/llama-3.1-8b-instruct-awq"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 8B Instruct AWQ"
    }
   ]
  },
  {
   "slug": "meta/meta/llama-3.1-8b-instruct-fp8",
   "model_name": "meta/llama-3.1-8b-instruct-fp8",
   "display_name": "Llama 3.1 8B Instruct fp8",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.152"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.287"
      }
     },
     "provider_model_id": "@cf/meta/llama-3.1-8b-instruct-fp8"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-25",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-3.1-8b-instruct-fp8",
    "workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 8B Instruct fp8"
    }
   ]
  },
  {
   "slug": "meta/meta/llama-3.3-70b-instruct-fp8-fast",
   "model_name": "meta/llama-3.3-70b-instruct-fp8-fast",
   "display_name": "Llama 3.3 70B Instruct fp8 Fast",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.293"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.253"
      }
     },
     "provider_model_id": "@cf/meta/llama-3.3-70b-instruct-fp8-fast"
    }
   ],
   "intro": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting",
   "released_at": "2024-12-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 24000,
   "max_output_tokens": 24000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
    "workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 70B Instruct fp8 Fast"
    }
   ]
  },
  {
   "slug": "meta/meta/m2m100-1.2b",
   "model_name": "meta/m2m100-1.2b",
   "display_name": "M2M100 1.2B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/m2m100-1.2b"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "@cf/meta/m2m100-1.2b"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-04-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "m2m",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/m2m100-1.2b",
    "workers-ai/@cf/meta/m2m100-1.2b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "M2M100 1.2B"
    }
   ]
  },
  {
   "slug": "meta/Nous-Hermes-llama-2-7b",
   "model_name": "Nous-Hermes-llama-2-7b",
   "display_name": "Nous-Hermes-llama-2-7b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "NousResearch/Nous-Hermes-llama-2-7b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Nous-Hermes-llama-2-7b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nous-Hermes-llama-2-7b"
    }
   ]
  },
  {
   "slug": "meta/Nous-Hermes-Llama2-13b",
   "model_name": "Nous-Hermes-Llama2-13b",
   "display_name": "Nous Hermes Llama2 13B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "nous-hermes-llama2-13b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.17"
      }
     },
     "provider_model_id": "nousresearch/nous-hermes-llama2-13b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "nousresearch/nous-hermes-llama2-13b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.225"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.225"
      }
     },
     "provider_model_id": "NousResearch/Nous-Hermes-Llama2-13b"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-04-25",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Nous-Hermes-Llama2-13b",
    "accounts/fireworks/models/nous-hermes-llama2-13b",
    "nous-hermes-llama2-13b",
    "nousresearch/nous-hermes-llama2-13b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nous Hermes Llama2 13B"
    }
   ]
  },
  {
   "slug": "meta/nous-hermes-llama2-70b",
   "model_name": "nous-hermes-llama2-70b",
   "display_name": "Nous Hermes Llama2 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nous-hermes-llama2-70b"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nous-hermes-llama2-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nous Hermes Llama2 70B"
    }
   ]
  },
  {
   "slug": "meta/nous-hermes-llama2-7b",
   "model_name": "nous-hermes-llama2-7b",
   "display_name": "Nous Hermes Llama2 7B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nous-hermes-llama2-7b"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nous-hermes-llama2-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nous Hermes Llama2 7B"
    }
   ]
  },
  {
   "slug": "meta/NousResearch/Hermes-3-Llama-3.1-405B",
   "model_name": "NousResearch/Hermes-3-Llama-3.1-405B",
   "display_name": "Hermes 3 Llama 3.1 405b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "Hermes-3-Llama-3.1-405B"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "nousresearch/hermes-3-llama-3.1-405b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "Hermes-3-Llama-3.1-405B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "nousresearch/hermes-3-llama-3.1-405b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "hermes-3-llama-3.1-405b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-09-25",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "hermes",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "model_type": "text_generation",
   "docs_url": "https://nebius.com/prices-ai-studio",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Hermes-3-Llama-3.1-405B",
    "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B",
    "hermes-3-llama-3.1-405b",
    "nousresearch/hermes-3-llama-3.1-405b",
    "nousresearch/hermes-3-llama-3.1-405b:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes 3 Llama 3.1 405b"
    }
   ]
  },
  {
   "slug": "meta/NousResearch/Hermes-3-Llama-3.1-70B",
   "model_name": "NousResearch/Hermes-3-Llama-3.1-70B",
   "display_name": "Nous: Hermes 3 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Hermes-3-Llama-3.1-70B"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Hermes-3-Llama-3.1-70B"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "nousresearch/hermes-3-llama-3.1-70b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.408"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      }
     },
     "provider_model_id": "NousResearch/hermes-3-llama-3.1-70b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "nousresearch/hermes-3-llama-3.1-70b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-08-18",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true
   },
   "knowledge_cutoff": "2023-12",
   "family": "nousresearch",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Hermes-3-Llama-3.1-70B",
    "NousResearch/hermes-3-llama-3.1-70b",
    "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B",
    "hermes-3-llama-3.1-70b",
    "nousresearch/hermes-3-llama-3.1-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nous: Hermes 3 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/phind-code-llama-34b-python-v1",
   "model_name": "phind-code-llama-34b-python-v1",
   "display_name": "Phind CodeLlama 34B Python v1",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/phind-code-llama-34b-python-v1"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/phind-code-llama-34b-python-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phind CodeLlama 34B Python v1"
    }
   ]
  },
  {
   "slug": "meta/phind-code-llama-34b-v1",
   "model_name": "phind-code-llama-34b-v1",
   "display_name": "Phind CodeLlama 34B v1",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/phind-code-llama-34b-v1"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/phind-code-llama-34b-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phind CodeLlama 34B v1"
    }
   ]
  },
  {
   "slug": "meta/phind-code-llama-34b-v2",
   "model_name": "phind-code-llama-34b-v2",
   "display_name": "Phind CodeLlama 34B v2",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/phind-code-llama-34b-v2"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/phind-code-llama-34b-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phind CodeLlama 34B v2"
    }
   ]
  },
  {
   "slug": "meta/shisa-v2-llama3.3-70b",
   "model_name": "shisa-v2-llama3.3-70b",
   "display_name": "Shisa V2 Llama 3.3 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "shisa-ai/shisa-v2-llama3.3-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-07-26",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "shisa-ai/shisa-v2-llama3.3-70b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Shisa V2 Llama 3.3 70B"
    }
   ]
  },
  {
   "slug": "meta/shisa-v2.1-llama3.3-70b",
   "model_name": "shisa-v2.1-llama3.3-70b",
   "display_name": "Shisa V2.1 Llama 3.3 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "shisa-ai/shisa-v2.1-llama3.3-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "shisa-ai/shisa-v2.1-llama3.3-70b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Shisa V2.1 Llama 3.3 70B"
    }
   ]
  },
  {
   "slug": "meta/snowflake-llama-3.3-70b",
   "model_name": "snowflake-llama-3.3-70b",
   "display_name": "snowflake-llama-3.3-70b",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "snowflake-llama-3.3-70b"
    }
   ]
  },
  {
   "slug": "meta/snowflake-llama3.3-70b",
   "model_name": "snowflake-llama3.3-70b",
   "display_name": "Llama-3.3-70B-Instruct",
   "vendor": "meta",
   "pricing": [],
   "intro": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting",
   "released_at": "2024-12-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.3-70B-Instruct"
    }
   ]
  },
  {
   "slug": "meta/us.meta.llama3-1-405b-instruct-v1:0",
   "model_name": "us.meta.llama3-1-405b-instruct-v1:0",
   "display_name": "Llama 3.1 405B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      }
     },
     "provider_model_id": "meta.llama3-1-405b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.225564",
        "completion": "0.075"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "meta.llama3-1-405b-instruct-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      }
     },
     "provider_model_id": "meta.llama3-1-405b-instruct-v1:0"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "knowledge_cutoff": "2023-12",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta.llama3-1-405b-instruct-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "Meta Llama 3.1 405B Instruct 是 Llama 3.1 Instruct 系列中最大且最强大的模型，专为对话推理和合成数据生成而设计，是进行领域特定持续预训练或微调的强大基础。Llama 3.1 多语言大模型（LLM）包括 8B、70B 和 405B 三种规模的预训练与指令微调生成模型（文本输入/输出）。这些指令微调模型针对多语言对话进行了优化，在多个行业通用基准测试中优于许多开源聊天模型。Llama 3.1 适用于商业和科研用途，支持多语言。指令微调模型适合助手式聊天场景，预训练模型则适用于更广泛的自然语言生成任务。Llama 3.1 的输出还可用于提升其他模型的性能，包括合成数据生成与优化。Llama 3.1 是一种自回归 Transformer 模型，采用优化架构。其微调版本结合了监督微调（SFT）和基于人类反馈的强化学习（RLHF），以更好地符合人类对有用性与安全性的偏好。",
    "zh-TW": "Meta Llama 3.1 405B Instruct 是 Llama 3.1 Instruct 系列中最大且最強的模型，專為對話推理與合成資料生成設計，亦是領域特定持續預訓練或微調的強大基礎。Llama 3.1 多語言 LLM 系列包含 8B、70B 與 405B 模型，經過預訓練與指令微調，優化多語言對話，並在多項業界基準中超越其他開源聊天模型。Llama 3.1 適用於商業與研究用途，指令微調模型適合助理型對話，預訓練模型則適用於更廣泛的自然語言生成任務。其輸出亦可用於改進其他模型，包括合成資料生成與優化。Llama 3.1 採用自回歸 Transformer 架構，經由監督式微調（SFT）與人類回饋強化學習（RLHF）對齊人類偏好，提升有用性與安全性。",
    "ja-JP": "Meta Llama 3.1 405B Instructは、Llama 3.1 Instructモデルの中で最大かつ最も強力なモデルであり、対話推論や合成データ生成に優れ、ドメイン特化の事前学習やファインチューニングの基盤としても最適です。Llama 3.1の多言語LLMは、8B、70B、405Bのサイズで事前学習および命令調整された生成モデル（テキスト入力/出力）です。命令調整モデルは多言語対話に最適化され、業界標準のベンチマークで多くのオープンチャットモデルを上回ります。Llama 3.1は商用および研究用途に対応しており、命令調整モデルはアシスタント型チャットに、事前学習モデルはより広範な自然言語生成タスクに適しています。Llama 3.1の出力は、合成データ生成や精緻化など、他のモデルの改善にも活用可能です。Llama 3.1は自己回帰型Transformerモデルで、最適化されたアーキテクチャを採用。命令調整版はSFT（教師ありファインチューニング）とRLHF（人間のフィードバックによる強化学習）を用いて、人間の好みに沿った有用性と安全性を実現しています。",
    "ru-RU": "Meta Llama 3.1 405B Instruct — самая крупная и мощная модель Llama 3.1 Instruct, высокоразвитая модель для диалогового рассуждения и генерации синтетических данных, а также прочная основа для дообучения в конкретных доменах. Многоязычные LLM Llama 3.1 — это набор предварительно обученных и настроенных на инструкции моделей генерации в размерах 8B, 70B и 405B (ввод текста/вывод текста). Модели, настроенные на инструкции, оптимизированы для многоязычного диалога и превосходят многие доступные открытые чат-модели в отраслевых бенчмарках. Llama 3.1 предназначена для коммерческого и исследовательского использования на разных языках. Модели, настроенные на инструкции, подходят для чатов в стиле помощника, а предварительно обученные модели — для более широких задач генерации естественного языка. Выводы Llama 3.1 также можно использовать для улучшения других моделей, включая генерацию и доработку синтетических данных. Llama 3.1 — это авторегрессионная модель Transformer с оптимизированной архитектурой. Настроенные версии используют SFT и RLHF для соответствия человеческим предпочтениям в полезности и безопасности."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 405B Instruct"
    }
   ]
  },
  {
   "slug": "meta/us.meta.llama3-1-70b-instruct-v1:0",
   "model_name": "us.meta.llama3-1-70b-instruct-v1:0",
   "display_name": "Llama 3.1 70B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta.llama3-1-70b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.99"
      }
     },
     "provider_model_id": "meta.llama3-1-70b-instruct-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.363636",
        "completion": "0.363636"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.99"
      }
     },
     "provider_model_id": "meta.llama3-1-70b-instruct-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.363636",
        "completion": "0.363636"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.99"
      }
     },
     "provider_model_id": "meta.llama3-1-70b-instruct-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.363636",
        "completion": "0.363636"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.99"
      }
     },
     "provider_model_id": "meta.llama3-1-70b-instruct-v1:0"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta.llama3-1-70b-instruct-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "更新后的 Meta Llama 3.1 70B Instruct 支持 128K 上下文窗口，具备多语言支持和更强的推理能力。Llama 3.1 多语言大模型包括 8B、70B 和 405B 三种规模的预训练与指令微调生成模型（文本输入/输出）。这些指令微调模型针对多语言对话进行了优化，在多个行业通用基准测试中优于许多开源聊天模型。Llama 3.1 适用于商业和科研用途，支持多语言。指令微调模型适合助手式聊天场景，预训练模型则适用于更广泛的自然语言生成任务。Llama 3.1 的输出还可用于提升其他模型的性能，包括合成数据生成与优化。Llama 3.1 是一种自回归 Transformer 模型，采用优化架构。其微调版本结合了监督微调（SFT）和基于人类反馈的强化学习（RLHF），以更好地符合人类对有用性与安全性的偏好。",
    "zh-TW": "更新版 Meta Llama 3.1 70B Instruct，具備 128K 擴展上下文視窗、多語言支援與更強推理能力。Llama 3.1 多語言 LLM 系列包含 8B、70B 與 405B 模型，經過預訓練與指令微調，優化多語言對話，並在多項業界基準中超越其他開源聊天模型。Llama 3.1 適用於商業與研究用途，指令微調模型適合助理型對話，預訓練模型則適用於更廣泛的自然語言生成任務。其輸出亦可用於改進其他模型，包括合成資料生成與優化。Llama 3.1 採用自回歸 Transformer 架構，經由監督式微調（SFT）與人類回饋強化學習（RLHF）對齊人類偏好，提升有用性與安全性。",
    "ja-JP": "Meta Llama 3.1 70B Instructのアップデート版で、128Kの拡張コンテキストウィンドウ、多言語対応、推論能力の向上を備えています。Llama 3.1の多言語LLMは、8B、70B、405Bのサイズで事前学習および命令調整された生成モデル（テキスト入力/出力）です。命令調整モデルは多言語対話に最適化され、業界標準のベンチマークで多くのオープンチャットモデルを上回ります。Llama 3.1は商用および研究用途に対応しており、命令調整モデルはアシスタント型チャットに、事前学習モデルはより広範な自然言語生成タスクに適しています。Llama 3.1の出力は、合成データ生成や精緻化など、他のモデルの改善にも活用可能です。Llama 3.1は自己回帰型Transformerモデルで、最適化されたアーキテクチャを採用。命令調整版はSFT（教師ありファインチューニング）とRLHF（人間のフィードバックによる強化学習）を用いて、人間の好みに沿った有用性と安全性を実現しています。",
    "ru-RU": "Обновлённая версия Meta Llama 3.1 70B Instruct с расширенным контекстом до 128K, поддержкой нескольких языков и улучшенным рассуждением. Модели Llama 3.1 предназначены для коммерческого и исследовательского использования, оптимизированы для диалогов и превосходят многие открытые модели в отраслевых бенчмарках."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 70B Instruct"
    }
   ]
  },
  {
   "slug": "meta/us.meta.llama3-1-8b-instruct-v1:0",
   "model_name": "us.meta.llama3-1-8b-instruct-v1:0",
   "display_name": "Llama 3.1 8B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "meta.llama3-1-8b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "meta.llama3-1-8b-instruct-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "meta.llama3-1-8b-instruct-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "meta.llama3-1-8b-instruct-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "bedrock",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "meta.llama3-1-8b-instruct-v1:0"
    },
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "llama3.1-8b-instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llama3.1-8b-instruct",
    "meta.llama3-1-8b-instruct-v1:0"
   ],
   "intro_i18n": {
    "zh-CN": "更新后的 Meta Llama 3.1 8B Instruct 支持 128K 上下文窗口，具备多语言支持和更强的推理能力。Llama 3.1 系列包括 8B、70B 和 405B 三种规模的指令微调文本模型，专为多语言聊天和强基准表现而优化。该系列适用于多语言的商业和科研用途；指令微调模型适合助手式聊天，预训练模型则适用于更广泛的生成任务。Llama 3.1 的输出还可用于提升其他模型（如合成数据生成与优化）。它是一种自回归 Transformer 模型，结合了监督微调（SFT）和基于人类反馈的强化学习（RLHF），以实现更高的有用性与安全性。",
    "zh-TW": "更新版 Meta Llama 3.1 8B Instruct，具備 128K 上下文視窗、多語言支援與更強推理能力。Llama 3.1 系列包含 8B、70B 與 405B 指令微調模型，優化多語言對話並在基準測試中表現優異。適用於跨語言的商業與研究用途；指令微調模型適合助理型對話，預訓練模型則適用於更廣泛的生成任務。其輸出亦可用於改進其他模型（如合成資料與優化）。此為自回歸 Transformer 模型，透過 SFT 與 RLHF 對齊人類偏好，提升有用性與安全性。",
    "ja-JP": "Meta Llama 3.1 8B Instructのアップデート版で、128Kのコンテキストウィンドウ、多言語対応、推論能力の向上を備えています。Llama 3.1ファミリーには、8B、70B、405Bの命令調整テキストモデルが含まれ、多言語チャットと高いベンチマーク性能に最適化されています。商用および研究用途に対応し、命令調整モデルはアシスタント型チャットに、事前学習モデルはより広範な生成タスクに適しています。Llama 3.1の出力は、合成データ生成や精緻化など、他のモデルの改善にも活用可能です。自己回帰型Transformerモデルであり、SFTとRLHFにより有用性と安全性を実現しています。",
    "ru-RU": "Обновлённая версия Meta Llama 3.1 8B Instruct с контекстом 128K, поддержкой нескольких языков и улучшенным рассуждением. Подходит для диалогов в стиле помощника и генерации текста. Результаты могут использоваться для улучшения других моделей, включая генерацию синтетических данных."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 8B Instruct"
    }
   ]
  },
  {
   "slug": "meta/us.meta.llama3-2-11b-instruct-v1:0",
   "model_name": "us.meta.llama3-2-11b-instruct-v1:0",
   "display_name": "Llama 3.2 11B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "meta.llama3-2-11b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.228571",
        "completion": "0.228571"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2023-12",
   "family": "llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta.llama3-2-11b-instruct-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 11B Instruct"
    }
   ]
  },
  {
   "slug": "meta/us.meta.llama3-2-1b-instruct-v1:0",
   "model_name": "us.meta.llama3-2-1b-instruct-v1:0",
   "display_name": "Llama 3.2 1B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "eu.meta.llama3-2-1b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.384615",
        "completion": "0.384615"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "eu.meta.llama3-2-1b-instruct-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "eu.meta.llama3-2-1b-instruct-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "eu.meta.llama3-2-1b-instruct-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2023-12",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "eu.meta.llama3-2-1b-instruct-v1:0",
    "meta.llama3-2-1b-instruct-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 1B Instruct"
    }
   ]
  },
  {
   "slug": "meta/us.meta.llama3-2-3b-instruct-v1:0",
   "model_name": "us.meta.llama3-2-3b-instruct-v1:0",
   "display_name": "Llama 3.2 3B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "eu.meta.llama3-2-3b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.394737",
        "completion": "0.394737"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "eu.meta.llama3-2-3b-instruct-v1:0",
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.17"
      }
     },
     "provider_model_id": "eu.meta.llama3-2-3b-instruct-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "eu.meta.llama3-2-3b-instruct-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "llama3.2-3b-instruct"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "doc"
    ],
    "output": []
   },
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2023-12",
   "family": "llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "eu.meta.llama3-2-3b-instruct-v1:0",
    "llama3.2-3b-instruct",
    "meta.llama3-2-3b-instruct-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 3B Instruct"
    }
   ]
  },
  {
   "slug": "meta/us.meta.llama3-2-90b-instruct-v1:0",
   "model_name": "us.meta.llama3-2-90b-instruct-v1:0",
   "display_name": "Llama 3.2 90B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "meta.llama3-2-90b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.18",
        "completion": "0.18"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2023-12",
   "family": "llama",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta.llama3-2-90b-instruct-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.2 90B Instruct"
    }
   ]
  },
  {
   "slug": "meta/us.meta.llama3-3-70b-instruct-v1:0",
   "model_name": "us.meta.llama3-3-70b-instruct-v1:0",
   "display_name": "Llama 3.3 Instruct 70B",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta.llama3-3-70b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta.llama3-3-70b-instruct-v1:0",
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta.llama3-3-70b-instruct-v1:0",
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "meta.llama3-3-70b-instruct-v1:0",
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "provider_model_id": "llama3.3-70b-instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llama3.3-70b-instruct",
    "meta.llama3-3-70b-instruct-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 Instruct 70B"
    }
   ]
  },
  {
   "slug": "meta/us.meta.llama4-maverick-17b-instruct-v1:0",
   "model_name": "us.meta.llama4-maverick-17b-instruct-v1:0",
   "display_name": "Llama 4 Maverick 17B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      }
     },
     "provider_model_id": "meta.llama4-maverick-17b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      }
     },
     "region": "us-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      }
     },
     "region": "us-east-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      }
     },
     "region": "us-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.97"
      }
     },
     "region": "us-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Open multimodal Llama model for strong reasoning and fast responses",
   "released_at": "2025-04-05",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta.llama4-maverick-17b-instruct-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 4 Maverick 17B Instruct"
    }
   ]
  },
  {
   "slug": "meta/us.meta.llama4-scout-17b-instruct-v1:0",
   "model_name": "us.meta.llama4-scout-17b-instruct-v1:0",
   "display_name": "Llama 4 Scout 17B Instruct",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     },
     "provider_model_id": "meta.llama4-scout-17b-instruct-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     },
     "region": "us-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Open multimodal Llama model for long-context analysis and efficient agents",
   "released_at": "2025-04-05",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 3500000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta.llama4-scout-17b-instruct-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 4 Scout 17B Instruct"
    }
   ]
  },
  {
   "slug": "meta/Wayfarer-Large-70B-Llama-3.3",
   "model_name": "Wayfarer-Large-70B-Llama-3.3",
   "display_name": "Llama 3.3 70B Wayfarer",
   "vendor": "meta",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.700000007"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.700000007"
      }
     },
     "provider_model_id": "LatitudeGames/Wayfarer-Large-70B-Llama-3.3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "latitudegames/wayfarer-large-70b-llama-3.3"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-02-20",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "LatitudeGames/Wayfarer-Large-70B-Llama-3.3",
    "latitudegames/wayfarer-large-70b-llama-3.3"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 70B Wayfarer"
    }
   ]
  },
  {
   "slug": "microsoft/ahm-Phi-3-5-mini-instruct",
   "model_name": "ahm-Phi-3-5-mini-instruct",
   "display_name": "ahm-Phi-3-5-mini-instruct",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ahm-Phi-3-5-mini-instruct"
    }
   ]
  },
  {
   "slug": "microsoft/ahm-Phi-3-5-MoE-instruct",
   "model_name": "ahm-Phi-3-5-MoE-instruct",
   "display_name": "ahm-Phi-3-5-MoE-instruct",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ahm-Phi-3-5-MoE-instruct"
    }
   ]
  },
  {
   "slug": "microsoft/ahm-Phi-3-5-vision-instruct",
   "model_name": "ahm-Phi-3-5-vision-instruct",
   "display_name": "ahm-Phi-3-5-vision-instruct",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ahm-Phi-3-5-vision-instruct"
    }
   ]
  },
  {
   "slug": "microsoft/ahm-Phi-3-medium-128k",
   "model_name": "ahm-Phi-3-medium-128k",
   "display_name": "ahm-Phi-3-medium-128k",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ahm-Phi-3-medium-128k"
    }
   ]
  },
  {
   "slug": "microsoft/ahm-Phi-3-medium-4k",
   "model_name": "ahm-Phi-3-medium-4k",
   "display_name": "ahm-Phi-3-medium-4k",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ahm-Phi-3-medium-4k"
    }
   ]
  },
  {
   "slug": "microsoft/ahm-Phi-3-small-128k",
   "model_name": "ahm-Phi-3-small-128k",
   "display_name": "ahm-Phi-3-small-128k",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ahm-Phi-3-small-128k"
    }
   ]
  },
  {
   "slug": "microsoft/aihub-Phi-4",
   "model_name": "aihub-Phi-4",
   "display_name": "aihub-Phi-4",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     }
    }
   ],
   "max_input_tokens": 16400,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihub-Phi-4"
    }
   ]
  },
  {
   "slug": "microsoft/aihub-Phi-4-mini-instruct",
   "model_name": "aihub-Phi-4-mini-instruct",
   "display_name": "aihub-Phi-4-mini-instruct",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihub-Phi-4-mini-instruct"
    }
   ]
  },
  {
   "slug": "microsoft/aihub-Phi-4-multimodal-instruct",
   "model_name": "aihub-Phi-4-multimodal-instruct",
   "display_name": "aihub-Phi-4-multimodal-instruct",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "audio",
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihub-Phi-4-multimodal-instruct"
    }
   ]
  },
  {
   "slug": "microsoft/AiHubmix-Phi-4-mini-reasoning",
   "model_name": "AiHubmix-Phi-4-mini-reasoning",
   "display_name": "AiHubmix-Phi-4-mini-reasoning",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AiHubmix-Phi-4-mini-reasoning"
    }
   ]
  },
  {
   "slug": "microsoft/MAI-DS-R1",
   "model_name": "MAI-DS-R1",
   "display_name": "MAI-DS-R1",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "mai-ds-r1"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.4"
      }
     },
     "provider_model_id": "mai-ds-r1"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/mai-ds-r1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mai-ds-r1"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-01-20",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 65536,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mai",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/",
   "model_type": "deep_thinking",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mai-ds-r1",
    "mai-ds-r1:free",
    "microsoft/mai-ds-r1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MAI-DS-R1"
    }
   ]
  },
  {
   "slug": "microsoft/MAI-DS-R1-GGUF",
   "model_name": "MAI-DS-R1-GGUF",
   "display_name": "unsloth/MAI-DS-R1-GGUF",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.79914765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.85409875"
      }
     },
     "provider_model_id": "unsloth/MAI-DS-R1-GGUF"
    }
   ],
   "released_at": "2026-01-19",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "unsloth/MAI-DS-R1-GGUF"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592687",
     "new": "2.85409875"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800595236",
     "new": "0.79914765"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.858164925",
     "new": "2.8592687"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800286179",
     "new": "0.800595236"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.860353575",
     "new": "2.858164925"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800899001",
     "new": "0.800286179"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592021",
     "new": "2.860353575"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800576588",
     "new": "0.800899001"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.859994675",
     "new": "2.8592021"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800798509",
     "new": "0.800576588"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8452425",
     "new": "2.859994675"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.7966679",
     "new": "0.800798509"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "unsloth/MAI-DS-R1-GGUF"
    }
   ]
  },
  {
   "slug": "microsoft/MAI-Image-2.5",
   "model_name": "MAI-Image-2.5",
   "display_name": "microsoft/mai-image-2.5",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "47"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "microsoft/mai-image-2.5"
    }
   ],
   "docs_url": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632",
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/mai-image-2.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "microsoft/mai-image-2.5"
    }
   ]
  },
  {
   "slug": "microsoft/microsoftPhi-mal-ds-r1",
   "model_name": "microsoftPhi-mal-ds-r1",
   "display_name": "MAI-DS-R1",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-05-20",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MAI-DS-R1"
    }
   ]
  },
  {
   "slug": "microsoft/microsoftPhi-phi-4-mini-reasoning",
   "model_name": "microsoftPhi-phi-4-mini-reasoning",
   "display_name": "Phi-4-mini-reasoning",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-4-mini-reasoning"
    }
   ]
  },
  {
   "slug": "microsoft/microsoftPhi-phi-4-reasoning",
   "model_name": "microsoftPhi-phi-4-reasoning",
   "display_name": "Phi-4-reasoning",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-4-reasoning"
    }
   ]
  },
  {
   "slug": "microsoft/phi-2",
   "model_name": "phi-2",
   "display_name": "phi-2",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "microsoft/phi-2"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "phi-2"
    }
   ]
  },
  {
   "slug": "microsoft/phi-2-3b",
   "model_name": "phi-2-3b",
   "display_name": "phi-2-3b",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 2048,
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "phi-2-3b"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-3-medium-128k-instruct",
   "model_name": "Phi-3-medium-128k-instruct",
   "display_name": "Phi-3-medium instruct (128k)",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "phi-3-medium-128k-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "phi-3-medium-128k-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-3-medium-128k-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "microsoft/phi-3-medium-128k-instruct"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2024-04-23",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-3-medium-128k-instruct",
    "phi-3-medium-128k-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "与 Phi-3-medium 模型相同，但支持更大上下文窗口，适用于 RAG 或少样本提示。",
    "zh-TW": "與 Phi-3-medium 相同的模型，具備更大的上下文視窗，適用於 RAG 或少量示例提示。",
    "ja-JP": "Phi-3-mediumモデルに、RAGやfew-shotプロンプト向けの大きなコンテキストウィンドウを追加したバージョンです。",
    "ru-RU": "Та же модель Phi-3-medium с увеличенным окном контекста для RAG или few-shot подсказок."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-3-medium instruct (128k)"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-3-medium-4k-instruct",
   "model_name": "Phi-3-medium-4k-instruct",
   "display_name": "Phi-3-medium instruct (4k)",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "phi-3-medium-4k-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "phi-3-medium-4k-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-3-medium-4k-instruct"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2024-04-23",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 4096,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-3-medium-4k-instruct",
    "phi-3-medium-4k-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "一款拥有 140 亿参数的模型，质量优于 Phi-3-mini，专注于高质量、推理密集型数据。",
    "zh-TW": "一個擁有 140 億參數的模型，品質優於 Phi-3-mini，專注於高品質、需推理的資料。",
    "ja-JP": "Phi-3-miniよりも高品質で、推論重視のデータに特化した140億パラメータのモデルです。",
    "ru-RU": "Модель с 14B параметрами, обеспечивающая более высокое качество, чем Phi-3-mini, с акцентом на данные, требующие глубокого рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-3-medium instruct (4k)"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-3-mini-128k-instruct",
   "model_name": "Phi-3-mini-128k-instruct",
   "display_name": "Phi-3-mini instruct (128k)",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     },
     "provider_model_id": "phi-3-mini-128k-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     },
     "provider_model_id": "phi-3-mini-128k-instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "phi-3-mini-128k-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-3-mini-128k-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "microsoft/phi-3-mini-128k-instruct"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-04-23",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/phi-3-mini-128k-instruct",
    "microsoft/phi-3-mini-128k-instruct",
    "phi-3-mini-128k-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "与 Phi-3-mini 模型相同，但支持更大上下文窗口，适用于 RAG 或少样本提示。",
    "zh-TW": "與 Phi-3-mini 相同的模型，具備更大的上下文視窗，適用於 RAG 或少量示例提示。",
    "ja-JP": "Phi-3-miniモデルに、RAGやfew-shotプロンプト向けの大きなコンテキストウィンドウを追加したバージョンです。",
    "ru-RU": "Та же модель Phi-3-mini с увеличенным окном контекста для RAG или few-shot подсказок."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-3-mini instruct (128k)"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-3-mini-4k-instruct",
   "model_name": "Phi-3-mini-4k-instruct",
   "display_name": "Phi-3-mini instruct (4k)",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     },
     "provider_model_id": "phi-3-mini-4k-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     },
     "provider_model_id": "phi-3-mini-4k-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-3-mini-4k-instruct"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-04-23",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 4096,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-3-mini-4k-instruct",
    "phi-3-mini-4k-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Phi-3 系列中最小的成员，优化了质量与低延迟表现。",
    "zh-TW": "Phi-3 系列中最小的成員，針對品質與低延遲進行最佳化。",
    "ja-JP": "Phi-3ファミリーで最小のモデルで、品質と低レイテンシに最適化されています。",
    "ru-RU": "Наименьшая модель в семействе Phi-3, оптимизированная для качества и низкой задержки."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-3-mini instruct (4k)"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-3-small-128k-instruct",
   "model_name": "Phi-3-small-128k-instruct",
   "display_name": "Phi-3-small instruct (128k)",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "phi-3-small-128k-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "phi-3-small-128k-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-3-small-128k-instruct"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-04-23",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-3-small-128k-instruct",
    "phi-3-small-128k-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "与 Phi-3-small 模型相同，但支持更大上下文窗口，适用于 RAG 或少样本提示。",
    "zh-TW": "與 Phi-3-small 相同的模型，具備更大的上下文視窗，適用於 RAG 或少量示例提示。",
    "ja-JP": "Phi-3-smallモデルに、RAGやfew-shotプロンプト向けの大きなコンテキストウィンドウを追加したバージョンです。",
    "ru-RU": "Та же модель Phi-3-small с увеличенным окном контекста для RAG или few-shot подсказок."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-3-small instruct (128k)"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-3-small-8k-instruct",
   "model_name": "Phi-3-small-8k-instruct",
   "display_name": "Phi-3-small instruct (8k)",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "phi-3-small-8k-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "phi-3-small-8k-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-3-small-8k-instruct"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-04-23",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 8192,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-3-small-8k-instruct",
    "phi-3-small-8k-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "一款拥有 70 亿参数的模型，质量优于 Phi-3-mini，专注于高质量、推理密集型数据。",
    "zh-TW": "一個擁有 70 億參數的模型，品質優於 Phi-3-mini，專注於高品質、需推理的資料。",
    "ja-JP": "Phi-3-miniよりも高品質で、推論重視のデータに特化した70億パラメータのモデルです。",
    "ru-RU": "Модель с 7B параметрами, обеспечивающая более высокое качество, чем Phi-3-mini, с акцентом на данные, требующие глубокого рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-3-small instruct (8k)"
    }
   ]
  },
  {
   "slug": "microsoft/phi-3-vision-128k-instruct",
   "model_name": "phi-3-vision-128k-instruct",
   "display_name": "Phi 3.5 Vision Instruct",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/phi-3-vision-128k-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "accounts/fireworks/models/phi-3-vision-128k-instruct"
    }
   ],
   "max_input_tokens": 32064,
   "max_output_tokens": 32064,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2024-03",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/phi-3-vision-128k-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Phi-3-Vision-128K-Instruct 是一个轻量级、先进的开源多模态模型，基于合成数据和精选的公共网络数据集构建，专注于高质量、推理密集型的文本与视觉数据。该模型属于 Phi-3 系列，支持 128K 上下文长度（以 token 计）。通过监督微调和偏好优化等严格增强过程，确保指令遵循的准确性和强大的安全性。",
    "zh-TW": "Phi-3-Vision-128K-Instruct 是一款輕量級、先進的開源多模態模型，基於合成資料與精選公開網路資料集訓練，專注於高品質、推理密集的文字與視覺資料。屬於 Phi-3 系列，支援 128K 的上下文長度（以 token 計）。模型經過嚴格優化，包括監督式微調與偏好調整，確保精確的指令遵循與強化的安全性。",
    "ja-JP": "Phi-3-Vision-128K-Instructは、合成データと厳選された公開Webデータセットを用いて構築された軽量かつ最先端のオープンマルチモーダルモデルです。高品質で推論を要するテキストおよび視覚データに焦点を当てています。Phi-3ファミリーに属し、128Kトークンのコンテキスト長をサポートするマルチモーダルバージョンです。正確な命令追従と高い安全性を確保するため、教師ありファインチューニングや直接的な好み最適化などの強化が施されています。",
    "ru-RU": "Phi-3-Vision-128K-Instruct — это легковесная, передовая открытая мультимодальная модель, построенная на синтетических данных и отобранных общедоступных веб-источниках, с акцентом на качественные данные, требующие рассуждений, в области текста и визуальной информации. Принадлежит к семейству Phi-3 и поддерживает мультимодальность с контекстом до 128K токенов. Модель проходит тщательную донастройку, включая обучение с учителем и оптимизацию предпочтений, чтобы обеспечить точное следование инструкциям и высокий уровень безопасности."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi 3.5 Vision Instruct"
    }
   ]
  },
  {
   "slug": "microsoft/phi-3.5-mini-128k-instruct",
   "model_name": "phi-3.5-mini-128k-instruct",
   "display_name": "phi-3.5-mini-128k-instruct",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "microsoft/phi-3.5-mini-128k-instruct"
    }
   ],
   "intro": "Phi-3.5 models are lightweight, state-of-the-art open models. These models were trained with Phi-3 datasets that include both synthetic data and the filtered, publicly available websites data, with a focus on high quality and reasoning-dense properties. Phi-3.5 Mini uses 3.8B parameters, and is a dense decoder-only transformer model using the same tokenizer as Phi-3 Mini.",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-3.5-mini-128k-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "phi-3.5-mini-128k-instruct"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-3.5-mini-instruct",
   "model_name": "Phi-3.5-mini-instruct",
   "display_name": "Phi-3.5-mini instruct (128k)",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     },
     "provider_model_id": "phi-3.5-mini-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     },
     "provider_model_id": "phi-3.5-mini-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-3.5-mini-instruct"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-08-20",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-3.5-mini-instruct",
    "phi-3.5-mini-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Phi-3-mini 模型的更新版本。",
    "zh-TW": "Phi-3-mini 模型的更新版本。",
    "ja-JP": "Phi-3-miniモデルのアップデート版です。",
    "ru-RU": "Обновлённая версия модели Phi-3-mini."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-3.5-mini instruct (128k)"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-3.5-MoE-instruct",
   "model_name": "Phi-3.5-MoE-instruct",
   "display_name": "Phi-3.5-MoE instruct (128k)",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.64"
      }
     },
     "provider_model_id": "phi-3.5-moe-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.64"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.64"
      }
     },
     "provider_model_id": "phi-3.5-moe-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-3.5-moe-instruct"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2024-08-20",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-3.5-moe-instruct",
    "phi-3.5-moe-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-3.5-MoE instruct (128k)"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-3.5-vision-instruct",
   "model_name": "Phi-3.5-vision-instruct",
   "display_name": "Phi-3.5-vision instruct (128k)",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-3.5-vision-instruct"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2024-08-20",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/phi-3/",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-3.5-vision-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Phi-3-vision 模型的更新版本。",
    "zh-TW": "Phi-3-vision 模型的更新版本。",
    "ja-JP": "Phi-3-vision モデルの更新版。",
    "ru-RU": "Обновлённая версия модели Phi-3-vision."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-3.5-vision instruct (128k)"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-4",
   "model_name": "Phi-4",
   "display_name": "Phi-4",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "phi-4"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "phi-4"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "phi-4"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-4"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "microsoft/phi-4"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "microsoft/phi-4"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "microsoft/phi-4"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "deepinfra/microsoft/phi-4"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "deepinfra/microsoft/phi-4"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2024-12-11",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 16000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://techcommunity.microsoft.com/blog/machinelearningblog/affordable-innovation-unveiling-the-pricing-of-phi-3-slms-on-models-as-a-service/4156495",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/microsoft/phi-4",
    "microsoft/phi-4",
    "phi-4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-4"
    }
   ]
  },
  {
   "slug": "microsoft/phi-4-mini",
   "model_name": "phi-4-mini",
   "display_name": "Phi-4-mini",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-12-11",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-4-mini"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-4-mini-instruct",
   "model_name": "Phi-4-mini-instruct",
   "display_name": "Phi-4-mini-instruct",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "phi-4-mini-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-4-mini-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "microsoft/phi-4-mini-instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "phi-4-mini-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-4-mini-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "microsoft/phi-4-mini-instruct"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "microsoft/Phi-4-mini-instruct"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-12-11",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/Phi-4-mini-instruct",
    "microsoft/phi-4-mini-instruct",
    "phi-4-mini-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-4-mini-instruct"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-4-mini-reasoning",
   "model_name": "Phi-4-mini-reasoning",
   "display_name": "Phi-4-mini-reasoning",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "phi-4-mini-reasoning"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "phi-4-mini-reasoning"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-4-mini-reasoning"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-12-11",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-4-mini-reasoning",
    "phi-4-mini-reasoning"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-4-mini-reasoning"
    }
   ]
  },
  {
   "slug": "microsoft/phi-4-multimodal",
   "model_name": "phi-4-multimodal",
   "display_name": "Phi-4-multimodal",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2024-12-11",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-4-multimodal"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-4-multimodal-instruct",
   "model_name": "Phi-4-multimodal-instruct",
   "display_name": "Phi-4-multimodal-instruct",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "phi-4-multimodal-instruct"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     }
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.47"
      }
     },
     "provider_model_id": "microsoft/Phi-4-multimodal-instruct"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-4-multimodal-instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "phi-4-multimodal-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-4-multimodal-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "microsoft/phi-4-multimodal-instruct"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2024-12-11",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "open_weights": true
   },
   "docs_url": "https://techcommunity.microsoft.com/blog/Azure-AI-Services-blog/announcing-new-phi-pricing-empowering-your-business-with-small-language-models/4395112",
   "model_type": "vision_understanding",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/Phi-4-multimodal-instruct",
    "microsoft/phi-4-multimodal-instruct",
    "phi-4-multimodal-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-4-multimodal-instruct"
    }
   ]
  },
  {
   "slug": "microsoft/Phi-4-reasoning",
   "model_name": "Phi-4-reasoning",
   "display_name": "Phi-4-Reasoning",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "phi-4-reasoning"
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "phi-4-reasoning"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "microsoft/phi-4-reasoning"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2024-12-11",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/phi-4-reasoning",
    "phi-4-reasoning"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-4-Reasoning"
    }
   ]
  },
  {
   "slug": "microsoft/phi-4-reasoning-plus",
   "model_name": "phi-4-reasoning-plus",
   "display_name": "Phi-4-reasoning-plus",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     }
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2024-12-11",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "phi",
   "capabilities": {
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Phi-4-reasoning-plus"
    }
   ]
  },
  {
   "slug": "microsoft/WizardCoder-Python-34B-V1.0",
   "model_name": "WizardCoder-Python-34B-V1.0",
   "display_name": "WizardLM/WizardCoder-Python-34B-V1.0",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "WizardLM/WizardCoder-Python-34B-V1.0"
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "WizardLM/WizardCoder-Python-34B-V1.0"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "WizardLM/WizardCoder-Python-34B-V1.0"
    }
   ]
  },
  {
   "slug": "microsoft/WizardLM-13B-V1.2",
   "model_name": "WizardLM-13B-V1.2",
   "display_name": "WizardLM-13B-V1.2",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "WizardLM/WizardLM-13B-V1.2"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "WizardLM/WizardLM-13B-V1.2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "WizardLM-13B-V1.2"
    }
   ]
  },
  {
   "slug": "microsoft/wizardlm-2-7b",
   "model_name": "wizardlm-2-7b",
   "display_name": "wizardlm-2-7b",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "microsoft/wizardlm-2-7b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "microsoft/wizardlm-2-7b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "wizardlm-2-7b"
    }
   ]
  },
  {
   "slug": "microsoft/WizardLM-2-8x22B",
   "model_name": "WizardLM-2-8x22B",
   "display_name": "Wizardlm 2 8x22B",
   "vendor": "microsoft",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "provider_model_id": "wizardlm-2-8x22b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "provider_model_id": "microsoft/WizardLM-2-8x22B"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "provider_model_id": "alpindale/WizardLM-2-8x22B"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "provider_model_id": "microsoft/wizardlm-2-8x22b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "microsoft/wizardlm-2-8x22b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "provider_model_id": "wizardlm-2-8x22b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "provider_model_id": "microsoft/wizardlm-2-8x22b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "provider_model_id": "microsoft/wizardlm-2-8x22b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "provider_model_id": "novita/microsoft/wizardlm-2-8x22b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "provider_model_id": "deepinfra/microsoft/WizardLM-2-8x22B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "microsoft/WizardLM-2-8x22B"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2024-04-24",
   "max_input_tokens": 65535,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2024-04",
   "family": "gpt",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alpindale/WizardLM-2-8x22B",
    "deepinfra/microsoft/WizardLM-2-8x22B",
    "microsoft/WizardLM-2-8x22B",
    "microsoft/wizardlm-2-8x22b",
    "microsoft/wizardlm-2-8x22b:nitro",
    "novita/microsoft/wizardlm-2-8x22b",
    "wizardlm-2-8x22b"
   ],
   "intro_i18n": {
    "zh-CN": "WizardLM 2 是微软 AI 推出的语言模型，擅长复杂对话、多语言任务、推理和助手应用。",
    "zh-TW": "WizardLM 2 是 Microsoft AI 推出的語言模型，擅長處理複雜對話、多語言任務、推理與助理應用。",
    "ja-JP": "WizardLM 2 は Microsoft AI による言語モデルで、複雑な対話、多言語タスク、推論、アシスタントに優れています。",
    "ru-RU": "WizardLM 2 — языковая модель от Microsoft AI, превосходно справляющаяся со сложными диалогами, многоязычными задачами, рассуждением и задачами помощников."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wizardlm 2 8x22B"
    }
   ]
  },
  {
   "slug": "minimax/alicloud-minimax-m2.5",
   "model_name": "alicloud-minimax-m2.5",
   "display_name": "alicloud-minimax-m2.5",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2876"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1504"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05752"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "alicloud-minimax-m2.5"
    }
   ]
  },
  {
   "slug": "minimax/cc-MiniMax-M2",
   "model_name": "cc-MiniMax-M2",
   "display_name": "cc-MiniMax-M2",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-MiniMax-M2"
    }
   ]
  },
  {
   "slug": "minimax/cc-minimax-m2.1",
   "model_name": "cc-minimax-m2.1",
   "display_name": "cc-minimax-m2.1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-minimax-m2.1"
    }
   ]
  },
  {
   "slug": "minimax/cc-minimax-m2.5",
   "model_name": "cc-minimax-m2.5",
   "display_name": "cc-minimax-m2.5",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-minimax-m2.5"
    }
   ]
  },
  {
   "slug": "minimax/cc-minimax-m2.5-highspeed",
   "model_name": "cc-minimax-m2.5-highspeed",
   "display_name": "cc-minimax-m2.5-highspeed",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-minimax-m2.5-highspeed"
    }
   ]
  },
  {
   "slug": "minimax/cc-minimax-m2.7",
   "model_name": "cc-minimax-m2.7",
   "display_name": "cc-minimax-m2.7",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-minimax-m2.7"
    }
   ]
  },
  {
   "slug": "minimax/cc-minimax-m2.7-highspeed",
   "model_name": "cc-minimax-m2.7-highspeed",
   "display_name": "cc-minimax-m2.7-highspeed",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-minimax-m2.7-highspeed"
    }
   ]
  },
  {
   "slug": "minimax/cc-minimax-m3",
   "model_name": "cc-minimax-m3",
   "display_name": "cc-minimax-m3",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-minimax-m3"
    }
   ]
  },
  {
   "slug": "minimax/chat-completion/models/MiniMax-M2_5-high-throughput",
   "model_name": "chat-completion/models/MiniMax-M2_5-high-throughput",
   "display_name": "MiniMax-M2.5 High Throughput",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput"
    }
   ],
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "released_at": "2026-02-12",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax-M2.5 High Throughput"
    }
   ]
  },
  {
   "slug": "minimax/coding-minimax-m2",
   "model_name": "coding-minimax-m2",
   "display_name": "coding-minimax-m2",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 204800,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-minimax-m2"
    }
   ]
  },
  {
   "slug": "minimax/coding-minimax-m2.1",
   "model_name": "coding-minimax-m2.1",
   "display_name": "coding-minimax-m2.1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 204800,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-minimax-m2.1"
    }
   ]
  },
  {
   "slug": "minimax/coding-minimax-m2.5",
   "model_name": "coding-minimax-m2.5",
   "display_name": "coding-minimax-m2.5",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 204800,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-minimax-m2.5"
    }
   ]
  },
  {
   "slug": "minimax/coding-minimax-m2.5-highspeed",
   "model_name": "coding-minimax-m2.5-highspeed",
   "display_name": "coding-minimax-m2.5-highspeed",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 204800,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-minimax-m2.5-highspeed"
    }
   ]
  },
  {
   "slug": "minimax/coding-minimax-m2.7-free",
   "model_name": "coding-minimax-m2.7-free",
   "display_name": "Coding MiniMax M2.7",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "coding-minimax-m2.7"
    }
   ],
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "released_at": "2026-03-18",
   "max_input_tokens": 204800,
   "max_output_tokens": 128100,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "coding-minimax-m2.7"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding MiniMax M2.7"
    }
   ]
  },
  {
   "slug": "minimax/coding-minimax-m2.7-highspeed",
   "model_name": "coding-minimax-m2.7-highspeed",
   "display_name": "Coding MiniMax M2.7 Highspeed",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "intro": "High-speed MiniMax model for low-latency coding and agent workflows",
   "released_at": "2026-03-18",
   "max_input_tokens": 204800,
   "max_output_tokens": 128100,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding MiniMax M2.7 Highspeed"
    }
   ]
  },
  {
   "slug": "minimax/coding-minimax-m3",
   "model_name": "coding-minimax-m3",
   "display_name": "coding-minimax-m3",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 204800,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-minimax-m3"
    }
   ]
  },
  {
   "slug": "minimax/fireworks/models/minimax-m2p5",
   "model_name": "fireworks/models/minimax-m2p5",
   "display_name": "MiniMax-M2.5",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "accounts/fireworks/models/minimax-m2p5"
    }
   ],
   "released_at": "2026-02-12",
   "max_input_tokens": 196608,
   "max_output_tokens": 196608,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/minimax-m2p5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax-M2.5"
    }
   ]
  },
  {
   "slug": "minimax/hailuo-02",
   "model_name": "hailuo-02",
   "display_name": "hailuo-02",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.49"
      }
     },
     "provider_model_id": "minimax/hailuo-02"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax/hailuo-02"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "hailuo-02"
    }
   ]
  },
  {
   "slug": "minimax/image-01",
   "model_name": "image-01",
   "display_name": "Image 01",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.003676"
      }
     }
    }
   ],
   "released_at": "2025-02-28",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "一款全新图像生成模型，细节表现出色，支持文本生成图像与图像转图像。",
    "zh-TW": "一款全新圖像生成模型，具備精細細節，支援文字轉圖像與圖像轉圖像功能。",
    "ja-JP": "細部まで表現可能な新しい画像生成モデルで、テキストから画像、画像から画像の生成に対応しています。",
    "ru-RU": "Новая модель генерации изображений с высокой детализацией, поддерживает генерацию по тексту и по изображению."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Image 01"
    }
   ]
  },
  {
   "slug": "minimax/image-01-live",
   "model_name": "image-01-live",
   "display_name": "Image 01 Live",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.003676"
      }
     }
    }
   ],
   "released_at": "2025-02-28",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "一款细节精致的图像生成模型，支持文本生成图像与可控风格预设。",
    "zh-TW": "一款具備精細細節的圖像生成模型，支援文字轉圖像與可控風格預設。",
    "ja-JP": "細部まで表現可能な画像生成モデルで、テキストから画像生成およびスタイルの制御プリセットに対応しています。",
    "ru-RU": "Модель генерации изображений с высокой детализацией, поддерживает генерацию по тексту и управляемые стили."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Image 01 Live"
    }
   ]
  },
  {
   "slug": "minimax/M2-her",
   "model_name": "M2-her",
   "display_name": "MiniMax M2-her",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     }
    }
   ],
   "released_at": "2026-01-23",
   "max_input_tokens": 65536,
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "一个专为角色扮演和多轮对话设计的文本对话模型，支持角色定制和情感表达。",
    "zh-TW": "一款專為角色扮演和多輪對話設計的文本對話模型，支持角色定制和情感表達。",
    "ja-JP": "ロールプレイやマルチターン会話のために設計されたテキスト対話モデルで、キャラクターのカスタマイズや感情表現が可能です。",
    "ru-RU": "Модель текстового диалога, разработанная для ролевых игр и многоходовых разговоров, с возможностью настройки персонажей и выражения эмоций."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2-her"
    }
   ]
  },
  {
   "slug": "minimax/minimax-01",
   "model_name": "minimax-01",
   "display_name": "MiniMax: MiniMax-01",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "minimax/minimax-01"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1394"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1219999999999999"
      }
     },
     "provider_model_id": "minimax/minimax-01"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "minimax/minimax-01"
    }
   ],
   "intro": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
   "released_at": "2025-01-15",
   "max_input_tokens": 1000192,
   "max_output_tokens": 1000192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-03",
   "family": "minimax",
   "deprecated": true,
   "model_type": "vision_understanding",
   "parameters": {
    "supported": [
     "max_tokens",
     "temperature",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax/minimax-01"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax: MiniMax-01"
    }
   ]
  },
  {
   "slug": "minimax/minimax-abab6-5s-chat",
   "model_name": "minimax-abab6-5s-chat",
   "display_name": "abab6.5s-chat",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     }
    }
   ],
   "released_at": "2024-07-24",
   "max_input_tokens": 245000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "abab6.5s-chat"
    }
   ]
  },
  {
   "slug": "minimax/minimax-abab7-chat-preview",
   "model_name": "minimax-abab7-chat-preview",
   "display_name": "abab7-chat-preview",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    }
   ],
   "released_at": "2025-04-05",
   "max_input_tokens": 245000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "abab7-chat-preview"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-Hailuo-02",
   "model_name": "MiniMax-Hailuo-02",
   "display_name": "MiniMax Hailuo 02",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.088235"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     },
     "provider_model_id": "minimax-hailuo-02"
    }
   ],
   "released_at": "2025-06-18",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax-hailuo-02"
   ],
   "intro_i18n": {
    "zh-CN": "下一代视频生成模型MiniMax Hailuo 02正式发布，支持1080P分辨率和10秒视频生成。",
    "zh-TW": "下一代影像生成模型MiniMax Hailuo 02正式發布，支持1080P解析度及10秒影像生成。",
    "ja-JP": "次世代ビデオ生成モデル「MiniMax Hailuo 02」が正式リリースされ、1080P解像度と10秒間のビデオ生成をサポート。",
    "ru-RU": "Модель генерации видео следующего поколения MiniMax Hailuo 02 официально выпущена, поддерживает разрешение 1080P и генерацию видео длиной до 10 секунд."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax Hailuo 02"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-Hailuo-2.3",
   "model_name": "MiniMax-Hailuo-2.3",
   "display_name": "MiniMax Hailuo 2.3",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.294118"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     },
     "provider_model_id": "minimax-hailuo-2.3"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     }
    }
   ],
   "released_at": "2025-10-28",
   "model_type": "video_generation",
   "capabilities": {
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax-hailuo-2.3"
   ],
   "intro_i18n": {
    "zh-CN": "全新视频生成模型，在身体动作、物理真实感和指令遵循性方面全面升级。",
    "zh-TW": "全新影像生成模型，全面升級身體動作、物理真實性及指令遵循性。",
    "ja-JP": "身体動作、物理的リアリズム、指示追従性において全面的にアップグレードされた新しいビデオ生成モデル。",
    "ru-RU": "Совершенно новая модель генерации видео с комплексными улучшениями в движении тела, физическом реализме и следовании инструкциям."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax Hailuo 2.3"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-Hailuo-2.3-Fast",
   "model_name": "MiniMax-Hailuo-2.3-Fast",
   "display_name": "MiniMax Hailuo 2.3 Fast",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.198529"
      }
     }
    }
   ],
   "released_at": "2025-10-28",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "全新视频生成模型，在身体动作、物理真实感和指令遵循性方面全面升级。",
    "zh-TW": "全新影像生成模型，全面升級身體動作、物理真實性及指令遵循性。",
    "ja-JP": "身体動作、物理的リアリズム、指示追従性において全面的にアップグレードされた新しいビデオ生成モデル。",
    "ru-RU": "Совершенно новая модель генерации видео с комплексными улучшениями в движении тела, физическом реализме и следовании инструкциям."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax Hailuo 2.3 Fast"
    }
   ]
  },
  {
   "slug": "minimax/minimax-latest",
   "model_name": "minimax-latest",
   "display_name": "MiniMax Latest",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax/minimax-latest"
    }
   ],
   "intro": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
   "released_at": "2026-05-03",
   "max_input_tokens": 512000,
   "max_output_tokens": 80000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax/minimax-latest"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax Latest"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M1",
   "model_name": "MiniMax-M1",
   "display_name": "MiniMax M1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.254"
      }
     },
     "provider_model_id": "minimax-m1"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m1"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m1"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "minimax/minimax-m1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1394"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3328"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "minimax/minimax-m1",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "3.25"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.31884"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m1"
    }
   ],
   "released_at": "2025-06-16",
   "max_input_tokens": 1000192,
   "max_output_tokens": 40000,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "knowledge_cutoff": "2024-06",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax-m1",
    "minimax-m1:extended",
    "minimax/minimax-m1"
   ],
   "intro_i18n": {
    "zh-CN": "一款全新自研推理模型，支持 80K 思维链和 100 万输入，性能媲美全球顶尖模型。",
    "zh-TW": "一款內部開發的推理模型，具備 80K 思路鏈與 100 萬輸入，效能媲美全球頂尖模型。",
    "ja-JP": "80Kの思考連鎖と1Mの入力を備えた新しい社内推論モデルで、世界トップクラスのモデルに匹敵する性能を発揮します。",
    "ru-RU": "Новая внутренняя модель рассуждений с поддержкой 80K цепочек размышлений и 1M входных токенов, обеспечивающая производительность на уровне ведущих мировых моделей."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M1"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M1-80k",
   "model_name": "MiniMax-M1-80k",
   "display_name": "MiniMax M1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M1-80k"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "minimax-m1-80k"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M1-80k"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "minimaxai/minimax-m1-80k"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6052"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4225000000000003"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M1-80k"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "minimax-m1-80k"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "minimaxai/minimax-m1-80k"
    }
   ],
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "released_at": "2025-06-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 40000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiniMaxAI/MiniMax-M1-80k",
    "accounts/fireworks/models/minimax-m1-80k",
    "minimax-m1-80k",
    "minimaxai/minimax-m1-80k"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M1"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2",
   "model_name": "MiniMax-M2",
   "display_name": "MiniMax-M2",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax-m2"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      }
     },
     "provider_model_id": "minimax-m2"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.288"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.152"
      }
     },
     "provider_model_id": "minimax-m2"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "minimax-m2"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.57"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.055"
      }
     },
     "provider_model_id": "minimax-m2"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.254"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.02"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029"
      }
     },
     "provider_model_id": "minimax-m2"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimaxai/minimax-m2"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.255"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax-m2"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m2"
    },
    {
     "provider": "minimax-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "minimax-cn-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "minimax-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.53"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax-m2"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.255"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.02"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "minimax/minimax-m2"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.303"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2121"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0303"
      }
     },
     "provider_model_id": "minimax-m2"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     },
     "provider_model_id": "minimax/minimax-m2"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimaxi/MiniMax-M2"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     },
     "provider_model_id": "hf:MiniMaxAI/MiniMax-M2"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.254"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.02"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.127"
      }
     },
     "provider_model_id": "deepinfra/MiniMaxAI/MiniMax-M2"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "minimax/minimax-m2"
    }
   ],
   "intro": "Efficient open MiniMax model built for coding agents and tool-heavy workflows",
   "released_at": "2025-10-27",
   "max_input_tokens": 196608,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "parallel_function_calling": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2024-10",
   "deprecated": true,
   "status": "deprecated",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiniMaxAI/MiniMax-M2",
    "accounts/fireworks/models/minimax-m2",
    "deepinfra/MiniMaxAI/MiniMax-M2",
    "hf:MiniMaxAI/MiniMax-M2",
    "minimax-m2",
    "minimax/minimax-m2",
    "minimaxai/minimax-m2",
    "minimaxi/MiniMax-M2"
   ],
   "intro_i18n": {
    "zh-CN": "MiniMax M2：上一代模型。",
    "zh-TW": "MiniMax M2：上一代模型。",
    "ja-JP": "MiniMax M2: 前世代モデル。",
    "ru-RU": "MiniMax M2: Модель предыдущего поколения."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2-her",
   "model_name": "minimax-m2-her",
   "display_name": "MiniMax: MiniMax M2-her",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2-her"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.30200000000000005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2069999999999999"
      }
     },
     "provider_model_id": "minimax/minimax-m2-her"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2-her"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "minimax/minimax-m2-her"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "minimax/minimax-m2-her"
    }
   ],
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "released_at": "2026-01-23",
   "max_input_tokens": 65536,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "family": "minimax",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "max_tokens",
     "temperature",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax/minimax-m2-her"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax: MiniMax M2-her"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2-maas",
   "model_name": "minimax-m2-maas",
   "display_name": "minimax-m2-maas",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimaxai/minimax-m2-maas",
     "region": "global"
    }
   ],
   "max_input_tokens": 196608,
   "max_output_tokens": 196608,
   "modalities": {
    "input": [
     "text",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimaxai/minimax-m2-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "minimax-m2-maas"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2-Stable",
   "model_name": "MiniMax-M2-Stable",
   "display_name": "MiniMax M2 Stable",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.030882"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.386029"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     }
    }
   ],
   "released_at": "2025-10-27",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "专为高效编程与智能体工作流打造，具备更高并发能力，适用于商业场景。",
    "zh-TW": "專為高效編碼與代理流程設計，具備更高併發能力，適用於商業應用。",
    "ja-JP": "効率的なコーディングとエージェントワークフローのために設計され、商用利用における高い同時実行性を実現します。",
    "ru-RU": "Создана для эффективного программирования и работы агентов, с повышенной параллельностью для коммерческого использования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2 Stable"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.1",
   "model_name": "MiniMax-M2.1",
   "display_name": "MiniMax-M2.1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m2-1"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "minimax-m2.1"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m2-1"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "minimax-m2.1"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.34"
      }
     },
     "provider_model_id": "minimax-m2.1"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0290000007"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.1"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0299999997"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    },
    {
     "provider": "friendli",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.1"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.1"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     },
     "provider_model_id": "minimax-m2.1"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "minimax-m2.1"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.1"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    },
    {
     "provider": "minimax-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "minimax-cn-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "minimax-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "moark",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.4"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.1"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax-m2.1"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "minimax-m2.1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.303"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2121"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0303"
      }
     },
     "provider_model_id": "novita/minimax-m2.1"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.1"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     },
     "provider_model_id": "hf:MiniMaxAI/MiniMax-M2.1"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1"
    }
   ],
   "intro": "Earlier MiniMax agent model for practical coding and productivity tasks",
   "released_at": "2025-12-23",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "parallel_function_calling": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2024-10",
   "deprecated": true,
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 1024
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiniMaxAI/MiniMax-M2.1",
    "Pro/MiniMaxAI/MiniMax-M2.1",
    "hf:MiniMaxAI/MiniMax-M2.1",
    "minimax-m2-1",
    "minimax-m2.1",
    "minimax-m2.1-free",
    "minimax/minimax-m2.1",
    "novita/minimax-m2.1"
   ],
   "intro_i18n": {
    "zh-CN": "MiniMax-M2.1 是 MiniMax 推出的旗舰开源大模型，专注于解决复杂的现实世界任务。其核心优势在于多语言编程能力以及作为智能体解决复杂任务的能力。",
    "zh-TW": "MiniMax-M2.1 是 MiniMax 推出的旗艦開源大型模型，專注於解決複雜的真實世界任務。其核心優勢在於多語言程式設計能力與作為智能代理執行複雜任務的能力。",
    "ja-JP": "MiniMax-M2.1は、MiniMaxが開発したフラッグシップのオープンソース大規模モデルで、複雑な現実世界のタスク解決に特化しています。多言語プログラミング能力とエージェントとしての高度なタスク処理能力が主な強みです。",
    "ru-RU": "MiniMax-M2.1 — это флагманская модель с открытым исходным кодом от MiniMax, ориентированная на решение сложных задач из реального мира. Её ключевые преимущества — поддержка многозадачного программирования и способность выступать в роли интеллектуального агента."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.1-highspeed",
   "model_name": "MiniMax-M2.1-highspeed",
   "display_name": "MiniMax M2.1 highspeed",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.030882"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.386029"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.617647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.470588"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1-highspeed"
    }
   ],
   "released_at": "2025-12-23",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax/minimax-m2.1-highspeed"
   ],
   "intro_i18n": {
    "zh-CN": "强大的多语言编程能力，全面升级的编程体验。更快、更高效。",
    "zh-TW": "強大的多語言編程能力，全面升級的編程體驗。速度更快，效率更高。",
    "ja-JP": "強力な多言語プログラミング機能を備え、プログラミング体験を包括的に向上。より高速かつ効率的です。",
    "ru-RU": "Мощные многоязычные программные возможности, всесторонне улучшенный опыт программирования. Быстрее и эффективнее."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.1 highspeed"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.1-lightning",
   "model_name": "MiniMax-M2.1-lightning",
   "display_name": "MiniMax-M2.1-lightning",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      }
     },
     "provider_model_id": "minimax-m2.1-lightning"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.1-lightning"
    }
   ],
   "max_input_tokens": 1000000,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "High-speed MiniMax model for low-latency coding and agent workflows",
   "released_at": "2025-12-23",
   "knowledge_cutoff": "2024-10",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax-m2.1-lightning",
    "minimax/minimax-m2.1-lightning"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.1-TEE",
   "model_name": "MiniMax-M2.1-TEE",
   "display_name": "MiniMax M2.1 TEE",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.1-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 196608,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiniMaxAI/MiniMax-M2.1-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.1 TEE"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.5",
   "model_name": "MiniMax-M2.5",
   "display_name": "MiniMax-M2.5",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "models-dev+litellm+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m2-5"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m2-5"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "avian",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.08"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "cloudferro-sherlock",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.027"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "dinference",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m2-5"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax-m2-5"
    },
    {
     "provider": "friendli",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax-m2-5"
    },
    {
     "provider": "hpc-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.030882"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "inceptron",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.225"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1125"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.225"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1125"
      }
     },
     "provider_model_id": "minimax-m2-5"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "minimax-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "minimax-cn-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "minimax-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308975772"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235903088"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.303"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2121"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0303"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.30435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.21739"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepinfra/MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.193"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.238"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "route/minimax-m2.5"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.030882"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.22"
      }
     },
     "provider_model_id": "Pro/MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.030882"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.386029"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     }
    },
    {
     "provider": "tencent-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "minimax-m2.5"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5"
    }
   ],
   "intro": "Prior MiniMax coding model for agent workflows, office edits, and automation",
   "released_at": "2026-02-12",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "parallel_function_calling": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2025-01",
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://openrouter.ai/minimax/minimax-m2.5",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "parallel_tool_calls",
     "presence_penalty",
     "reasoning",
     "reasoning_effort",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    " MiniMaxAI/MiniMax-M2.5",
    "MiniMax/MiniMax-M2.5",
    "MiniMaxAI/MiniMax-M2.5",
    "Pro/MiniMaxAI/MiniMax-M2.5",
    "TEE/minimax-m2.5",
    "deepinfra/MiniMaxAI/MiniMax-M2.5",
    "fireworks/minimax-m2.5",
    "inceptron/minimax-m2.5",
    "minimax-m2-5",
    "minimax-m2.5",
    "minimax-m2.5-free",
    "minimax/minimax-m2.5",
    "minimax/minimax-m2.5:free",
    "minimaxi/MiniMax-M2.5",
    "nebius/minimaxi/minimax-m2.5",
    "route/minimax-m2.5"
   ],
   "intro_i18n": {
    "zh-CN": "MiniMax-M2.5 是 MiniMax 推出的旗舰开源大模型，专注于解决复杂的现实世界任务。其核心优势在于多语言编程能力以及作为 Agent 解决复杂任务的能力。",
    "zh-TW": "MiniMax-M2.5 是 MiniMax 推出的旗艦開源大型模型，專注於解決複雜的現實世界任務。其核心優勢包括多語言編程能力以及作為代理解決複雜任務的能力。",
    "ja-JP": "MiniMax-M2.5は、MiniMaxによるフラッグシップのオープンソース大規模モデルで、複雑な現実世界のタスクを解決することに焦点を当てています。その主な強みは、多言語プログラミング能力とエージェントとして複雑なタスクを解決する能力です。",
    "ru-RU": "MiniMax-M2.5 — это флагманская открытая крупная модель от MiniMax, ориентированная на решение сложных реальных задач. Её основные преимущества — многоязычные программные возможности и способность решать сложные задачи в качестве агента."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.1275",
     "new": "0.1125"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "1.13",
     "new": "1.07"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.255",
     "new": "0.225"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.1275",
     "new": "0.1125"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "1.13",
     "new": "1.07"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.255",
     "new": "0.225"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.236494112",
     "new": "1.235903088"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309123528",
     "new": "0.308975772"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.1245",
     "new": "0.1275"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "1.106",
     "new": "1.13"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.249",
     "new": "0.255"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.1245",
     "new": "0.1275"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "1.106",
     "new": "1.13"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.249",
     "new": "0.255"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.237353096",
     "new": "1.236494112"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309338274",
     "new": "0.309123528"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.238657448",
     "new": "1.237353096"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309664362",
     "new": "0.309338274"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.1275",
     "new": "0.1245"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "1.13",
     "new": "1.106"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.5-fast",
   "model_name": "MiniMax-M2.5-fast",
   "display_name": "MiniMax-M2.5-fast",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5-fast"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-01-20",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 8000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiniMaxAI/MiniMax-M2.5-fast"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax-M2.5-fast"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.5-FP4",
   "model_name": "MiniMax-M2.5-FP4",
   "display_name": "MiniMax-M2.5-FP4",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5-FP4"
    }
   ],
   "max_input_tokens": 192000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiniMaxAI/MiniMax-M2.5-FP4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax-M2.5-FP4"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.5-highspeed",
   "model_name": "MiniMax-M2.5-highspeed",
   "display_name": "MiniMax-M2.5-highspeed",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.8"
      }
     },
     "provider_model_id": "minimax-m2-5-highspeed"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.288"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.152"
      }
     },
     "provider_model_id": "minimax-m2.5-highspeed"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-highspeed"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-highspeed"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax-m2.5-highspeed"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-highspeed"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-highspeed"
    },
    {
     "provider": "minimax-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "minimax-cn-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "minimax-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-highspeed"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-highspeed"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-highspeed"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6087"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.43478"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-highspeed"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "minimaxi/MiniMax-M2.5-highspeed"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.193"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.238"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "route/minimax-m2.5-highspeed"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-highspeed"
    }
   ],
   "intro": "High-speed MiniMax model for low-latency coding and agent workflows",
   "released_at": "2026-02-13",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax-m2-5-highspeed",
    "minimax-m2.5-highspeed",
    "minimax/minimax-m2.5-highspeed",
    "minimaxi/MiniMax-M2.5-highspeed",
    "route/minimax-m2.5-highspeed"
   ],
   "intro_i18n": {
    "zh-CN": "MiniMax M2.5 Highspeed：与M2.5性能相同，但推理速度更快。",
    "zh-TW": "MiniMax M2.5 高速版：與 M2.5 性能相同，但推理速度更快。",
    "ja-JP": "MiniMax M2.5 Highspeed: M2.5と同等の性能で推論速度が向上。",
    "ru-RU": "MiniMax M2.5 Highspeed: Та же производительность, что и у M2.5, но с ускоренным выводом."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.5-lightning",
   "model_name": "MiniMax-M2.5-lightning",
   "display_name": "MiniMax-M2.5-lightning",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-lightning"
    }
   ],
   "max_input_tokens": 1000000,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "High-speed MiniMax model for low-latency coding and agent workflows",
   "released_at": "2026-02-13",
   "knowledge_cutoff": "2025-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax/minimax-m2.5-lightning"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2.5-official",
   "model_name": "minimax-m2.5-official",
   "display_name": "MiniMax M2.5",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m2.5-official"
    }
   ],
   "released_at": "2026-02-12",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax/minimax-m2.5-official"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.5"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.5-TEE",
   "model_name": "MiniMax-M2.5-TEE",
   "display_name": "MiniMax M2.5 TEE",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.5-TEE"
    }
   ],
   "intro": "Prior MiniMax coding model for agent workflows, office edits, and automation",
   "released_at": "2026-02-12",
   "max_input_tokens": 196608,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiniMaxAI/MiniMax-M2.5-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.5 TEE"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2.5@eu-central-1",
   "model_name": "minimax-m2.5@eu-central-1",
   "display_name": "bedrock/minimax-m2.5@eu-central-1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "bedrock/minimax-m2.5@eu-central-1"
    }
   ],
   "released_at": "2026-05-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/minimax-m2.5@eu-central-1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/minimax-m2.5@eu-central-1"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2.5@eu-north-1",
   "model_name": "minimax-m2.5@eu-north-1",
   "display_name": "bedrock/minimax-m2.5@eu-north-1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "bedrock/minimax-m2.5@eu-north-1"
    }
   ],
   "released_at": "2026-05-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/minimax-m2.5@eu-north-1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/minimax-m2.5@eu-north-1"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2.5@eu-south-1",
   "model_name": "minimax-m2.5@eu-south-1",
   "display_name": "bedrock/minimax-m2.5@eu-south-1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "bedrock/minimax-m2.5@eu-south-1"
    }
   ],
   "released_at": "2026-05-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/minimax-m2.5@eu-south-1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/minimax-m2.5@eu-south-1"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2.5@eu-west-1",
   "model_name": "minimax-m2.5@eu-west-1",
   "display_name": "bedrock/minimax-m2.5@eu-west-1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "bedrock/minimax-m2.5@eu-west-1"
    }
   ],
   "released_at": "2026-05-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/minimax-m2.5@eu-west-1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/minimax-m2.5@eu-west-1"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2.5@us-east-1",
   "model_name": "minimax-m2.5@us-east-1",
   "display_name": "bedrock/minimax-m2.5@us-east-1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "bedrock/minimax-m2.5@us-east-1"
    }
   ],
   "released_at": "2026-05-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/minimax-m2.5@us-east-1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/minimax-m2.5@us-east-1"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2.5@us-east-2",
   "model_name": "minimax-m2.5@us-east-2",
   "display_name": "bedrock/minimax-m2.5@us-east-2",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "bedrock/minimax-m2.5@us-east-2"
    }
   ],
   "released_at": "2026-05-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/minimax-m2.5@us-east-2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/minimax-m2.5@us-east-2"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2.5@us-west-2",
   "model_name": "minimax-m2.5@us-west-2",
   "display_name": "bedrock/minimax-m2.5@us-west-2",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "bedrock/minimax-m2.5@us-west-2"
    }
   ],
   "released_at": "2026-05-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/minimax-m2.5@us-west-2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/minimax-m2.5@us-west-2"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.7",
   "model_name": "MiniMax-M2.7",
   "display_name": "MiniMax-M2.7",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m2-7"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "MiniMax/MiniMax-M2.7"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m2-7",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax-m2-7"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.111"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.7"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax-m2-7"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m2-7"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.7"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.061765"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.82"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.7"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.82"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     },
     "provider_model_id": "minimax-m2-7"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "minimax-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "minimax-cn-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "minimax-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308975772"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235903088"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "minimaxai/minimax-m2.7"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.054"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.303"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2121"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0606"
      }
     },
     "provider_model_id": "minimax-m2.7"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.30435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.21739"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "fireworks/minimax-m2.7"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "route/minimax-m2.7"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.061765"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.386029"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235294"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.7"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.7"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3055"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2219"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7"
    }
   ],
   "intro": "Open MiniMax flagship for coding agents, office automation, and complex environments",
   "released_at": "2026-03-18",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2025-01",
   "docs_url": "https://cloud.sambanova.ai/plans/pricing",
   "benchmarks": {
    "intelligence_index": 38.1,
    "coding_index": 52.6,
    "agentic_index": 25.6
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiniMax/MiniMax-M2.7",
    "MiniMaxAI/MiniMax-M2.7",
    "fireworks/minimax-m2.7",
    "minimax-m2-7",
    "minimax-m2.7",
    "minimax/minimax-m2.7",
    "minimaxai/minimax-m2.7",
    "minimaxi/MiniMax-M2.7",
    "novita/minimax/minimax-m2.7",
    "route/minimax-m2.7"
   ],
   "intro_i18n": {
    "zh-CN": "首个具备自进化能力的模型，拥有顶尖的编码与智能体性能（约 60 tps）。",
    "zh-TW": "首個具自我進化能力的模型，具備頂級編碼與智能體效能（約 60 tps）。",
    "ja-JP": "自己進化型モデルの第一弾で、トップクラスのコーディング性能とエージェント能力を備え、約 60 tps の高速性能を発揮します。",
    "ru-RU": "Первая саморазвивающаяся модель с высококлассной производительностью в кодировании и агентных задачах (~60 tps)."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.236494112",
     "new": "1.235903088"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309123528",
     "new": "0.308975772"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.237353096",
     "new": "1.236494112"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309338274",
     "new": "0.309123528"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.43",
     "new": "0.41"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.72",
     "new": "2.64"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.86",
     "new": "0.82"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.43",
     "new": "0.41"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.72",
     "new": "2.64"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.86",
     "new": "0.82"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.238657448",
     "new": "1.237353096"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309664362",
     "new": "0.309338274"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.238910372",
     "new": "1.238657448"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309727593",
     "new": "0.309664362"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.238471808",
     "new": "1.238910372"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309617952",
     "new": "0.309727593"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.23630318",
     "new": "1.238471808"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309075795",
     "new": "0.309617952"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.418",
     "new": "0.43"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.624",
     "new": "2.72"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.7-highspeed",
   "model_name": "MiniMax-M2.7-highspeed",
   "display_name": "MiniMax-M2.7-highspeed",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.8"
      }
     },
     "provider_model_id": "minimax-m2-7-highspeed"
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax-m2-7-highspeed"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-highspeed"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-highspeed"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax-m2.7-highspeed"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-highspeed"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-highspeed"
    },
    {
     "provider": "minimax-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "minimax-cn-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "minimax-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-highspeed"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-highspeed"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-highspeed"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimaxi/MiniMax-M2.7-highspeed"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "route/minimax-m2.7-highspeed"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-highspeed"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-highspeed"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.611"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4439"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0611"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3819"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-highspeed"
    }
   ],
   "intro": "Low-latency M2.7 variant for interactive coding plans and agent loops",
   "released_at": "2026-03-18",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "text_generation",
   "knowledge_cutoff": "2025-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax-m2-7-highspeed",
    "minimax-m2.7-highspeed",
    "minimax/minimax-m2.7-highspeed",
    "minimaxi/MiniMax-M2.7-highspeed",
    "novita/minimax/minimax-m2.7-highspeed",
    "route/minimax-m2.7-highspeed"
   ],
   "intro_i18n": {
    "zh-CN": "MiniMax M2.7 Highspeed：与M2.7性能相同，但推理速度显著提升。",
    "zh-TW": "MiniMax M2.7 高速版：與 M2.7 性能相同，但推理速度顯著提升。",
    "ja-JP": "MiniMax M2.7 Highspeed: M2.7と同等の性能で推論速度が大幅に向上。",
    "ru-RU": "MiniMax M2.7 Highspeed: Та же производительность, что и у M2.7, но с значительно ускоренным выводом."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M2.7-Turbo",
   "model_name": "MiniMax-M2.7-Turbo",
   "display_name": "MiniMax M2.7 Turbo",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M2.7-Turbo"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "minimax/minimax-m2.7-turbo"
    }
   ],
   "intro": "Efficient MiniMax model for quick assistance, coding, and routine automation",
   "released_at": "2026-03-18",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiniMaxAI/MiniMax-M2.7-Turbo",
    "minimax/minimax-m2.7-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.7 Turbo"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m21",
   "model_name": "minimax-m21",
   "display_name": "MiniMax M2.1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 198000,
   "max_output_tokens": 49500,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.1"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m25",
   "model_name": "minimax-m25",
   "display_name": "MiniMax M2.5",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "drun",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.16"
      }
     },
     "provider_model_id": "public/minimax-m25"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    }
   ],
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "released_at": "2025-03-01",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "public/minimax-m25"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.5"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "cache_read",
     "old": "0.04",
     "new": "0.03"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "completion",
     "old": "1.19",
     "new": "0.95"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "prompt",
     "old": "0.34",
     "new": "0.27"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m27",
   "model_name": "minimax-m27",
   "display_name": "MiniMax M2.7",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06875"
      }
     }
    }
   ],
   "intro": "Open MiniMax flagship for coding agents, office automation, and complex environments",
   "released_at": "2026-03-18",
   "max_input_tokens": 198000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.7"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2p1",
   "model_name": "minimax-m2p1",
   "display_name": "MiniMax-M2.1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "accounts/fireworks/models/minimax-m2p1"
    }
   ],
   "docs_url": "https://fireworks.ai/models/fireworks/minimax-m2p1",
   "max_input_tokens": 204800,
   "max_output_tokens": 204800,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true
   },
   "intro": "Built for strong real-world performance across complex, multi-language, and agent-driven workflows. 228B parameter model with robust support for systems, backend, web, mobile, and office-style tasks.",
   "released_at": "2025-12-23",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/minimax-m2p1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax-M2.1"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m2p7",
   "model_name": "minimax-m2p7",
   "display_name": "MiniMax-M2.7",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "accounts/fireworks/models/minimax-m2p7"
    }
   ],
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "released_at": "2026-04-12",
   "max_input_tokens": 196608,
   "max_output_tokens": 196608,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/minimax-m2p7"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax-M2.7"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-M3",
   "model_name": "MiniMax-M3",
   "display_name": "MiniMax-M3",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "models-dev+litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "tracks": [
      {
       "label": ">512000000K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "14",
        "completion": "14",
        "cache_read": "14"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 512000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">512K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 512000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.288"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.152"
      }
     },
     "provider_model_id": "minimax-m3"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "minimax-m3"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.355"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.775"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.089"
      }
     },
     "provider_model_id": "minimax-m3"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M3"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax/minimax-m3"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "accounts/fireworks/models/minimax-m3"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M3"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m3"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "minimax-m3"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax/minimax-m3"
    },
    {
     "provider": "lilac",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "minimaxai/minimax-m3"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "minimax-m3"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "minimax/minimax-m3"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "minimax/minimax-m3"
    },
    {
     "provider": "minimax-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "tracks": [
      {
       "label": ">512K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 512000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "minimax-cn-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "minimax-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.308975772"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.235903088"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax/minimax-m3"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m3"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "minimaxai/minimax-m3"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m3"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m3",
     "tracks": [
      {
       "label": ">512K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 512000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax-m3"
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "minimax-m3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax/minimax-m3"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "minimax/minimax-m3"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.30435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.21739"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06087"
      }
     },
     "provider_model_id": "minimax/minimax-m3"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "fireworks/minimax-m3"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "hf:MiniMaxAI/MiniMax-M3"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "MiniMaxAI/MiniMax-M3"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "minimax/minimax-m3",
     "tracks": [
      {
       "label": ">512K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4",
        "completion": "4",
        "cache_read": "4"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 512000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      }
     }
    },
    {
     "provider": "wafer-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02746152"
      }
     },
     "provider_model_id": "minimax/minimax-m3",
     "tracks": [
      {
       "label": ">512K context",
       "factor": "1",
       "charge_factors": {
        "completion": "0.457692",
        "cache_read": "2",
        "prompt": "0.457692"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 512000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "MiniMax multimodal model for long-context coding, perception, and agent planning",
   "released_at": "2026-06-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2025-01",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "benchmarks": {
    "intelligence_index": 44.4,
    "coding_index": 58.6,
    "agentic_index": 35.4
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiniMaxAI/MiniMax-M3",
    "accounts/fireworks/models/minimax-m3",
    "fireworks/minimax-m3",
    "hf:MiniMaxAI/MiniMax-M3",
    "minimax-m3",
    "minimax-m3-free",
    "minimax/minimax-m3",
    "minimax/minimax-m3:thinking",
    "minimaxai/minimax-m3",
    "minimaxi/minimax-m3",
    "tensorx/minimax-m3"
   ],
   "intro_i18n": {
    "zh-CN": "前沿编码模型，支持原生多模态输入，1M上下文，并具备强大的代理能力。",
    "zh-TW": "前沿的編碼模型，支持原生多模態輸入，具備100萬上下文和強大的代理能力。",
    "ja-JP": "フロンティアコーディングモデル。ネイティブなマルチモーダル入力、1Mコンテキスト、強力なエージェント機能を備えています。",
    "ru-RU": "Модель кодирования Frontier с поддержкой родного мультимодального ввода, контекстом на 1M и мощными агентными возможностями."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.236494112",
     "new": "1.235903088"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309123528",
     "new": "0.308975772"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.237353096",
     "new": "1.236494112"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309338274",
     "new": "0.309123528"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.238657448",
     "new": "1.237353096"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309664362",
     "new": "0.309338274"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.238910372",
     "new": "1.238657448"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309727593",
     "new": "0.309664362"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.238471808",
     "new": "1.238910372"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309617952",
     "new": "0.309727593"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.23630318",
     "new": "1.238471808"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309075795",
     "new": "0.309617952"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.236371388",
     "new": "1.23630318"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.309092847",
     "new": "0.309075795"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m3-el",
   "model_name": "minimax-m3-el",
   "display_name": "MiniMax-M3-EL",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.303"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2121"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0606"
      }
     }
    }
   ],
   "released_at": "2026-06-01",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax-M3-EL"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m3-n",
   "model_name": "minimax-m3-n",
   "display_name": "Minimax-M3-N",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.303"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2121"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0606"
      }
     }
    }
   ],
   "released_at": "2026-06-12",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Minimax-M3-N"
    }
   ]
  },
  {
   "slug": "minimax/minimax-m3-preview",
   "model_name": "minimax-m3-preview",
   "display_name": "MiniMax M3 Preview",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    }
   ],
   "intro": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
   "released_at": "2026-06-12",
   "max_input_tokens": 524288,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax-m3",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M3 Preview"
    }
   ]
  },
  {
   "slug": "minimax/MiniMax-Text-01",
   "model_name": "MiniMax-Text-01",
   "display_name": "MiniMax Text 01",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "minimax",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      }
     },
     "provider_model_id": "minimax-text-01"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.12"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "minimax-text-01"
    }
   ],
   "released_at": "2025-01-15",
   "max_input_tokens": 1000192,
   "max_output_tokens": 40000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "vision": true,
    "image_output": true,
    "pdf_input": true,
    "open_weights": true,
    "prompt_caching": true
   },
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax-text-01"
   ],
   "intro_i18n": {
    "zh-CN": "MiniMax-01 引入超越传统 Transformer 的大规模线性注意力机制，拥有 4560 亿参数，每次激活 459 亿，支持最长 400 万上下文（为 GPT-4o 的 32 倍，Claude-3.5-Sonnet 的 20 倍），性能顶尖。",
    "zh-TW": "MiniMax-01 採用超越傳統 Transformer 的大規模線性注意力機制，擁有 4560 億參數，每次啟用 459 億，支援最多 400 萬字元上下文（為 GPT-4o 的 32 倍，Claude-3.5-Sonnet 的 20 倍），效能頂尖。",
    "ja-JP": "MiniMax-01は、従来のTransformerを超える大規模な線形アテンションを導入し、4560億のパラメータと1パスあたり45.9億のアクティブパラメータを持ちます。最大400万トークンのコンテキストをサポートし（GPT-4oの32倍、Claude-3.5-Sonnetの20倍）、最高水準の性能を実現します。",
    "ru-RU": "MiniMax-01 представляет масштабное линейное внимание, выходящее за рамки классических трансформеров, с 456B параметрами и 45.9B активируемыми за проход. Обеспечивает производительность высшего уровня и поддерживает до 4M токенов контекста (в 32 раза больше GPT-4o, в 20 раз больше Claude-3.5-Sonnet)."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax Text 01"
    }
   ]
  },
  {
   "slug": "minimax/minimax.minimax-m2",
   "model_name": "minimax.minimax-m2",
   "display_name": "MiniMax M2",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.45"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.309"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.236"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.45"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.45"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.309"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.236"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.41"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.45"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "released_at": "2025-10-27",
   "max_input_tokens": 204608,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2"
    }
   ]
  },
  {
   "slug": "minimax/minimax.minimax-m2.1",
   "model_name": "minimax.minimax-m2.1",
   "display_name": "MiniMax M2.1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.309"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.236"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.309"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.236"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "released_at": "2025-12-23",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.1"
    }
   ]
  },
  {
   "slug": "minimax/minimax.minimax-m2.5",
   "model_name": "minimax.minimax-m2.5",
   "display_name": "MiniMax M2.5",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.24"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.24"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "MiniMax model for chat, coding, office work, and agentic tasks",
   "released_at": "2026-03-18",
   "max_input_tokens": 196608,
   "max_output_tokens": 98304,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "minimax",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.5"
    }
   ]
  },
  {
   "slug": "minimax/mm-minimax-m2.7-highspeed",
   "model_name": "mm-minimax-m2.7-highspeed",
   "display_name": "mm-minimax-m2.7-highspeed",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mm-minimax-m2.7-highspeed"
    }
   ]
  },
  {
   "slug": "minimax/mm-minimax-m3",
   "model_name": "mm-minimax-m3",
   "display_name": "mm-minimax-m3",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.288"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.152"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mm-minimax-m3"
    }
   ]
  },
  {
   "slug": "minimax/ppio-minimax-minimax-m2",
   "model_name": "ppio-minimax-minimax-m2",
   "display_name": "minimax/minimax-m2",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 204800,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "minimax/minimax-m2"
    }
   ]
  },
  {
   "slug": "minimax/ppio-minimax-minimax-m2-1",
   "model_name": "ppio-minimax-minimax-m2-1",
   "display_name": "minimax/minimax-m2.1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 204800,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "minimax/minimax-m2.1"
    }
   ]
  },
  {
   "slug": "minimax/sophnet-MiniMax-M2-1",
   "model_name": "sophnet-MiniMax-M2-1",
   "display_name": "sophnet/MiniMax-M2.1",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2026-01-06",
   "max_input_tokens": 196000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/MiniMax-M2.1"
    }
   ]
  },
  {
   "slug": "minimax/speech-2.6-turbo",
   "model_name": "speech-2.6-turbo",
   "display_name": "speech-2.6-turbo",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "30"
      }
     },
     "provider_model_id": "minimax/speech-2.6-turbo"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax/speech-2.6-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "speech-2.6-turbo"
    }
   ]
  },
  {
   "slug": "minimax/speech-2.8-turbo",
   "model_name": "speech-2.8-turbo",
   "display_name": "speech-2.8-turbo",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "30"
      }
     },
     "provider_model_id": "minimax/speech-2.8-turbo"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax/speech-2.8-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "speech-2.8-turbo"
    }
   ]
  },
  {
   "slug": "minimax/video-01-director",
   "model_name": "video-01-director",
   "display_name": "video-01-director",
   "vendor": "minimax",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.28"
      }
     },
     "provider_model_id": "minimax/video-01-director"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "minimax/video-01-director"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "video-01-director"
    }
   ]
  },
  {
   "slug": "mistral/aihubmix-Codestral-2501",
   "model_name": "aihubmix-Codestral-2501",
   "display_name": "aihubmix-Codestral-2501",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Codestral-2501"
    }
   ]
  },
  {
   "slug": "mistral/aihubmix-Mistral-large",
   "model_name": "aihubmix-Mistral-large",
   "display_name": "aihubmix-Mistral-large",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Mistral-large"
    }
   ]
  },
  {
   "slug": "mistral/aihubmix-Mistral-large-2407",
   "model_name": "aihubmix-Mistral-large-2407",
   "display_name": "aihubmix-Mistral-large-2407",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Mistral-large-2407"
    }
   ]
  },
  {
   "slug": "mistral/aihubmix-Mistral-Large-2411",
   "model_name": "aihubmix-Mistral-Large-2411",
   "display_name": "aihubmix-Mistral-Large-2411",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-Mistral-Large-2411"
    }
   ]
  },
  {
   "slug": "mistral/AiHubmix-mistral-medium",
   "model_name": "AiHubmix-mistral-medium",
   "display_name": "AiHubmix-mistral-medium",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AiHubmix-mistral-medium"
    }
   ]
  },
  {
   "slug": "mistral/codestral",
   "model_name": "codestral",
   "display_name": "Codestral",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistral/codestral"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistral/codestral"
    }
   ],
   "intro": "Mistral's cutting-edge language model for coding. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "released_at": "2024-05-29",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 256000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "codestral",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/codestral"
   ],
   "intro_i18n": {
    "zh-CN": "Codestral 是 Mistral AI 推出的首个代码模型，具备强大的代码生成能力。",
    "zh-TW": "Codestral 是 Mistral AI 推出的首款程式模型，具備強大的程式碼生成能力。",
    "ja-JP": "Codestralは、Mistral AIによる初のコードモデルで、強力なコード生成をサポートします。",
    "ru-RU": "Codestral — первая модель для программирования от Mistral AI, обеспечивающая высокое качество генерации кода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Codestral"
    }
   ]
  },
  {
   "slug": "mistral/codestral-2",
   "model_name": "codestral-2",
   "display_name": "codestral-2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistralai/codestral-2",
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistralai/codestral-2",
     "region": "us-central1"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/codestral-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codestral-2"
    }
   ]
  },
  {
   "slug": "mistral/codestral-2@001",
   "model_name": "codestral-2@001",
   "display_name": "codestral-2@001",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistralai/codestral-2@001",
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistralai/codestral-2@001",
     "region": "us-central1"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/codestral-2@001"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codestral-2@001"
    }
   ]
  },
  {
   "slug": "mistral/codestral-2405",
   "model_name": "codestral-2405",
   "display_name": "codestral-2405",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {
    "structured_output": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/codestral-2501",
   "model_name": "codestral-2501",
   "display_name": "Codestral 25.01",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistral-ai/codestral-2501"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistralai/codestral-2501"
    }
   ],
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "intro": "Mistral coding model for code completion, generation, and developer workflows",
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2024-03",
   "max_input_tokens": 32000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "codestral",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-ai/codestral-2501",
    "mistralai/codestral-2501"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Codestral 25.01"
    }
   ]
  },
  {
   "slug": "mistral/codestral-2508",
   "model_name": "codestral-2508",
   "display_name": "codestral-2508",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "mistralai/codestral-2508"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8999999999999999"
      }
     },
     "provider_model_id": "mistralai/codestral-2508"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "mistralai/codestral-2508"
    }
   ],
   "docs_url": "https://mistral.ai/news/codestral-25-08",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.",
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "text",
     "code"
    ]
   },
   "released_at": "2025-07-30",
   "knowledge_cutoff": "2025-03",
   "family": "mistral",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/codestral-2508"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/codestral-embed",
   "model_name": "codestral-embed",
   "display_name": "codestral-embed",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "mistral/codestral-embed"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "mistral/codestral-embed"
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_embedding",
   "capabilities": {},
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "embedding"
    ]
   },
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2025-05-28",
   "max_output_tokens": 1536,
   "family": "codestral-embed",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/codestral-embed"
   ],
   "intro_i18n": {
    "zh-CN": "一款代码嵌入模型，用于嵌入代码库和仓库，支持编程助手。",
    "zh-TW": "一款用於嵌入代碼庫與儲存庫的代碼嵌入模型，支援編碼助手應用。",
    "ja-JP": "コードベースやリポジトリの埋め込みに対応したコード埋め込みモデルで、コーディングアシスタントを支援します。",
    "ru-RU": "Модель для встраивания кода, предназначенная для индексирования кодовых баз и репозиториев в помощь ассистентам по программированию."
   }
  },
  {
   "slug": "mistral/codestral-embed-2505",
   "model_name": "codestral-embed-2505",
   "display_name": "codestral-embed-2505",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "mistralai/codestral-embed-2505"
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_embedding",
   "capabilities": {
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/codestral-embed-2505"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/codestral-latest",
   "model_name": "codestral-latest",
   "display_name": "Codestral",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistral/codestral-latest"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistral/codestral-latest"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistral/codestral-latest"
    }
   ],
   "intro": "Mistral code model for completions, refactors, and developer IDE workflows",
   "released_at": "2024-05-29",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 256000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "codestral",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/codestral-latest"
   ],
   "intro_i18n": {
    "zh-CN": "Codestral 是我们最先进的代码模型；v2（2025年1月）专为低延迟、高频任务（如 FIM、代码修复和测试生成）而设计。",
    "zh-TW": "Codestral 是我們最先進的程式模型；v2（2025 年 1 月）針對低延遲、高頻率任務如 FIM、程式碼修正與測試生成進行優化。",
    "ja-JP": "Codestralは、最も高度なコーディングモデルで、v2（2025年1月）はFIM、コード修正、テスト生成などの低レイテンシ・高頻度タスクに最適化されています。",
    "ru-RU": "Codestral — наша самая продвинутая модель для программирования; версия v2 (январь 2025) оптимизирована для задач с низкой задержкой и высокой частотой, таких как FIM, исправление кода и генерация тестов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/codestral-mamba",
   "model_name": "codestral-mamba",
   "display_name": "codestral-mamba",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "mistralai/codestral-mamba"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/codestral-mamba"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codestral-mamba"
    }
   ]
  },
  {
   "slug": "mistral/codestral-mamba-latest",
   "model_name": "codestral-mamba-latest",
   "display_name": "codestral-mamba-latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/technology/",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/codestral@2405",
   "model_name": "codestral@2405",
   "display_name": "codestral@2405",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codestral@2405"
    }
   ]
  },
  {
   "slug": "mistral/codestral@latest",
   "model_name": "codestral@latest",
   "display_name": "codestral@latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codestral@latest"
    }
   ]
  },
  {
   "slug": "mistral/completion/models/Ministral-3-14B-Reasoning-2512",
   "model_name": "completion/models/Ministral-3-14B-Reasoning-2512",
   "display_name": "Ministral 3 14B Reasoning 2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      }
     },
     "provider_model_id": "mistralai/completion/models/Ministral-3-14B-Reasoning-2512"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/completion/models/Ministral-3-14B-Reasoning-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3 14B Reasoning 2512"
    }
   ]
  },
  {
   "slug": "mistral/completion/models/Ministral-3-3B-Reasoning-2512",
   "model_name": "completion/models/Ministral-3-3B-Reasoning-2512",
   "display_name": "Ministral 3 3B Reasoning 2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.039"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.54825"
      }
     },
     "provider_model_id": "mistralai/completion/models/Ministral-3-3B-Reasoning-2512"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2025-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/completion/models/Ministral-3-3B-Reasoning-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3 3B Reasoning 2512"
    }
   ]
  },
  {
   "slug": "mistral/databricks-mixtral-8x7b-instruct",
   "model_name": "databricks-mixtral-8x7b-instruct",
   "display_name": "databricks-mixtral-8x7b-instruct",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.50001"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.00002"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-mixtral-8x7b-instruct"
    }
   ]
  },
  {
   "slug": "mistral/DeepHermes-3-Mistral-24B-Preview",
   "model_name": "DeepHermes-3-Mistral-24B-Preview",
   "display_name": "DeepHermes-3 Mistral 24B (Preview)",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "NousResearch/DeepHermes-3-Mistral-24B-Preview"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "nousresearch/deephermes-3-mistral-24b-preview"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "NousResearch/DeepHermes-3-Mistral-24B-Preview"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-05-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "family": "nousresearch",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/DeepHermes-3-Mistral-24B-Preview",
    "nousresearch/deephermes-3-mistral-24b-preview"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepHermes-3 Mistral 24B (Preview)"
    }
   ]
  },
  {
   "slug": "mistral/devstral-2",
   "model_name": "devstral-2",
   "display_name": "Devstral 2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/devstral-2"
    }
   ],
   "intro": "Mistral coding agent model for repository tasks and software engineering workflows",
   "released_at": "2025-12-09",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "capabilities": {
    "function_calling": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/devstral-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Devstral 2"
    }
   ]
  },
  {
   "slug": "mistral/devstral-2-123b",
   "model_name": "devstral-2-123b",
   "display_name": "Devstral 2 123B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.41"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.06"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.1"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.41"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.06"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.62"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.1"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral.devstral-2-123b",
     "region": "us-west-2"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4573"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2866"
      }
     }
    }
   ],
   "intro": "Mistral coding agent model for repository tasks and software engineering workflows",
   "released_at": "2026-02-17",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral.devstral-2-123b"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "2.283",
     "new": "2.2866"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "0.4566",
     "new": "0.4573"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "2.2896",
     "new": "2.283"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "0.4579",
     "new": "0.4566"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Devstral 2 123B"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "2.2766",
     "new": "2.2896"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "0.4553",
     "new": "0.4579"
    }
   ]
  },
  {
   "slug": "mistral/devstral-2-123b-instruct-2512",
   "model_name": "devstral-2-123b-instruct-2512",
   "display_name": "Devstral 2 123B Instruct (2512)",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "mistralai/devstral-2-123b-instruct-2512"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "intro": "Mistral's coding-agent model for repository work, terminal tasks, and software fixes",
   "released_at": "2026-01-07",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 256000,
   "max_output_tokens": 16384,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/devstral-2-123b-instruct-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Devstral 2 123B Instruct (2512)"
    }
   ]
  },
  {
   "slug": "mistral/Devstral-2-123B-Instruct-2512-TEE",
   "model_name": "Devstral-2-123B-Instruct-2512-TEE",
   "display_name": "Devstral 2 123B Instruct 2512 TEE",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "mistralai/Devstral-2-123B-Instruct-2512-TEE"
    }
   ],
   "released_at": "2026-01-10",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/Devstral-2-123B-Instruct-2512-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Devstral 2 123B Instruct 2512 TEE"
    }
   ]
  },
  {
   "slug": "mistral/devstral-2:123b",
   "model_name": "devstral-2:123b",
   "display_name": "devstral-2:123b",
   "vendor": "mistral",
   "pricing": [],
   "intro": "Mistral coding agent model for repository tasks and software engineering workflows",
   "released_at": "2025-12-09",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Devstral 2 123B 擅长使用工具探索代码库、编辑多个文件，并支持软件工程代理。",
    "zh-TW": "Devstral 2 123B 擅長使用工具探索程式碼庫、編輯多個檔案，並支援軟體工程代理人。",
    "ja-JP": "Devstral 2 123B は、ツールを活用してコードベースを探索し、複数ファイルを編集し、ソフトウェアエンジニアリングエージェントを支援することに優れています。",
    "ru-RU": "Devstral 2 123B превосходно использует инструменты для анализа кодовой базы, редактирования нескольких файлов и поддержки агентов в области программной инженерии."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "devstral-2:123b"
    }
   ]
  },
  {
   "slug": "mistral/devstral-2512",
   "model_name": "devstral-2512",
   "display_name": "Devstral 2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "mistralai/devstral-2512"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/devstral-2512"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/devstral-2512"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.039999999999999994"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "mistralai/devstral-2512"
    }
   ],
   "intro": "Mistral's coding-agent model for repository work, terminal tasks, and software fixes",
   "released_at": "2025-12-09",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true
   },
   "docs_url": "https://mistral.ai/news/devstral-2-vibe-cli",
   "model_type": "text_generation",
   "benchmarks": {
    "intelligence_index": 19.2,
    "coding_index": 31.3,
    "agentic_index": 10.6
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/devstral-2512",
    "mistralai/devstral-2512",
    "mistralai/devstral-2512:free"
   ],
   "intro_i18n": {
    "zh-CN": "Devstral 2 是一款企业级文本模型，擅长使用工具探索代码库、编辑多个文件，并为软件工程 Agent 提供支持。",
    "zh-TW": "Devstral 2 是一款企業級文本模型，擅長使用工具探索代碼庫、編輯多個文件並驅動軟件工程代理。",
    "ja-JP": "Devstral 2は、コードベースの探索、複数ファイルの編集、ソフトウェアエンジニアリングエージェントの強化に優れたエンタープライズレベルのテキストモデルです。",
    "ru-RU": "Devstral 2 — это корпоративная текстовая модель, которая превосходно справляется с использованием инструментов для исследования кодовых баз, редактирования нескольких файлов и поддержки агентов для разработки программного обеспечения."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/devstral-latest",
   "model_name": "devstral-latest",
   "display_name": "Devstral 2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/devstral-latest"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-12-09",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true
   },
   "docs_url": "https://mistral.ai/news/devstral-2-vibe-cli",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/devstral-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "mistral/devstral-medium",
   "model_name": "devstral-medium",
   "display_name": "Mistral: Devstral Medium",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistralai/devstral-medium"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+computeprices+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistralai/devstral-medium"
    }
   ],
   "intro": "Mistral coding agent model for repository tasks and software engineering workflows",
   "released_at": "2025-07-10",
   "max_input_tokens": 131072,
   "max_output_tokens": 26215,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "deprecated": true,
   "model_type": "text_generation",
   "family": "Devstral",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/devstral-medium"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral: Devstral Medium"
    }
   ]
  },
  {
   "slug": "mistral/devstral-medium-2507",
   "model_name": "devstral-medium-2507",
   "display_name": "Devstral Medium",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/devstral-medium-2507"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/devstral-medium-2507"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-07-10",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "stream": true
   },
   "docs_url": "https://mistral.ai/news/devstral",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/devstral-medium-2507"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/devstral-medium-251121",
   "model_name": "devstral-medium-251121",
   "display_name": "devstral-medium-251121",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "devstral-medium-251121"
    }
   ]
  },
  {
   "slug": "mistral/devstral-medium-latest",
   "model_name": "devstral-medium-latest",
   "display_name": "Devstral 2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/devstral-medium-latest"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/devstral-medium-latest"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-12-02",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true
   },
   "docs_url": "https://mistral.ai/news/devstral-2-vibe-cli",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/devstral-medium-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/devstral-small",
   "model_name": "devstral-small",
   "display_name": "Devstral Small 1.1",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistralai/devstral-small"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "mistralai/devstral-small"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral/devstral-small"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "mistral/devstral-small"
    }
   ],
   "intro": "Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%).",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "released_at": "2025-05-21",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/devstral-small",
    "mistralai/devstral-small"
   ],
   "intro_i18n": {
    "zh-CN": "Devstral 是一款面向软件工程任务的智能体大语言模型，是软件工程智能体的强力选择。",
    "zh-TW": "Devstral 是一款專為軟體工程任務設計的代理型大型語言模型，是軟體工程代理的強力選擇。",
    "ja-JP": "Devstralは、ソフトウェアエンジニアリングタスク向けのエージェント型LLMで、ソフトウェアエンジニアリングエージェントに最適です。",
    "ru-RU": "Devstral — агентная LLM для задач в области разработки ПО, отличный выбор для инженерных агентов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Devstral Small 1.1"
    }
   ]
  },
  {
   "slug": "mistral/devstral-small-2",
   "model_name": "devstral-small-2",
   "display_name": "Devstral Small 2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral/devstral-small-2"
    }
   ],
   "intro": "Mistral coding agent model for repository tasks and software engineering workflows",
   "released_at": "2025-12-09",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/devstral-small-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Devstral Small 2"
    }
   ]
  },
  {
   "slug": "mistral/devstral-small-2-24b-instruct-2512",
   "model_name": "devstral-small-2-24b-instruct-2512",
   "display_name": "Devstral Small 2 24B Instruct 2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "evroc",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.47"
      }
     },
     "provider_model_id": "mistralai/devstral-small-2-24b-instruct-2512"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/devstral-small-2-24b-instruct-2512"
    }
   ],
   "released_at": "2025-12-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "devstral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/devstral-small-2-24b-instruct-2512",
    "mistralai/devstral-small-2-24b-instruct-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Devstral Small 2 24B Instruct 2512"
    }
   ]
  },
  {
   "slug": "mistral/devstral-small-2:24b",
   "model_name": "devstral-small-2:24b",
   "display_name": "devstral-small-2:24b",
   "vendor": "mistral",
   "pricing": [],
   "intro": "Mistral coding agent model for repository tasks and software engineering workflows",
   "released_at": "2025-12-09",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "devstral-small-2:24b"
    }
   ]
  },
  {
   "slug": "mistral/devstral-small-2505",
   "model_name": "devstral-small-2505",
   "display_name": "Devstral Small 2505",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/devstral-small-2505"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistralai/Devstral-Small-2505"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.060000000000000005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.060000000000000005"
      }
     },
     "provider_model_id": "mistralai/Devstral-Small-2505"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "devstral-small-2505:free"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-05-07",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "stream": true
   },
   "docs_url": "https://mistral.ai/news/devstral",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/devstral-small-2505",
    "devstral-small-2505:free",
    "mistralai/Devstral-Small-2505"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/devstral-small-2507",
   "model_name": "devstral-small-2507",
   "display_name": "Devstral Small",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral/devstral-small-2507"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistralai/devstral-small-2507"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral/devstral-small-2507"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-07-10",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "stream": true
   },
   "docs_url": "https://mistral.ai/news/devstral",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/devstral-small-2507",
    "mistralai/devstral-small-2507"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/devstral-small-latest",
   "model_name": "devstral-small-latest",
   "display_name": "devstral-small-latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral/devstral-small-latest"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral/devstral-small-latest"
    }
   ],
   "docs_url": "https://docs.mistral.ai/models/devstral-small-2-25-12",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-04-22",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/devstral-small-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    }
   ]
  },
  {
   "slug": "mistral/dolphin-2p6-mixtral-8x7b",
   "model_name": "dolphin-2p6-mixtral-8x7b",
   "display_name": "Dolphin 2.6 Mixtral 8x7b",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/dolphin-2p6-mixtral-8x7b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/dolphin-2p6-mixtral-8x7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Dolphin 2.6 Mixtral 8x7b"
    }
   ]
  },
  {
   "slug": "mistral/dolphin-mistral-24b-venice-edition:free",
   "model_name": "dolphin-mistral-24b-venice-edition:free",
   "display_name": "Uncensored (free)",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-07-09",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral",
   "capabilities": {
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cognitivecomputations/dolphin-mistral-24b-venice-edition:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Uncensored (free)"
    }
   ]
  },
  {
   "slug": "mistral/dolphin-mixtral-8x22b",
   "model_name": "dolphin-mixtral-8x22b",
   "display_name": "dolphin-mixtral-8x22b",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "cognitivecomputations/dolphin-mixtral-8x22b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cognitivecomputations/dolphin-mixtral-8x22b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "dolphin-mixtral-8x22b"
    }
   ]
  },
  {
   "slug": "mistral/dolphin-mixtral-8x7b",
   "model_name": "dolphin-mixtral-8x7b",
   "display_name": "dolphin-mixtral-8x7b",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "cognitivecomputations/dolphin-mixtral-8x7b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cognitivecomputations/dolphin-mixtral-8x7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "dolphin-mixtral-8x7b"
    }
   ]
  },
  {
   "slug": "mistral/dolphin3.0-mistral-24b:free",
   "model_name": "dolphin3.0-mistral-24b:free",
   "display_name": "dolphin3.0-mistral-24b:free",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "dolphin3.0-mistral-24b:free"
    }
   ]
  },
  {
   "slug": "mistral/dolphin3.0-r1-mistral-24b:free",
   "model_name": "dolphin3.0-r1-mistral-24b:free",
   "display_name": "dolphin3.0-r1-mistral-24b:free",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "dolphin3.0-r1-mistral-24b:free"
    }
   ]
  },
  {
   "slug": "mistral/E5-Mistral-7B-Instruct",
   "model_name": "E5-Mistral-7B-Instruct",
   "display_name": "E5 Mistral 7B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "e5-mistral-7b-instruct"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "stackit",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "intfloat/e5-mistral-7b-instruct"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2023-12-11",
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "docs_url": "https://nebius.com/prices-ai-studio",
   "model_type": "text_embedding",
   "knowledge_cutoff": "2023-12",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "e5-mistral-7b-instruct",
    "intfloat/e5-mistral-7b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "E5 Mistral 7B"
    }
   ]
  },
  {
   "slug": "mistral/hermes-2-pro-mistral-7b",
   "model_name": "hermes-2-pro-mistral-7b",
   "display_name": "Hermes 2 Pro Mistral 7B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/hermes-2-pro-mistral-7b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/hermes-2-pro-mistral-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes 2 Pro Mistral 7B"
    }
   ]
  },
  {
   "slug": "mistral/labs-devstral-small-2512",
   "model_name": "labs-devstral-small-2512",
   "display_name": "Devstral Small 2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-12-09",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "devstral",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true
   },
   "docs_url": "https://docs.mistral.ai/models/devstral-small-2-25-12",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Devstral Small 2 擅长使用工具探索代码库、编辑多个文件，并为软件工程 Agent 提供支持。",
    "zh-TW": "Devstral Small 2 擅長使用工具探索代碼庫、編輯多個文件並驅動軟件工程代理。",
    "ja-JP": "Devstral Small 2は、コードベースの探索、複数ファイルの編集、ソフトウェアエンジニアリングエージェントの強化に優れています。",
    "ru-RU": "Devstral Small 2 превосходно справляется с использованием инструментов для исследования кодовых баз, редактирования нескольких файлов и поддержки агентов для разработки программного обеспечения."
   }
  },
  {
   "slug": "mistral/labs-leanstral-1-5",
   "model_name": "labs-leanstral-1-5",
   "display_name": "labs-leanstral-1-5",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true,
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "labs-leanstral-1-5"
    }
   ]
  },
  {
   "slug": "mistral/labs-leanstral-1-5-1",
   "model_name": "labs-leanstral-1-5-1",
   "display_name": "labs-leanstral-1-5-1",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "labs-leanstral-1-5-1"
    }
   ]
  },
  {
   "slug": "mistral/labs-leanstral-2603",
   "model_name": "labs-leanstral-2603",
   "display_name": "Leanstral",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 196608,
   "deprecated": true,
   "modalities": {
    "input": [
     "image",
     "text",
     "code"
    ],
    "output": [
     "text",
     "code"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true,
    "vision": true
   },
   "released_at": "2026-03-16",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Mistral的首个开源代码代理，专为Lean 4设计，适用于现实存储库中的形式化证明工程。拥有1190亿参数，其中65亿为激活参数。",
    "zh-TW": "Mistral首款開源代碼代理，專為Lean 4設計，適用於現實存儲庫中的形式化證明工程。119B參數，6.5B激活。",
    "ja-JP": "Lean 4用に設計されたMistralの最初のオープンソースコードエージェントで、現実的なリポジトリでの形式的証明エンジニアリングに対応。119Bパラメータ、6.5Bアクティブ。",
    "ru-RU": "Первая модель открытого исходного кода для работы с кодом от Mistral, разработанная для Lean 4, созданная для формального доказательства в реалистичных репозиториях. 119B параметров с 6.5B активных."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Leanstral"
    }
   ]
  },
  {
   "slug": "mistral/labs-mistral-small-creative",
   "model_name": "labs-mistral-small-creative",
   "display_name": "labs-mistral-small-creative",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "labs-mistral-small-creative"
    }
   ]
  },
  {
   "slug": "mistral/Llama-3.05-NT-Storybreaker-Ministral-70B",
   "model_name": "Llama-3.05-NT-Storybreaker-Ministral-70B",
   "display_name": "Llama 3.05 Storybreaker Ministral 70b",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2024-12-01",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.05 Storybreaker Ministral 70b"
    }
   ]
  },
  {
   "slug": "mistral/magistral-medium",
   "model_name": "magistral-medium",
   "display_name": "Magistral Medium",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "mistral/magistral-medium"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "mistral/magistral-medium"
    }
   ],
   "intro": "Magistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "released_at": "2025-03-17",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "magistral-medium",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/magistral-medium"
   ],
   "intro_i18n": {
    "zh-CN": "通过深度理解支持复杂思维，具备可追踪、可验证的透明推理能力。即使在任务中途，也能在多语言环境中保持高保真推理。",
    "zh-TW": "透過深層理解支援複雜思維，並提供可追溯與可驗證的透明推理。即使在任務中途，也能維持跨語言的高保真推理能力。",
    "ja-JP": "深い理解に基づく複雑な思考を支援し、透明性のある推論を提供します。タスク中でも言語間で高精度な推論を維持します。",
    "ru-RU": "Сложное мышление, поддерживаемое глубоким пониманием и прозрачной логикой, которую можно проследить и проверить. Сохраняет точность рассуждений на разных языках даже в середине задачи."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Magistral Medium"
    }
   ]
  },
  {
   "slug": "mistral/magistral-medium-1-2-2509",
   "model_name": "magistral-medium-1-2-2509",
   "display_name": "magistral-medium-1-2-2509",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/news/magistral",
   "max_input_tokens": 40000,
   "max_output_tokens": 40000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/magistral-medium-2506",
   "model_name": "magistral-medium-2506",
   "display_name": "magistral-medium-2506",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "magistral-medium-2506:thinking"
    }
   ],
   "docs_url": "https://mistral.ai/news/magistral",
   "max_input_tokens": 40000,
   "max_output_tokens": 40000,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "assistant_prefill": true
   },
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "magistral-medium-2506:thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/magistral-medium-2509",
   "model_name": "magistral-medium-2509",
   "display_name": "magistral-medium-2509",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/news/magistral",
   "max_input_tokens": 40000,
   "max_output_tokens": 40000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "image",
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-09-18",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Magistral Medium 1.2是Mistral AI的前沿推理模型（2025年9月），支持视觉功能。",
    "zh-TW": "Magistral Medium 1.2是Mistral AI的前沿推理模型（2025年9月），支持視覺功能。",
    "ja-JP": "Magistral Medium 1.2は、Mistral AIによるフロンティア推論モデル（2025年9月）で、ビジョンサポートを備えています。",
    "ru-RU": "Magistral Medium 1.2 — передовая модель рассуждений от Mistral AI (сентябрь 2025) с поддержкой визуализации."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/magistral-medium-el",
   "model_name": "magistral-medium-el",
   "display_name": "Magistral-Medium-EL",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.6263"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.5657"
      }
     }
    }
   ],
   "released_at": "2025-06-18",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Magistral-Medium-EL"
    }
   ]
  },
  {
   "slug": "mistral/magistral-medium-latest",
   "model_name": "magistral-medium-latest",
   "display_name": "Magistral Medium",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "mistral/magistral-medium-latest"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "mistral/magistral-medium-latest"
    }
   ],
   "intro": "Mistral reasoning model for transparent analysis, math, and complex decisions",
   "released_at": "2025-03-17",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "magistral-medium",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://mistral.ai/news/magistral",
   "model_type": "text_generation",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/magistral-medium-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/magistral-small",
   "model_name": "magistral-small",
   "display_name": "Magistral Small",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral/magistral-small"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral/magistral-small"
    }
   ],
   "intro": "Mistral reasoning model for transparent analysis, math, and complex decisions",
   "released_at": "2025-03-17",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "magistral-small",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/magistral-small"
   ],
   "intro_i18n": {
    "zh-CN": "通过深度理解支持复杂思维，具备可追踪、可验证的透明推理能力。即使在任务中途，也能在多语言环境中保持高保真推理。",
    "zh-TW": "透過深層理解支援複雜思維，並提供可追溯與可驗證的透明推理。即使在任務中途，也能維持跨語言的高保真推理能力。",
    "ja-JP": "深い理解に基づく複雑な思考を支援し、透明性のある推論を提供します。タスク中でも言語間で高精度な推論を維持します。",
    "ru-RU": "Сложное мышление, поддерживаемое глубоким пониманием и прозрачной логикой, которую можно проследить и проверить. Сохраняет точность рассуждений на разных языках даже в середине задачи."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/magistral-small-1-2",
   "model_name": "magistral-small-1-2",
   "display_name": "Magistral Small 1.2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Magistral Small 1.2"
    }
   ]
  },
  {
   "slug": "mistral/magistral-small-1-2-2509",
   "model_name": "magistral-small-1-2-2509",
   "display_name": "magistral-small-1-2-2509",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/pricing#api-pricing",
   "max_input_tokens": 40000,
   "max_output_tokens": 40000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/magistral-small-2506",
   "model_name": "magistral-small-2506",
   "display_name": "magistral-small-2506",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "mistralai/Magistral-Small-2506"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "Magistral-Small-2506"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/magistral-small-2506"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/pricing#api-pricing",
   "max_input_tokens": 40000,
   "max_output_tokens": 40000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "assistant_prefill": true,
    "stream": true
   },
   "intro": "Mistral reasoning model for transparent analysis, math, and complex decisions",
   "released_at": "2025-09-25",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2025-01",
   "family": "magistral-small",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Magistral-Small-2506",
    "mistralai/Magistral-Small-2506",
    "mistralai/magistral-small-2506"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/Magistral-Small-2509",
   "model_name": "Magistral-Small-2509",
   "display_name": "Magistral Small 1.2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry+portkey+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "magistral-small-2509"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.61"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.82"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.515"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.545"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.78"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.33"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.61"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.82"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.61"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.82"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.515"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.545"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.78"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.33"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.61"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.82"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral.magistral-small-2509",
     "region": "us-west-2"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "magistral-small-2509"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.36"
      }
     },
     "provider_model_id": "mistralai/Magistral-Small-2509"
    }
   ],
   "max_input_tokens": 131072,
   "deprecated": true,
   "modalities": {
    "input": [
     "image",
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true,
    "open_weights": true,
    "prompt_caching": true
   },
   "intro": "Mistral reasoning model for transparent analysis, math, and complex decisions",
   "released_at": "2025-12-02",
   "max_output_tokens": 40000,
   "family": "magistral",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "magistral-small-2509",
    "mistral.magistral-small-2509",
    "mistralai/Magistral-Small-2509"
   ],
   "intro_i18n": {
    "zh-CN": "Magistral Small 1.2 是 Mistral AI 于 2025 年 9 月发布的开源小型推理模型，支持视觉输入。",
    "zh-TW": "Magistral Small 1.2 是 Mistral AI 推出的開源小型推理模型（2025 年 9 月），支援視覺任務。",
    "ja-JP": "Magistral Small 1.2はMistral AIによるオープンソースの小型推論モデルで、視覚入力をサポートします。",
    "ru-RU": "Magistral Small 1.2 — это компактная модель рассуждений с открытым исходным кодом от Mistral AI (сентябрь 2025 года) с поддержкой обработки изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Magistral Small 1.2"
    }
   ]
  },
  {
   "slug": "mistral/magistral-small-latest",
   "model_name": "magistral-small-latest",
   "display_name": "magistral-small-latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral/magistral-small-latest"
    }
   ],
   "docs_url": "https://mistral.ai/pricing#api-pricing",
   "max_input_tokens": 40000,
   "max_output_tokens": 40000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "assistant_prefill": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-04-22",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/magistral-small-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/ministral-14b",
   "model_name": "ministral-14b",
   "display_name": "Ministral 14B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistral/ministral-14b"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2025-12-02",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/ministral-14b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 14B"
    }
   ]
  },
  {
   "slug": "mistral/ministral-14b-2512",
   "model_name": "ministral-14b-2512",
   "display_name": "ministral-14b-2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "mistralai/ministral-14b-2512"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/ministral-14b-2512"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/ministral-14b-2512"
    }
   ],
   "intro": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true,
    "vision": true,
    "pdf_input": true,
    "open_weights": true,
    "prompt_caching": true,
    "stream": true,
    "image_output": true
   },
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "released_at": "2025-12-16",
   "knowledge_cutoff": "2024-12",
   "max_output_tokens": 128000,
   "family": "mistral",
   "benchmarks": {
    "intelligence_index": 11.1,
    "coding_index": 14.4,
    "agentic_index": 2.2
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/ministral-14b-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "assistant_prefill: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ministral-14b-2512"
    }
   ]
  },
  {
   "slug": "mistral/ministral-14b-instruct-2512",
   "model_name": "ministral-14b-instruct-2512",
   "display_name": "Ministral 3 14B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "mistralai/ministral-14b-instruct-2512"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2025-12-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-12",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/ministral-14b-instruct-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3 14B"
    }
   ]
  },
  {
   "slug": "mistral/ministral-14b-latest",
   "model_name": "ministral-14b-latest",
   "display_name": "Ministral 3 14B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistral/ministral-14b-latest"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true,
    "assistant_prefill": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-04-22",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/ministral-14b-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ministral-14b-latest"
    }
   ]
  },
  {
   "slug": "mistral/ministral-3-14b",
   "model_name": "ministral-3-14b",
   "display_name": "Ministral 3 14B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "family": "Ministral",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3 14B"
    }
   ]
  },
  {
   "slug": "mistral/ministral-3-14b-2512",
   "model_name": "ministral-3-14b-2512",
   "display_name": "ministral-3-14b-2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/pricing",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/Ministral-3-14B-Instruct-2512",
   "model_name": "Ministral-3-14B-Instruct-2512",
   "display_name": "Ministral 3 14B Instruct 2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "ministral-3-14b-instruct-2512"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/Ministral-3-14B-Instruct-2512"
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-12-02",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/ministral-3-14b-instruct-2512",
    "ministral-3-14b-instruct-2512",
    "mistralai/Ministral-3-14B-Instruct-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3 14B Instruct 2512"
    }
   ]
  },
  {
   "slug": "mistral/ministral-3-3b-2512",
   "model_name": "ministral-3-3b-2512",
   "display_name": "ministral-3-3b-2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/ministral-3-3b-instruct-2512",
   "model_name": "ministral-3-3b-instruct-2512",
   "display_name": "Ministral 3 3B Instruct 2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/ministral-3-3b-instruct-2512"
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/ministral-3-3b-instruct-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3 3B Instruct 2512"
    }
   ]
  },
  {
   "slug": "mistral/ministral-3-8b-2512",
   "model_name": "ministral-3-8b-2512",
   "display_name": "ministral-3-8b-2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/pricing",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/ministral-3-8b-instruct-2512",
   "model_name": "ministral-3-8b-instruct-2512",
   "display_name": "Ministral 3 8B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/ministral-3-8b-instruct-2512"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2025-12-15",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/ministral-3-8b-instruct-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3 8B"
    }
   ]
  },
  {
   "slug": "mistral/ministral-3:14b",
   "model_name": "ministral-3:14b",
   "display_name": "ministral-3:14b",
   "vendor": "mistral",
   "pricing": [],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2024-12-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Ministral 3 14B是Ministral 3系列中最大的模型，提供与更大规模的Mistral Small 3.2 24B模型相当的性能。针对本地部署进行了优化，在包括本地设置在内的各种硬件上提供高性能。",
    "zh-TW": "Ministral 3 14B是Ministral 3系列中最大的模型，提供與更大規模的Mistral Small 3.2 24B模型相當的最先進性能。針對本地部署進行優化，能在包括本地設置在內的各種硬件上提供高性能。",
    "ja-JP": "Ministral 3 14Bは、Ministral 3シリーズで最大のモデルで、より大きなMistral Small 3.2 24Bモデルに匹敵する最先端のパフォーマンスを提供します。ローカル展開向けに最適化されており、ローカルセットアップを含むさまざまなハードウェアで高いパフォーマンスを発揮します。",
    "ru-RU": "Ministral 3 14B — крупнейшая модель в серии Ministral 3, обеспечивающая передовую производительность, сопоставимую с более крупным аналогом Mistral Small 3.2 24B. Оптимизирована для локального развертывания, обеспечивает высокую производительность на различных аппаратных платформах, включая локальные настройки."
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ministral-3:14b"
    }
   ]
  },
  {
   "slug": "mistral/ministral-3:3b",
   "model_name": "ministral-3:3b",
   "display_name": "ministral-3:3b",
   "vendor": "mistral",
   "pricing": [],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2024-10-22",
   "max_input_tokens": 262144,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Ministral 3 3B是Ministral 3系列中最小且最高效的模型，在紧凑的封装中提供强大的语言和视觉能力。专为边缘部署设计，在包括本地设置在内的各种硬件上提供高性能。",
    "zh-TW": "Ministral 3 3B是Ministral 3系列中最小且最高效的模型，提供強大的語言及視覺能力，設計用於邊緣部署，能在包括本地設置在內的各種硬件上提供高性能。",
    "ja-JP": "Ministral 3 3Bは、Ministral 3シリーズで最小かつ最も効率的なモデルで、コンパクトなパッケージで強力な言語およびビジョン機能を提供します。エッジ展開向けに設計されており、ローカルセットアップを含むさまざまなハードウェアで高いパフォーマンスを発揮します。",
    "ru-RU": "Ministral 3 3B — самая компактная и эффективная модель в серии Ministral 3, предлагающая сильные языковые и визуальные возможности в компактном формате. Разработана для развертывания на периферийных устройствах, обеспечивает высокую производительность на различных аппаратных платформах, включая локальные настройки."
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ministral-3:3b"
    }
   ]
  },
  {
   "slug": "mistral/ministral-3:8b",
   "model_name": "ministral-3:8b",
   "display_name": "ministral-3:8b",
   "vendor": "mistral",
   "pricing": [],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2024-12-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Ministral 3 8B是Ministral 3系列中强大且高效的模型，提供顶级的文本和视觉能力。专为边缘部署设计，在包括本地设置在内的各种硬件上提供高性能。",
    "zh-TW": "Ministral 3 8B是Ministral 3系列中強大且高效的模型，提供頂級文字及視覺能力。專為邊緣部署設計，能在包括本地設置在內的各種硬件上提供高性能。",
    "ja-JP": "Ministral 3 8Bは、Ministral 3シリーズで強力かつ効率的なモデルで、最上級のテキストおよびビジョン機能を提供します。エッジ展開向けに設計されており、ローカルセットアップを含むさまざまなハードウェアで高いパフォーマンスを発揮します。",
    "ru-RU": "Ministral 3 8B — мощная и эффективная модель в серии Ministral 3, обеспечивающая передовые текстовые и визуальные возможности. Создана для развертывания на периферийных устройствах, обеспечивает высокую производительность на различных аппаратных платформах, включая локальные настройки."
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ministral-3:8b"
    }
   ]
  },
  {
   "slug": "mistral/ministral-3b",
   "model_name": "ministral-3b",
   "display_name": "Ministral 3B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistral-ai/ministral-3b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistralai/ministral-3b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistral/ministral-3b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistral/ministral-3b"
    }
   ],
   "intro": "Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mistral 7B on most benchmarks. Supporting up to 128k context length, it's ideal for orchestrating agentic workflows and specialist tasks with efficient inference.",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "released_at": "2024-10-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "docs_url": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-ai/ministral-3b",
    "mistral/ministral-3b",
    "mistralai/ministral-3b"
   ],
   "intro_i18n": {
    "zh-CN": "一款紧凑高效的模型，适用于设备端任务，如助手和本地分析，提供低延迟性能。",
    "zh-TW": "一款緊湊高效的模型，適用於裝置端任務，如助手與本地分析，提供低延遲效能。",
    "ja-JP": "アシスタントやローカル分析などのオンデバイスタスク向けのコンパクトで高効率なモデルで、低遅延性能を実現します。",
    "ru-RU": "Компактная и эффективная модель для задач на устройстве, таких как ассистенты и локальная аналитика, с низкой задержкой."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3B"
    }
   ]
  },
  {
   "slug": "mistral/ministral-3b-2512",
   "model_name": "ministral-3b-2512",
   "display_name": "Ministral 3B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "mistralai/ministral-3b-2512"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistralai/ministral-3b-2512"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/ministral-3b-2512"
    }
   ],
   "intro": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true,
    "open_weights": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true,
    "image_output": true
   },
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "released_at": "2025-12-02",
   "max_output_tokens": 8192,
   "family": "mistral",
   "benchmarks": {
    "intelligence_index": 6.8,
    "coding_index": 4.8,
    "agentic_index": 1.6
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/ministral-3b-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3B"
    }
   ]
  },
  {
   "slug": "mistral/ministral-3b-latest",
   "model_name": "ministral-3b-latest",
   "display_name": "Ministral 3B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.25",
        "completion": "1.25"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistral/ministral-3b-latest"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2024-10-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "assistant_prefill": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/ministral-3b-latest"
   ],
   "intro_i18n": {
    "zh-CN": "Ministral 3B 是 Mistral 推出的顶级边缘模型。",
    "zh-TW": "Ministral 3B 是 Mistral 的頂級邊緣模型。",
    "ja-JP": "Ministral 3Bは、Mistralの最上位エッジモデルです。",
    "ru-RU": "Ministral 3B — это флагманская модель edge-класса от Mistral."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "assistant_prefill: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/ministral-8b",
   "model_name": "ministral-8b",
   "display_name": "Ministral 8B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistral/ministral-8b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistral/ministral-8b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistral/ministral-8b"
    }
   ],
   "intro": "Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "released_at": "2024-10-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/ministral-8b",
    "mistralai/ministral-8b"
   ],
   "intro_i18n": {
    "zh-CN": "一款更强大的模型，推理速度更快、内存效率更高，适用于复杂工作流和高要求的边缘应用。",
    "zh-TW": "一款更強大的模型，具備更快且記憶體效率更高的推理能力，適合複雜工作流程與高需求邊緣應用。",
    "ja-JP": "より高性能でメモリ効率の良い推論を実現し、複雑なワークフローや高負荷なエッジアプリケーションに最適です。",
    "ru-RU": "Более мощная модель с быстрой и экономной по памяти инференцией, идеально подходит для сложных рабочих процессов и требовательных edge-приложений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 8B"
    }
   ]
  },
  {
   "slug": "mistral/ministral-8b-2512",
   "model_name": "ministral-8b-2512",
   "display_name": "ministral-8b-2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "mistralai/ministral-8b-2512"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "mistralai/ministral-8b-2512"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/ministral-8b-2512"
    }
   ],
   "docs_url": "https://mistral.ai/pricing",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "open_weights": true,
    "stream": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2025-12-02",
   "family": "mistral",
   "benchmarks": {
    "intelligence_index": 9,
    "coding_index": 9.7,
    "agentic_index": 1.2
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/ministral-8b-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "mistral/ministral-8b-latest",
   "model_name": "ministral-8b-latest",
   "display_name": "Ministral 8B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "mistral/ministral-8b-latest"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2024-10-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://mistral.ai/pricing",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/ministral-8b-latest"
   ],
   "intro_i18n": {
    "zh-CN": "Ministral 8B 是 Mistral 推出的高性价比边缘模型。",
    "zh-TW": "Ministral 8B 是 Mistral 推出的高性價比邊緣模型。",
    "ja-JP": "Ministral 8Bは、Mistralによる高コストパフォーマンスのエッジモデルです。",
    "ru-RU": "Ministral 8B — высокоэффективная модель edge-класса от Mistral с оптимальным соотношением цена/качество."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/mistral",
   "model_name": "mistral",
   "display_name": "mistral",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34249185"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34249185"
      }
     }
    }
   ],
   "released_at": "2025-10-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Mistral 是 Mistral AI 推出的 70 亿参数模型，适用于多种语言任务。",
    "zh-TW": "Mistral 是 Mistral AI 推出的 7B 模型，適用於多樣化語言任務。",
    "ja-JP": "Mistralは、Mistral AIによる7Bモデルで、多様な言語タスクに対応します。",
    "ru-RU": "Mistral — модель на 7B параметров от Mistral AI, подходящая для разнообразных языковых задач."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343112244",
     "new": "0.34249185"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343112244",
     "new": "0.34249185"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.342979791",
     "new": "0.343112244"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.342979791",
     "new": "0.343112244"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343242429",
     "new": "0.342979791"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343242429",
     "new": "0.342979791"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343104252",
     "new": "0.343242429"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343104252",
     "new": "0.343242429"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343199361",
     "new": "0.343104252"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343199361",
     "new": "0.343104252"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.3414291",
     "new": "0.343199361"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.3414291",
     "new": "0.343199361"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral"
    }
   ]
  },
  {
   "slug": "mistral/mistral-3-14B",
   "model_name": "mistral-3-14B",
   "display_name": "Ministral 3 14B Instruct",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2025-12-15",
   "max_input_tokens": 262144,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3 14B Instruct"
    }
   ]
  },
  {
   "slug": "mistral/mistral-31-24b",
   "model_name": "mistral-31-24b",
   "display_name": "Venice Medium",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "released_at": "2025-03-18",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "family": "mistral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "stream": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Venice Medium"
    }
   ]
  },
  {
   "slug": "mistral/mistral-7b",
   "model_name": "mistral-7b",
   "display_name": "Mistral 7B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mistral-7b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "family": "Mistral",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mistral-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral 7B"
    }
   ]
  },
  {
   "slug": "mistral/mistral-7b-instruct",
   "model_name": "mistral-7b-instruct",
   "display_name": "mistralai/mistral-7b-instruct:free",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.002"
      }
     },
     "provider_model_id": "mistralai/mistral-7b-instruct:free"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.059"
      }
     },
     "provider_model_id": "mistralai/mistral-7b-instruct"
    }
   ],
   "capabilities": {},
   "released_at": "2024-06-27",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-7b-instruct",
    "mistralai/mistral-7b-instruct:free"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistralai/mistral-7b-instruct:free"
    }
   ]
  },
  {
   "slug": "mistral/mistral-7b-instruct-4k",
   "model_name": "mistral-7b-instruct-4k",
   "display_name": "mistral-7b-instruct-4k",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-7b-instruct-4k"
    }
   ]
  },
  {
   "slug": "mistral/Mistral-7B-Instruct-v0.2",
   "model_name": "Mistral-7B-Instruct-v0.2",
   "display_name": "mistral-7b-instruct-v0.2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.197"
      }
     },
     "provider_model_id": "mistral-7b-instruct-v0.2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistral-7b-instruct-v0.2"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/Mistral-7B-Instruct-v0.2"
    }
   ],
   "capabilities": {},
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "released_at": "2025-05-26",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-7b-instruct-v0.2",
    "mistralai/Mistral-7B-Instruct-v0.2",
    "mistralai/mistral-7b-instruct-v0.2"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral（7B）Instruct v0.2 提升了指令处理能力和结果准确性。",
    "zh-TW": "Mistral（7B）Instruct v0.2 改進了指令處理與結果準確性。",
    "ja-JP": "Mistral（7B）Instruct v0.2は、命令処理と結果の正確性を向上させています。",
    "ru-RU": "Mistral (7B) Instruct v0.2 улучшает обработку инструкций и точность результатов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-7b-instruct-v0.2"
    }
   ]
  },
  {
   "slug": "mistral/Mistral-7B-Instruct-v0.3",
   "model_name": "Mistral-7B-Instruct-v0.3",
   "display_name": "Mistral 7B Instruct v0.3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistral-7b-instruct-v0.3"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/Mistral-7B-Instruct-v0.3"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/mistral-7b-instruct-v0.3"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "mistral-7b-instruct-v0.3"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/Mistral-7B-Instruct-v0.3"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2024-05-22",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-7b-instruct-v0.3",
    "mistralai/Mistral-7B-Instruct-v0.3",
    "mistralai/mistral-7b-instruct-v0.3"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral（7B）Instruct v0.3 提供高效计算和强大的语言理解，适用于多种场景。",
    "zh-TW": "Mistral（7B）Instruct v0.3 提供高效運算與強大的語言理解能力，適用於多種應用場景。",
    "ja-JP": "Mistral（7B）Instruct v0.3は、効率的な計算と優れた言語理解を提供し、多様な用途に対応します。",
    "ru-RU": "Mistral (7B) Instruct v0.3 обеспечивает эффективные вычисления и отличное понимание языка для множества сценариев."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral 7B Instruct v0.3"
    }
   ]
  },
  {
   "slug": "mistral/mistral-7b-instruct-v03",
   "model_name": "mistral-7b-instruct-v03",
   "display_name": "Mistral-7B-Instruct-v0.3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/mistral-7b-instruct-v03"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-04-01",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-7b-instruct-v03"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral-7B-Instruct-v0.3"
    }
   ]
  },
  {
   "slug": "mistral/mistral-7b-instruct-v0p2",
   "model_name": "mistral-7b-instruct-v0p2",
   "display_name": "Mistral 7B Instruct v0.2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mistral-7b-instruct-v0p2"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mistral-7b-instruct-v0p2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral 7B Instruct v0.2"
    }
   ]
  },
  {
   "slug": "mistral/mistral-7b-instruct-v3",
   "model_name": "mistral-7b-instruct-v3",
   "display_name": "Mistral 7B Instruct v0.3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mistral-7b-instruct-v3"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mistral-7b-instruct-v3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral 7B Instruct v0.3"
    }
   ]
  },
  {
   "slug": "mistral/Mistral-7B-OpenOrca",
   "model_name": "Mistral-7B-OpenOrca",
   "display_name": "Mistral-7B-OpenOrca",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Open-Orca/Mistral-7B-OpenOrca"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Open-Orca/Mistral-7B-OpenOrca"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral-7B-OpenOrca"
    }
   ]
  },
  {
   "slug": "mistral/Mistral-7B-v0.1",
   "model_name": "Mistral-7B-v0.1",
   "display_name": "Mistral-7B-v0.1",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/Mistral-7B-v0.1"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/Mistral-7B-v0.1"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral 7B 虽小巧但性能强劲，适合批处理和分类、文本生成等简单任务，具备扎实的推理能力。",
    "zh-TW": "Mistral 7B 體積小但效能強，適合批次處理與分類、文本生成等簡單任務，具備穩定的推理能力。",
    "ja-JP": "Mistral 7Bはコンパクトながら高性能で、分類やテキスト生成などのバッチ処理やシンプルなタスクに強く、堅実な推論力を備えています。",
    "ru-RU": "Mistral 7B — компактная, но высокопроизводительная модель, хорошо подходит для пакетной обработки и простых задач, таких как классификация и генерация текста, с уверенными логическими способностями."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral-7B-v0.1"
    }
   ]
  },
  {
   "slug": "mistral/mistral-7b-v0p2",
   "model_name": "mistral-7b-v0p2",
   "display_name": "Mistral 7B v0.2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mistral-7b-v0p2"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mistral-7b-v0p2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral 7B v0.2"
    }
   ]
  },
  {
   "slug": "mistral/mistral-ai-devstral-2512",
   "model_name": "mistral-ai-devstral-2512",
   "display_name": "devstral-2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "released_at": "2025-12-17",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "devstral-2512"
    }
   ]
  },
  {
   "slug": "mistral/mistral-ai-devstral-medium-2507",
   "model_name": "mistral-ai-devstral-medium-2507",
   "display_name": "devstral-medium-2507",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "released_at": "2025-07-12",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "devstral-medium-2507"
    }
   ]
  },
  {
   "slug": "mistral/mistral-ai-devstral-small-2505",
   "model_name": "mistral-ai-devstral-small-2505",
   "display_name": "devstral-small-2505",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2025-05-22",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "devstral-small-2505"
    }
   ]
  },
  {
   "slug": "mistral/mistral-ai-devstral-small-2507",
   "model_name": "mistral-ai-devstral-small-2507",
   "display_name": "devstral-small-2507",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2025-07-12",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "devstral-small-2507"
    }
   ]
  },
  {
   "slug": "mistral/mistral-ai-pixtral-large-2411",
   "model_name": "mistral-ai-pixtral-large-2411",
   "display_name": "pixtral-large-2411",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "released_at": "2025-08-06",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "pixtral-large-2411"
    }
   ]
  },
  {
   "slug": "mistral/mistral-ai-pixtral-large-latest",
   "model_name": "mistral-ai-pixtral-large-latest",
   "display_name": "pixtral-large-latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "released_at": "2025-03-18",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "pixtral-large-latest"
    }
   ]
  },
  {
   "slug": "mistral/mistral-code-agent-latest",
   "model_name": "mistral-code-agent-latest",
   "display_name": "Mistral Code Agent Latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-06-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Code Agent Latest"
    }
   ]
  },
  {
   "slug": "mistral/mistral-code-fim-latest",
   "model_name": "mistral-code-fim-latest",
   "display_name": "mistral-code-fim-latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "text",
     "code"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-code-fim-latest"
    }
   ]
  },
  {
   "slug": "mistral/mistral-code-latest",
   "model_name": "mistral-code-latest",
   "display_name": "Mistral Code Latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "code"
    ],
    "output": [
     "text",
     "code"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-06-02",
   "max_output_tokens": 32768,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Code Latest"
    }
   ]
  },
  {
   "slug": "mistral/mistral-embed",
   "model_name": "mistral-embed",
   "display_name": "Mistral Embed",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistral/mistral-embed"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistral/mistral-embed"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2023-12-11",
   "max_input_tokens": 8000,
   "max_output_tokens": 3072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-embed",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {},
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-embed"
   ],
   "intro_i18n": {
    "zh-CN": "一款通用文本嵌入模型，适用于语义搜索、相似度计算、聚类和 RAG 工作流。",
    "zh-TW": "一款通用文本嵌入模型，適用於語意搜尋、相似度分析、聚類與 RAG 工作流程。",
    "ja-JP": "意味検索、類似性評価、クラスタリング、RAGワークフローに対応した汎用テキスト埋め込みモデルです。",
    "ru-RU": "Универсальная модель встраивания текста для семантического поиска, оценки схожести, кластеризации и RAG-процессов."
   }
  },
  {
   "slug": "mistral/mistral-embed-2312",
   "model_name": "mistral-embed-2312",
   "display_name": "Mistral: Mistral Embed 2312",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistralai/mistral-embed-2312"
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_embedding",
   "capabilities": {
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-embed-2312"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral: Mistral Embed 2312"
    }
   ]
  },
  {
   "slug": "mistral/mistral-embed-dim128-2510",
   "model_name": "mistral-embed-dim128-2510",
   "display_name": "mistral-embed-dim128-2510",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-embed-dim128-2510"
    }
   ]
  },
  {
   "slug": "mistral/mistral-embed-dim256-2510",
   "model_name": "mistral-embed-dim256-2510",
   "display_name": "mistral-embed-dim256-2510",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-embed-dim256-2510"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large",
   "model_name": "mistral-large",
   "display_name": "Mistral Large",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/mistral-large"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.001"
      }
     },
     "provider_model_id": "mistralai/mistral-large"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/mistral-large"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistral/mistral-large"
    }
   ],
   "intro": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here.",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "released_at": "2024-07-24",
   "max_input_tokens": 128000,
   "max_output_tokens": 25600,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2024-11",
   "family": "mistral-large",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-large",
    "mistralai/mistral-large"
   ],
   "intro_i18n": {
    "zh-CN": "Mixtral Large 是 Mistral 的旗舰模型，结合代码生成、数学和推理能力，支持 128K 上下文窗口。",
    "zh-TW": "Mixtral Large 是 Mistral 的旗艦模型，結合代碼生成、數學與推理能力，支援 128K 上下文視窗。",
    "ja-JP": "Mixtral Largeは、Mistralのフラッグシップモデルで、コード生成、数学、推論を128Kのコンテキストウィンドウで実現します。",
    "ru-RU": "Mixtral Large — флагманская модель от Mistral, сочетающая генерацию кода, математику и рассуждение с контекстным окном на 128K."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Large"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-2",
   "model_name": "mistral-large-2",
   "display_name": "mistral-large-2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.0303"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.0909"
      }
     }
    }
   ],
   "released_at": "2024-07-24",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "max_output_tokens": 4096,
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-large-2"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-2402",
   "model_name": "mistral-large-2402",
   "display_name": "mistral-large-2402",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "31.2"
      }
     },
     "provider_model_id": "mistral.mistral-large-2402-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.192308",
        "completion": "0.192308"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.673077",
        "completion": "0.673077"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.192308",
        "completion": "0.192308"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.4"
      }
     },
     "provider_model_id": "mistral.mistral-large-2402-v1:0",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.6"
      }
     },
     "provider_model_id": "mistral.mistral-large-2402-v1:0",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.8"
      }
     },
     "provider_model_id": "mistral.mistral-large-2402-v1:0",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      }
     },
     "provider_model_id": "mistral.mistral-large-2402-v1:0",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.6"
      }
     },
     "provider_model_id": "mistral.mistral-large-2402-v1:0",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.6"
      }
     },
     "provider_model_id": "mistral.mistral-large-2402-v1:0",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20.2"
      }
     },
     "provider_model_id": "mistral.mistral-large-2402-v1:0",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "mistral.mistral-large-2402-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "mistral.mistral-large-2402-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.846"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.627"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "assistant_prefill": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-12-01",
   "family": "mistral-large",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral.mistral-large-2402-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-2407",
   "model_name": "mistral-large-2407",
   "display_name": "mistral-large-2407",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "Mistral-large-2407"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "mistral.mistral-large-2407-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.166667",
        "completion": "1.166667"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.333333",
        "completion": "0.333333"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistral.mistral-large-2407-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/mistral-large-2407"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/mistral-large-2407"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
   "released_at": "2024-11-19",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2024-03",
   "family": "mistral-large",
   "docs_url": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Mistral-large-2407",
    "mistral.mistral-large-2407-v1:0",
    "mistralai/mistral-large-2407"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-2411",
   "model_name": "mistral-large-2411",
   "display_name": "Mistral Large 2.1",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistral-ai/mistral-large-2411"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistralai/mistral-large-2411"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistralai/mistral-large-2411"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistral/mistral-large-2411"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistralai/mistral-large-2411"
    }
   ],
   "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
   "released_at": "2024-11-18",
   "knowledge_cutoff": "2024-11",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-large",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "stream": true
   },
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-ai/mistral-large-2411",
    "mistral/mistral-large-2411",
    "mistralai/mistral-large-2411"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral 的旗舰模型，适用于需要大规模推理或专业化的复杂任务（如合成文本生成、代码生成、RAG 或智能体）。",
    "zh-TW": "Mistral 的旗艦模型，適用於需要大規模推理或專業化的複雜任務（如合成文本生成、代碼生成、RAG 或智能代理）。",
    "ja-JP": "Mistralのフラッグシップモデルで、大規模な推論や専門性を要する複雑なタスク（合成テキスト生成、コード生成、RAG、エージェントなど）に対応します。",
    "ru-RU": "Флагманская модель Mistral для сложных задач, требующих масштабного рассуждения или специализации (генерация синтетического текста, кода, RAG или агенты)."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-2512",
   "model_name": "mistral-large-2512",
   "display_name": "Mistral Large 3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistralai/mistral-large-2512"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral/mistral-large-2512"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/mistral-large-2512"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "mistralai/mistral-large-2512"
    }
   ],
   "intro": "Mistral's largest general model for enterprise agents, coding, and multilingual reasoning",
   "released_at": "2024-11-01",
   "knowledge_cutoff": "2024-11",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-large",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://docs.mistral.ai/models/mistral-large-3-25-12",
   "model_type": "vision_understanding",
   "benchmarks": {
    "intelligence_index": 15.9,
    "coding_index": 20.1,
    "agentic_index": 5.5
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.0645
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-large-2512",
    "mistralai/mistral-large-2512"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral Large 3是一款最先进的开源权重通用多模态模型，采用精细的专家混合架构。拥有410亿激活参数和6750亿总参数。",
    "zh-TW": "Mistral Large 3是一款最先進的開源權重通用多模態模型，採用精細的專家混合架構。具有41B激活參數及675B總參數。",
    "ja-JP": "Mistral Large 3は、最先端のオープンウェイト汎用マルチモーダルモデルで、粒度の細かいエキスパートの混合アーキテクチャを備えています。41Bアクティブパラメータ、675B総パラメータを特徴とします。",
    "ru-RU": "Mistral Large 3 — передовая мультимодальная модель общего назначения с открытым весом и архитектурой Mixture of Experts. Имеет 41B активных параметров и 675B общих параметров."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-3",
   "model_name": "mistral-large-3",
   "display_name": "mistral-large-3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistralai/mistral-large-3"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "route/mistral-large-3"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral/mistral-large-3"
    }
   ],
   "docs_url": "https://docs.mistral.ai/models/mistral-large-3-25-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "open_weights": true
   },
   "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
   "released_at": "2025-12-02",
   "knowledge_cutoff": "2024-10",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-large",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-large-3",
    "mistralai/mistral-large-3",
    "route/mistral-large-3"
   ]
  },
  {
   "slug": "mistral/mistral-large-3-675b-instruct-2512",
   "model_name": "mistral-large-3-675b-instruct-2512",
   "display_name": "Mistral Large 3 675B Instruct 2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "mistralai/mistral-large-3-675b-instruct-2512"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/mistral-large-3-675b-instruct-2512"
    }
   ],
   "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
   "released_at": "2025-12-02",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-large",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-large-3-675b-instruct-2512"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Large 3 675B Instruct 2512"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-3-fp8",
   "model_name": "mistral-large-3-fp8",
   "display_name": "Mistral Large 3 675B Instruct 2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mistral-large-3-fp8"
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mistral-large-3-fp8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Large 3 675B Instruct 2512"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-3:675b",
   "model_name": "mistral-large-3:675b",
   "display_name": "mistral-large-3:675b",
   "vendor": "mistral",
   "pricing": [],
   "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
   "released_at": "2025-12-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-large",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Mistral Large 3是一款最先进的开源权重通用多模态模型，采用精细的专家混合架构。拥有410亿激活参数和6750亿总参数。",
    "zh-TW": "Mistral Large 3是一款最先進的開源權重通用多模態模型，採用精細的專家混合架構。具有41B激活參數及675B總參數。",
    "ja-JP": "Mistral Large 3は、洗練されたエキスパートの混合アーキテクチャを備えた最先端のオープンウェイト汎用マルチモーダルモデルです。41Bアクティブパラメータ、675B総パラメータを持っています。",
    "ru-RU": "Mistral Large 3 — передовая мультимодальная модель общего назначения с открытым весом и усовершенствованной архитектурой Mixture of Experts. Имеет 41B активных параметров и 675B общих параметров."
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-large-3:675b"
    }
   ]
  },
  {
   "slug": "mistral/Mistral-Large-Instruct-2411",
   "model_name": "Mistral-Large-Instruct-2411",
   "display_name": "Mistral Large Instruct 2411",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "mistralai/Mistral-Large-Instruct-2411"
    }
   ],
   "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
   "released_at": "2024-11-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-large",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/Mistral-Large-Instruct-2411"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Large Instruct 2411"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-latest",
   "model_name": "mistral-large-latest",
   "display_name": "Mistral Large",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral/mistral-large-latest"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral/mistral-large-latest"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistral/mistral-large-latest"
    }
   ],
   "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
   "released_at": "2024-11-01",
   "knowledge_cutoff": "2024-11",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-large",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true
   },
   "docs_url": "https://docs.mistral.ai/models/mistral-large-3-25-12",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-large-latest"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral Large是旗舰模型，擅长多语言任务、复杂推理和代码生成，非常适合高端应用。",
    "zh-TW": "Mistral Large是旗艦模型，擅長多語言任務、複雜推理及代碼生成，非常適合高端應用。",
    "ja-JP": "Mistral Largeは、マルチリンガルタスク、複雑な推論、コード生成に優れたフラッグシップモデルで、高度なアプリケーションに最適です。",
    "ru-RU": "Mistral Large — флагманская модель, превосходящая в многоязычных задачах, сложных рассуждениях и генерации кода для высококлассных приложений."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-pixtral-2411",
   "model_name": "mistral-large-pixtral-2411",
   "display_name": "mistral-large-pixtral-2411",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-large-pixtral-2411"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large-veteran-2512",
   "model_name": "mistral-large-veteran-2512",
   "display_name": "mistral-large-veteran-2512",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-large-veteran-2512"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large@2407",
   "model_name": "mistral-large@2407",
   "display_name": "mistral-large@2407",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-large@2407"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large@2411-001",
   "model_name": "mistral-large@2411-001",
   "display_name": "mistral-large@2411-001",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-large@2411-001"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large@latest",
   "model_name": "mistral-large@latest",
   "display_name": "mistral-large@latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-large@latest"
    }
   ]
  },
  {
   "slug": "mistral/mistral-large2",
   "model_name": "mistral-large2",
   "display_name": "Mistral Large",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
   "released_at": "2024-11-01",
   "knowledge_cutoff": "2024-11",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-large",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Large"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium",
   "model_name": "mistral-medium",
   "display_name": "mistral-medium",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.1"
      }
     }
    },
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.71245925"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.7081975"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.1"
      }
     },
     "provider_model_id": "mistralai/mistral-medium"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.7273"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.1818"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/mistral-medium"
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 8191,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-05-07",
   "knowledge_cutoff": "2024-10",
   "family": "mistral-medium",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-medium",
    "mistralai/mistral-medium"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.7185374",
     "new": "5.7081975"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.71556122",
     "new": "1.71245925"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.71632985",
     "new": "5.7185374"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.714898955",
     "new": "1.71556122"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.72070715",
     "new": "5.71632985"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.716212145",
     "new": "1.714898955"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.7184042",
     "new": "5.72070715"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.71552126",
     "new": "1.716212145"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.71998935",
     "new": "5.7184042"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.715996805",
     "new": "1.71552126"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.690485",
     "new": "5.71998935"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.7071455",
     "new": "1.715996805"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.70217625",
     "new": "5.690485"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.710652875",
     "new": "1.7071455"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "open_weights: false→true"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium-2312",
   "model_name": "mistral-medium-2312",
   "display_name": "mistral-medium-2312",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.1"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {
    "structured_output": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/mistral-medium-2505",
   "model_name": "mistral-medium-2505",
   "display_name": "Mistral Medium 3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistral-ai/mistral-medium-2505"
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/mistral-medium-2505"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "route/mistral-medium-2505"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-05-07",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-medium",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-ai/mistral-medium-2505",
    "mistral/mistral-medium-2505",
    "route/mistral-medium-2505"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium-2508",
   "model_name": "mistral-medium-2508",
   "display_name": "Mistral Medium 3.1",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-08-12",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-medium",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://mistral.ai/news/mistral-medium-3",
   "model_type": "vision_understanding",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Mistral Medium 3.1以8倍更低的成本提供最先进的性能，并简化企业部署。",
    "zh-TW": "Mistral Medium 3.1以8倍更低的成本提供最先進性能，簡化企業部署。",
    "ja-JP": "Mistral Medium 3.1は、8倍低コストで最先端のパフォーマンスを提供し、エンタープライズ展開を簡素化します。",
    "ru-RU": "Mistral Medium 3.1 обеспечивает передовую производительность при 8-кратном снижении затрат и упрощает развертывание в корпоративной среде."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium-2604",
   "model_name": "mistral-medium-2604",
   "display_name": "Mistral Medium 3.5",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Balanced Mistral model for enterprise assistants, multilingual work, and tools",
   "released_at": "2026-04-29",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-medium",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true
   },
   "docs_url": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/mistral-medium-3",
   "model_name": "mistral-medium-3",
   "display_name": "Mistral: Mistral Medium 3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3",
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3",
     "region": "us-central1"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5748"
      }
     }
    }
   ],
   "intro": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true
   },
   "max_input_tokens": 262144,
   "deprecated": true,
   "modalities": {
    "input": [
     "image",
     "text",
     "pdf",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "released_at": "2025-05-07",
   "max_output_tokens": 26215,
   "knowledge_cutoff": "2025-03",
   "family": "mistral-medium",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-medium-3"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "8.5613",
     "new": "8.5748"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "1.7123",
     "new": "1.715"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "8.586",
     "new": "8.5613"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "1.7172",
     "new": "1.7123"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral: Mistral Medium 3"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "8.5373",
     "new": "8.586"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "1.7075",
     "new": "1.7172"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium-3-1",
   "model_name": "mistral-medium-3-1",
   "display_name": "Mistral: Mistral Medium 3.1",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3.1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3.1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3.1"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5253"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6263"
      }
     },
     "provider_model_id": "mistral-medium-3.1"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-08-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 26215,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-06",
   "family": "mistral-medium",
   "model_type": "vision_understanding",
   "benchmarks": {
    "intelligence_index": 14.7,
    "coding_index": 20.5,
    "agentic_index": 6.2
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-medium-3.1",
    "mistralai/mistral-medium-3.1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral: Mistral Medium 3.1"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium-3-1-2508",
   "model_name": "mistral-medium-3-1-2508",
   "display_name": "mistral-medium-3-1-2508",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/news/mistral-medium-3",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/mistral-medium-3-5",
   "model_name": "mistral-medium-3-5",
   "display_name": "mistral-medium-3-5",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "mistral-medium-3.5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.71245925"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.7081975"
      }
     },
     "provider_model_id": "mistral-medium-3.5"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "mistral-medium-3.5"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3-5"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "mistral/mistral-medium-3.5"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3-5"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "mistral/mistral-medium-3-5"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3-5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "mistral/mistral-medium-3.5"
    }
   ],
   "docs_url": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-04-30",
   "knowledge_cutoff": "2024-11",
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "family": "mistral-medium",
   "benchmarks": {
    "intelligence_index": 29.9,
    "coding_index": 46.9,
    "agentic_index": 19
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-medium-3.5",
    "mistral/mistral-medium-3-5",
    "mistral/mistral-medium-3.5",
    "mistral/mistral-medium-3.5:thinking",
    "mistralai/mistral-medium-3-5"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral Medium 3.5 是一款前沿级多模态模型，针对代理和编程用例进行了优化，以修改后的 MIT 许可证形式发布为开源权重。",
    "zh-TW": "Mistral Medium 3.5 是一款前沿級多模態模型，針對代理和編程使用場景進行了優化，並以修改版 MIT 許可證形式發布為開源權重。",
    "ja-JP": "Mistral Medium 3.5は、エージェントおよびコーディングユースケース向けに最適化されたフロンティアクラスのマルチモーダルモデルで、修正版MITライセンスの下でオープンウェイトとしてリリースされています。",
    "ru-RU": "Mistral Medium 3.5 — это передовая мультимодальная модель, оптимизированная для агентных и программных сценариев использования, выпущенная с открытым весом по модифицированной лицензии MIT."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.7185374",
     "new": "5.7081975"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.71556122",
     "new": "1.71245925"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.71632985",
     "new": "5.7185374"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.714898955",
     "new": "1.71556122"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.72070715",
     "new": "5.71632985"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.716212145",
     "new": "1.714898955"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.7184042",
     "new": "5.72070715"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.71552126",
     "new": "1.716212145"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.71998935",
     "new": "5.7184042"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.715996805",
     "new": "1.71552126"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.690485",
     "new": "5.71998935"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.7071455",
     "new": "1.715996805"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "5.70217625",
     "new": "5.690485"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "1.710652875",
     "new": "1.7071455"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "open_weights: false→true"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium-3-5-0",
   "model_name": "mistral-medium-3-5-0",
   "display_name": "mistral-medium-3-5-0",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-medium-3-5-0"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium-3-instruct",
   "model_name": "mistral-medium-3-instruct",
   "display_name": "Mistral Medium 3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3-instruct"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-09-25",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-medium",
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-medium-3-instruct"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Medium 3"
    }
   ]
  },
  {
   "slug": "mistral/Mistral-Medium-3.5-128B",
   "model_name": "Mistral-Medium-3.5-128B",
   "display_name": "Mistral Medium 3.5 128B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "mistralai/Mistral-Medium-3.5-128B"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.725"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.9"
      }
     },
     "provider_model_id": "mistralai/Mistral-Medium-3.5-128B"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "mistral-medium-3.5-128b"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2026-04-29",
   "knowledge_cutoff": "2026-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-medium",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-medium-3.5-128b",
    "mistralai/Mistral-Medium-3.5-128B"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Medium 3.5 128B"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium-3@001",
   "model_name": "mistral-medium-3@001",
   "display_name": "mistral-medium-3@001",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3@001",
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistralai/mistral-medium-3@001",
     "region": "us-central1"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 8191,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-medium-3@001"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-medium-3@001"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium-c21211-r0-75",
   "model_name": "mistral-medium-c21211-r0-75",
   "display_name": "mistral-medium-c21211-r0-75",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-medium-c21211-r0-75"
    }
   ]
  },
  {
   "slug": "mistral/mistral-medium-latest",
   "model_name": "mistral-medium-latest",
   "display_name": "Mistral Medium",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/mistral-medium-latest"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/mistral-medium-latest"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "mistral/mistral-medium-latest"
    }
   ],
   "intro": "Balanced Mistral model for enterprise assistants, multilingual work, and tools",
   "released_at": "2026-04-29",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-medium",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true
   },
   "docs_url": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04",
   "model_type": "vision_understanding",
   "knowledge_cutoff": "2025-05",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-medium-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "mistral",
     "charge": "completion",
     "old": "2",
     "new": "7.5"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "mistral",
     "charge": "prompt",
     "old": "0.4",
     "new": "1.5"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "open_weights: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/mistral-moderation-2411",
   "model_name": "mistral-moderation-2411",
   "display_name": "mistral-moderation-2411",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "deprecated": true,
   "model_type": "safety_detection",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-moderation-2411"
    }
   ]
  },
  {
   "slug": "mistral/mistral-moderation-2603",
   "model_name": "mistral-moderation-2603",
   "display_name": "mistral-moderation-2603",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "safety_detection",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-moderation-2603"
    }
   ]
  },
  {
   "slug": "mistral/mistral-moderation-latest",
   "model_name": "mistral-moderation-latest",
   "display_name": "mistral-moderation-latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "model_type": "safety_detection",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-moderation-latest"
    }
   ]
  },
  {
   "slug": "mistral/mistral-nemo",
   "model_name": "mistral-nemo",
   "display_name": "Mistral Nemo",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+pydantic-prices+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistral-ai/mistral-nemo"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     }
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0575"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0975"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0287"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.17"
      }
     },
     "provider_model_id": "mistralai/mistral-nemo"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "mistralai/mistral-nemo"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.17"
      }
     },
     "provider_model_id": "mistralai/mistral-nemo"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.17"
      }
     },
     "provider_model_id": "mistralai/mistral-nemo"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "mistralai/mistral-nemo"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.17"
      }
     },
     "provider_model_id": "novita/mistralai/mistral-nemo"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "mistral/mistral-nemo"
    }
   ],
   "intro": "Efficient Mistral-NVIDIA open model for multilingual chat and local deployment",
   "released_at": "2024-07-01",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-nemo",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "docs_url": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-ai/mistral-nemo",
    "mistral-nemo:free",
    "mistral/mistral-nemo",
    "mistralai/mistral-nemo",
    "novita/mistralai/mistral-nemo"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral Nemo 是一款前沿大语言模型，在其参数规模下具备最先进的推理、世界知识和编程能力。",
    "zh-TW": "Mistral Nemo 是一款先進的大型語言模型，具備同級最佳的推理能力、世界知識與編碼能力。",
    "ja-JP": "Mistral Nemoは、同サイズ帯で最先端の推論力、世界知識、コーディング能力を備えた先進的なLLMです。",
    "ru-RU": "Mistral Nemo — передовая LLM с выдающимися возможностями рассуждения, знаниями о мире и кодированием для своей размерности."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/mistral-nemo-12b-instruct",
   "model_name": "mistral-nemo-12b-instruct",
   "display_name": "Mistral Nemo 12B Instruct",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "inference",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.038"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistral/mistral-nemo-12b-instruct"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 16000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-nemo",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-nemo-12b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Nemo 12B Instruct"
    }
   ]
  },
  {
   "slug": "mistral/mistral-nemo-base-2407",
   "model_name": "mistral-nemo-base-2407",
   "display_name": "Mistral Nemo Base 2407",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mistral-nemo-base-2407"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mistral-nemo-base-2407"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Nemo Base 2407"
    }
   ]
  },
  {
   "slug": "mistral/Mistral-Nemo-Instruct-2407",
   "model_name": "Mistral-Nemo-Instruct-2407",
   "display_name": "Mistral Nemo Instruct",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "unsloth/Mistral-Nemo-Instruct-2407"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.013"
      }
     },
     "provider_model_id": "mistral-nemo-instruct-2407"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistralai/Mistral-Nemo-Instruct-2407"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral-nemo-instruct-2407"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistralai/Mistral-Nemo-Instruct-2407"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistral-nemo-instruct-2407"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistralai/Mistral-Nemo-Instruct-2407"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistralai/Mistral-Nemo-Instruct-2407"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1207"
      }
     },
     "provider_model_id": "mistralai/Mistral-Nemo-Instruct-2407"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "mistral-nemo-instruct-2407"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistral-nemo-instruct-2407"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "deepinfra/mistralai/Mistral-Nemo-Instruct-2407"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2024-07-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-05",
   "model_type": "text_generation",
   "docs_url": "https://nebius.com/prices-ai-studio",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mistral-nemo-instruct-2407",
    "deepinfra/mistralai/Mistral-Nemo-Instruct-2407",
    "mistral-nemo-instruct-2407",
    "mistralai/Mistral-Nemo-Instruct-2407",
    "unsloth/Mistral-Nemo-Instruct-2407"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Nemo Instruct"
    }
   ]
  },
  {
   "slug": "mistral/Mistral-Nemo-Instruct-2407-FP8",
   "model_name": "Mistral-Nemo-Instruct-2407-FP8",
   "display_name": "Mistral Nemo",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "stackit",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "neuralmagic/Mistral-Nemo-Instruct-2407-FP8"
    }
   ],
   "released_at": "2024-07-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "mistral",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "neuralmagic/Mistral-Nemo-Instruct-2407-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Nemo"
    }
   ]
  },
  {
   "slug": "mistral/Mistral-Nemo-Instruct-2407-TEE",
   "model_name": "Mistral-Nemo-Instruct-2407-TEE",
   "display_name": "Mistral Nemo Instruct 2407 TEE",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0245"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0978"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01225"
      }
     },
     "provider_model_id": "unsloth/Mistral-Nemo-Instruct-2407-TEE"
    }
   ],
   "intro": "Efficient Mistral-NVIDIA open model for multilingual chat and local deployment",
   "released_at": "2024-07-01",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-nemo",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "unsloth/Mistral-Nemo-Instruct-2407-TEE"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Nemo Instruct 2407 TEE"
    }
   ]
  },
  {
   "slug": "mistral/mistral-nemo@2407",
   "model_name": "mistral-nemo@2407",
   "display_name": "mistral-nemo@2407",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-nemo@2407"
    }
   ]
  },
  {
   "slug": "mistral/mistral-nemo@latest",
   "model_name": "mistral-nemo@latest",
   "display_name": "mistral-nemo@latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-nemo@latest"
    }
   ]
  },
  {
   "slug": "mistral/mistral-nemotron",
   "model_name": "mistral-nemotron",
   "display_name": "mistral-nemotron",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/mistral-nemotron"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-06-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-nemotron"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-nemotron"
    }
   ]
  },
  {
   "slug": "mistral/mistral-ocr-2505",
   "model_name": "mistral-ocr-2505",
   "display_name": "mistral-ocr-2505",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0005"
      }
     },
     "provider_model_id": "mistralai/mistral-ocr-2505"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "structured_output": true,
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-ocr-2505"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-ocr-2505"
    }
   ]
  },
  {
   "slug": "mistral/mistral-saba",
   "model_name": "mistral-saba",
   "display_name": "Mistral: Saba",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "mistralai/mistral-saba"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.595"
      }
     },
     "provider_model_id": "mistralai/mistral-saba"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "mistralai/mistral-saba"
    }
   ],
   "intro": "Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. Read more at the blog post here",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "released_at": "2025-02-17",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2024-09",
   "family": "mistral",
   "deprecated": true,
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-saba"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral: Saba"
    }
   ]
  },
  {
   "slug": "mistral/mistral-saba-24b",
   "model_name": "mistral-saba-24b",
   "display_name": "mistral-saba-24b",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.79"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-saba-24b"
    }
   ]
  },
  {
   "slug": "mistral/mistral-saba-latest",
   "model_name": "mistral-saba-latest",
   "display_name": "Mistral Saba",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Saba"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small",
   "model_name": "mistral-small",
   "display_name": "mistral-small",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34249185"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34249185"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "mistralai/mistral-small"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4002"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral/mistral-small"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral/mistral-small"
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 8191,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "image",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Efficient Mistral model for fast chat, extraction, and production assistants",
   "released_at": "2024-09-17",
   "knowledge_cutoff": "2025-06",
   "family": "mistral-small",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-small",
    "mistralai/mistral-small"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral Small 适用于任何需要高效率和低延迟的语言任务。",
    "zh-TW": "Mistral Small 適用於任何需要高效率與低延遲的語言任務。",
    "ja-JP": "Mistral Smallは、高効率かつ低遅延を求めるあらゆる言語タスクに適しています。",
    "ru-RU": "Mistral Small подходит для любых языковых задач, где важны высокая эффективность и низкая задержка."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343112244",
     "new": "0.34249185"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343112244",
     "new": "0.34249185"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.2",
     "new": "0.08"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.075",
     "new": "0.05"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.342979791",
     "new": "0.343112244"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.342979791",
     "new": "0.343112244"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "0.3995",
     "new": "0.4002"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "0.1712",
     "new": "0.1715"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343242429",
     "new": "0.342979791"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343242429",
     "new": "0.342979791"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "scaleway",
     "charge": "completion",
     "old": "0.4007",
     "new": "0.3995"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "scaleway",
     "charge": "prompt",
     "old": "0.1717",
     "new": "0.1712"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343104252",
     "new": "0.343242429"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343104252",
     "new": "0.343242429"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.08",
     "new": "0.2"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.05",
     "new": "0.075"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343199361",
     "new": "0.343104252"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343199361",
     "new": "0.343104252"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.3414291",
     "new": "0.343199361"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.3414291",
     "new": "0.343199361"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-2409",
   "model_name": "mistral-small-2409",
   "display_name": "mistral-small-2409",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-small-2409"
    }
   ]
  },
  {
   "slug": "mistral/Mistral-Small-24B-Instruct-2501",
   "model_name": "Mistral-Small-24B-Instruct-2501",
   "display_name": "Mistral: Mistral Small 3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "mistral-small-24b-instruct-2501"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "unsloth/Mistral-Small-24B-Instruct-2501"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "mistralai/Mistral-Small-24B-Instruct-2501"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "mistralai/Mistral-Small-24B-Instruct-2501"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "mistral-small-24b-instruct-2501"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mistral-small-24b-instruct-2501"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "mistralai/mistral-small-24b-instruct-2501"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "mistralai/mistral-small-24b-instruct-2501"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistralai/Mistral-Small-24B-Instruct-2501"
    }
   ],
   "intro": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "released_at": "2025-12-29",
   "max_input_tokens": 32768,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2023-10",
   "family": "mistral-small",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mistral-small-24b-instruct-2501",
    "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501",
    "mistral-small-24b-instruct-2501",
    "mistral-small-24b-instruct-2501:free",
    "mistralai/Mistral-Small-24B-Instruct-2501",
    "mistralai/mistral-small-24b-instruct-2501",
    "unsloth/Mistral-Small-24B-Instruct-2501"
   ],
   "intro_i18n": {
    "zh-CN": "一个拥有 240 亿参数的模型，具备与更大模型相当的先进能力。",
    "zh-TW": "一個具備 24B 參數的模型，擁有與更大型模型相當的先進能力。",
    "ja-JP": "24Bパラメータを持つモデルで、より大規模なモデルに匹敵する最先端の性能を発揮します。",
    "ru-RU": "Модель с 24 миллиардами параметров, обладающая передовыми возможностями, сопоставимыми с более крупными моделями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral: Mistral Small 3"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-2501",
   "model_name": "mistral-small-2501",
   "display_name": "mistral-small-2501",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-small-2501"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-2503",
   "model_name": "mistral-small-2503",
   "display_name": "Mistral Small 3.1",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistral-ai/mistral-small-2503"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistralai/mistral-small-2503",
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistralai/mistral-small-2503",
     "region": "us-central1"
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral/mistral-small-2503"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "route/mistral-small-2503"
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "intro": "Efficient Mistral model for fast chat, extraction, and production assistants",
   "released_at": "2025-03-01",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-small",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-ai/mistral-small-2503",
    "mistral/mistral-small-2503",
    "mistralai/mistral-small-2503",
    "route/mistral-small-2503"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral Small 适用于任何需要高效率和低延迟的语言任务。",
    "zh-TW": "Mistral Small 適用於任何需要高效率與低延遲的語言任務。",
    "ja-JP": "Mistral Smallは、高効率かつ低遅延を求めるあらゆる言語タスクに適しています。",
    "ru-RU": "Mistral Small подходит для любых задач, связанных с языком, где важны высокая эффективность и низкая задержка."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Small 3.1"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-2503@001",
   "model_name": "mistral-small-2503@001",
   "display_name": "mistral-small-2503@001",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-small-2503@001"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-2506",
   "model_name": "mistral-small-2506",
   "display_name": "Mistral Small 3.2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "intro": "Efficient Mistral model for fast chat, extraction, and production assistants",
   "released_at": "2025-06-20",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-small",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "deprecated": true,
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Mistral Small是翻译、摘要和情感分析的经济高效、快速且可靠的选择。",
    "zh-TW": "Mistral Small是一款成本效益高、快速且可靠的選擇，適用於翻譯、摘要及情感分析。",
    "ja-JP": "Mistral Smallは、翻訳、要約、感情分析においてコスト効率が高く、迅速かつ信頼性の高いオプションです。",
    "ru-RU": "Mistral Small — экономичный, быстрый и надежный вариант для перевода, суммаризации и анализа настроений."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-2603",
   "model_name": "mistral-small-2603",
   "display_name": "Mistral Small 4",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+pydantic-prices+truefoundry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.128"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.51"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.013"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "mistralai/mistral-small-2603"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "mistralai/mistral-small-2603"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "mistral/mistral-small-2603"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "mistralai/mistral-small-2603"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    }
   ],
   "intro": "Fast Mistral production model for chat, extraction, and cost-sensitive agents",
   "released_at": "2026-03-16",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-small",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "benchmarks": {
    "intelligence_index": 19.6,
    "coding_index": 26.6,
    "agentic_index": 4.7
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-small-2603",
    "mistralai/mistral-small-2603"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral的强大混合模型，将指令、推理和编码能力统一于单一模型中。拥有1190亿参数，其中65亿为激活参数。",
    "zh-TW": "Mistral的強大混合模型，將指令、推理及編程能力統一於一個模型中。119B參數，6.5B激活。",
    "ja-JP": "Mistralの強力なハイブリッドモデルで、指示、推論、コーディング機能を単一モデルに統合しています。119Bパラメータ、6.5Bアクティブ。",
    "ru-RU": "Мощная гибридная модель Mistral, объединяющая возможности инструкций, рассуждений и кодирования в одной модели. 119B параметров с 6.5B активных."
   }
  },
  {
   "slug": "mistral/mistral-small-3",
   "model_name": "mistral-small-3",
   "display_name": "Mistral-Small-3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.101"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.303"
      }
     }
    }
   ],
   "released_at": "2025-01-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral-Small-3"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-3-1-24b-instruct-2503",
   "model_name": "mistral-small-3-1-24b-instruct-2503",
   "display_name": "Mistral Small 3.1 24B Instruct 2503",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "chutesai/Mistral-Small-3.1-24B-Instruct-2503"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34249185"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34249185"
      }
     },
     "provider_model_id": "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "chutesai/Mistral-Small-3.1-24B-Instruct-2503"
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "parallel_function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "released_at": "2025-12-29",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "chutesai",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "chutesai/Mistral-Small-3.1-24B-Instruct-2503",
    "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343112244",
     "new": "0.34249185"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343112244",
     "new": "0.34249185"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.342979791",
     "new": "0.343112244"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.342979791",
     "new": "0.343112244"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343242429",
     "new": "0.342979791"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343242429",
     "new": "0.342979791"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343104252",
     "new": "0.343242429"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343104252",
     "new": "0.343242429"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.343199361",
     "new": "0.343104252"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.343199361",
     "new": "0.343104252"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.3414291",
     "new": "0.343199361"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.3414291",
     "new": "0.343199361"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Small 3.1 24B Instruct 2503"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-3-2-24b-instruct",
   "model_name": "mistral-small-3-2-24b-instruct",
   "display_name": "Mistral Small 3.2 24B Instruct",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistral-small-3.2-24b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "mistralai/mistral-small-3.2-24b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/mistral-small-3.2-24b-instruct"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    }
   ],
   "intro": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "released_at": "2026-01-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-small",
   "knowledge_cutoff": "2023-10",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-small-3.2-24b-instruct",
    "mistral-small-3.2-24b-instruct:free",
    "mistralai/mistral-small-3.2-24b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Small 3.2 24B Instruct"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-3-2-2506",
   "model_name": "mistral-small-3-2-2506",
   "display_name": "mistral-small-3-2-2506",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "mistral/mistral-small-31-24b-instruct",
   "model_name": "mistral-small-31-24b-instruct",
   "display_name": "Mistral Small 31 24b Instruct",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-04-15",
   "max_input_tokens": 128000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Small 31 24b Instruct"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-4-119b",
   "model_name": "mistral-small-4-119b",
   "display_name": "Mistral Small 4 119B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "intro": "Efficient Mistral model for fast chat, extraction, and production assistants",
   "released_at": "2026-03-15",
   "max_input_tokens": 256000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-small",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Small 4 119B"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-4-119b-2603",
   "model_name": "mistral-small-4-119b-2603",
   "display_name": "mistral-small-4-119b-2603",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "mistralai/mistral-small-4-119b-2603"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/mistral-small-4-119b-2603"
    }
   ],
   "intro": "Efficient Mistral model for fast chat, extraction, and production assistants",
   "released_at": "2026-03-16",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-small-4-119b-2603",
    "mistralai/mistral-small-4-119b-2603:thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-small-4-119b-2603"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-creative",
   "model_name": "mistral-small-creative",
   "display_name": "Mistral: Mistral Small Creative",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistralai/mistral-small-creative"
    }
   ],
   "max_input_tokens": 32768,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "released_at": "2025-12-16",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-small-creative"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral: Mistral Small Creative"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small-latest",
   "model_name": "mistral-small-latest",
   "display_name": "Mistral Small",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "mistral/mistral-small-latest"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "mistral/mistral-small-latest"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "mistral/mistral-small-latest"
    }
   ],
   "intro": "Efficient Mistral model for fast chat, extraction, and production assistants",
   "released_at": "2026-03-16",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-small",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "image_output": true,
    "assistant_prefill": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "docs_url": "https://mistral.ai/pricing",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/mistral-small-latest"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral Small 是一款高性价比、快速且可靠的模型，适用于翻译、摘要和情感分析。",
    "zh-TW": "Mistral Small 是翻譯、摘要與情感分析等任務的高效、快速且可靠選擇。",
    "ja-JP": "Mistral Smallは、翻訳、要約、感情分析においてコスト効率が高く、迅速かつ信頼性の高い選択肢です。",
    "ru-RU": "Mistral Small — экономичное, быстрое и надежное решение для перевода, суммирования и анализа тональности."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/mistral-small3.2",
   "model_name": "mistral-small3.2",
   "display_name": "Mistral Small 3.2",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     }
    }
   ],
   "intro": "Efficient Mistral model for fast chat, extraction, and production assistants",
   "released_at": "2025-01-31",
   "max_input_tokens": 120000,
   "max_output_tokens": 120000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-small",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Small 3.2"
    }
   ]
  },
  {
   "slug": "mistral/mistral-tiny",
   "model_name": "mistral-tiny",
   "display_name": "mistral-tiny",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "mistralai/mistral-tiny"
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {
    "structured_output": true,
    "assistant_prefill": true
   },
   "intro": "Note: This model is being deprecated. Recommended replacement is the newer Ministral 8B",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/mistral-tiny"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/mistral-tiny-2407",
   "model_name": "mistral-tiny-2407",
   "display_name": "mistral-tiny-2407",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-tiny-2407"
    }
   ]
  },
  {
   "slug": "mistral/mistral-tiny-latest",
   "model_name": "mistral-tiny-latest",
   "display_name": "mistral-tiny-latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-tiny-latest"
    }
   ]
  },
  {
   "slug": "mistral/mistral-vibe-cli-fast",
   "model_name": "mistral-vibe-cli-fast",
   "display_name": "mistral-vibe-cli-fast",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-vibe-cli-fast"
    }
   ]
  },
  {
   "slug": "mistral/mistral-vibe-cli-latest",
   "model_name": "mistral-vibe-cli-latest",
   "display_name": "mistral-vibe-cli-latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-vibe-cli-latest"
    }
   ]
  },
  {
   "slug": "mistral/mistral-vibe-cli-with-tools",
   "model_name": "mistral-vibe-cli-with-tools",
   "display_name": "mistral-vibe-cli-with-tools",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral-vibe-cli-with-tools"
    }
   ]
  },
  {
   "slug": "mistral/mistral.ministral-3-14b-instruct",
   "model_name": "mistral.ministral-3-14b-instruct",
   "display_name": "Ministral 14B 3.0",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.206"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.206"
      }
     },
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.206"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.206"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2024-12-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 14B 3.0"
    }
   ]
  },
  {
   "slug": "mistral/mistral.ministral-3-3b-instruct",
   "model_name": "mistral.ministral-3-3b-instruct",
   "display_name": "Ministral 3 3B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.103"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.103"
      }
     },
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.103"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.103"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2025-12-02",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3 3B"
    }
   ]
  },
  {
   "slug": "mistral/mistral.ministral-3-8b-instruct",
   "model_name": "mistral.ministral-3-8b-instruct",
   "display_name": "Ministral 3 8B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      }
     },
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
   "released_at": "2024-12-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "ministral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ministral 3 8B"
    }
   ]
  },
  {
   "slug": "mistral/mistral.mistral-large-3-675b-instruct",
   "model_name": "mistral.mistral-large-3-675b-instruct",
   "display_name": "Mistral Large 3",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.61"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.82"
      }
     },
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76"
      }
     },
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.515"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.545"
      }
     },
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.78"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.33"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.61"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.82"
      }
     },
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.61"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.82"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.515"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.545"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.78"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.33"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.61"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.82"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work",
   "released_at": "2025-12-02",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "assistant_prefill": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Large 3"
    }
   ]
  },
  {
   "slug": "mistral/mistral.mistral-small-2402-v1:0",
   "model_name": "mistral.mistral-small-2402-v1:0",
   "display_name": "mistral.mistral-small-2402-v1:0",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "region": "us-east-1"
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 8191,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistral.mistral-small-2402-v1:0"
    }
   ]
  },
  {
   "slug": "mistral/mistral/mistral-7b-instruct-v0.1",
   "model_name": "mistral/mistral-7b-instruct-v0.1",
   "display_name": "Mistral 7B Instruct v0.1",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "workers-ai/@cf/mistral/mistral-7b-instruct-v0.1"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "@cf/mistral/mistral-7b-instruct-v0.1"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/Mistral-7B-Instruct-v0.1"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "mistralai/mistral-7b-instruct-v0.1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "mistral-7b-instruct-v0.1"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/Mistral-7B-Instruct-v0.1"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-04-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral",
   "capabilities": {
    "reasoning": true,
    "structured_output": true
   },
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/mistral/mistral-7b-instruct-v0.1",
    "mistral-7b-instruct-v0.1",
    "mistralai/Mistral-7B-Instruct-v0.1",
    "mistralai/mistral-7b-instruct-v0.1",
    "workers-ai/@cf/mistral/mistral-7b-instruct-v0.1"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral（7B）Instruct 以其在多种语言任务中的强大表现而闻名。",
    "zh-TW": "Mistral（7B）Instruct 以其在多種語言任務中的強大表現而聞名。",
    "ja-JP": "Mistral（7B）Instructは、多くの言語タスクで優れた性能を発揮します。",
    "ru-RU": "Mistral (7B) Instruct известна своей высокой производительностью в различных языковых задачах."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral 7B Instruct v0.1"
    }
   ]
  },
  {
   "slug": "mistral/mistralai/mistral-small-3.1-24b-instruct",
   "model_name": "mistralai/mistral-small-3.1-24b-instruct",
   "display_name": "Mistral Small 3.1 24B Instruct",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.351"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.555"
      }
     },
     "provider_model_id": "mistral-small-3.1-24b-instruct"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     },
     "provider_model_id": "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.351"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.555"
      }
     },
     "provider_model_id": "@cf/mistralai/mistral-small-3.1-24b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.351"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.555"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "mistral-small-3.1-24b-instruct"
    }
   ],
   "intro": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "released_at": "2025-03-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-small",
   "knowledge_cutoff": "2023-10",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/mistralai/mistral-small-3.1-24b-instruct",
    "mistral-small-3.1-24b-instruct",
    "mistral-small-3.1-24b-instruct:free",
    "mistralai/mistral-small-3.1-24b-instruct:free",
    "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Small 3.1 24B Instruct"
    }
   ]
  },
  {
   "slug": "mistral/mistralai/Mistral-Small-3.2-24B-Instruct-2506",
   "model_name": "mistralai/Mistral-Small-3.2-24B-Instruct-2506",
   "display_name": "Mistral Small 3.2 24B Instruct 2506",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     }
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "chutesai/Mistral-Small-3.2-24B-Instruct-2506"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "mistral-small-3.2-24b-instruct-2506"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Mistral-Small-3.2-24B-Instruct-2506"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "chutesai/Mistral-Small-3.2-24B-Instruct-2506"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "mistral-small-3.2-24b-instruct-2506"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral-small-3.2-24b-instruct-2506"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506"
    }
   ],
   "intro": "Efficient Mistral model for fast chat, extraction, and production assistants",
   "released_at": "2025-10-01",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 32000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-small",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Mistral-Small-3.2-24B-Instruct-2506",
    "chutesai/Mistral-Small-3.2-24B-Instruct-2506",
    "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506",
    "mistral-small-3.2-24b-instruct-2506"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Small 3.2 24B Instruct 2506"
    }
   ]
  },
  {
   "slug": "mistral/mistralai/mixtral-8x7b-instruct-v01",
   "model_name": "mistralai/mixtral-8x7b-instruct-v01",
   "display_name": "mistralai/mixtral-8x7b-instruct-v01",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nim/mistralai/mixtral-8x7b-instruct-v01"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nim/mistralai/mixtral-8x7b-instruct-v01"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mistralai/mixtral-8x7b-instruct-v01"
    }
   ]
  },
  {
   "slug": "mistral/mixtral-8x22b",
   "model_name": "mixtral-8x22b",
   "display_name": "Mixtral 8x22B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mixtral-8x22b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "family": "Mixtral",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mixtral-8x22b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mixtral 8x22B"
    }
   ]
  },
  {
   "slug": "mistral/mixtral-8x22b-instruct",
   "model_name": "mixtral-8x22b-instruct",
   "display_name": "Mistral: Mixtral 8x22B Instruct",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mixtral-8x22b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mixtral-8x22b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/mixtral-8x22b-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/mixtral-8x22b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/mixtral-8x22b-instruct"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistral/mixtral-8x22b-instruct"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "mistral/mixtral-8x22b-instruct"
    }
   ],
   "intro": "Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include:\n- strong math, coding, and reasoning\n- large context length (64k)\n- fluency in English, French, Italian, German, and Spanish",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "released_at": "2024-04-17",
   "max_input_tokens": 65536,
   "max_output_tokens": 13108,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2024-01",
   "family": "mistral",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.3
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mixtral-8x22b-instruct",
    "mistral/mixtral-8x22b-instruct",
    "mistralai/mixtral-8x22b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Mixtral MoE 8x22B Instruct v0.1 是 Mixtral MoE 8x22B v0.1 的指令微调版本，启用了聊天补全 API。",
    "zh-TW": "Mixtral MoE 8x22B Instruct v0.1 是 Mixtral MoE 8x22B v0.1 的指令微調版本，已啟用聊天補全 API。",
    "ja-JP": "Mixtral MoE 8x22B Instruct v0.1は、Mixtral MoE 8x22B v0.1の命令調整済みバージョンで、チャット補完APIが有効化されています。",
    "ru-RU": "Mixtral MoE 8x22B Instruct v0.1 — это дообученная на инструкциях версия модели Mixtral MoE 8x22B v0.1 с включенной поддержкой API завершения чата."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral: Mixtral 8x22B Instruct"
    }
   ]
  },
  {
   "slug": "mistral/mixtral-8x22b-instruct-hf",
   "model_name": "mixtral-8x22b-instruct-hf",
   "display_name": "mixtral-8x22b-instruct-hf",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mixtral-8x22b-instruct-hf"
    }
   ]
  },
  {
   "slug": "mistral/Mixtral-8x22B-Instruct-v0.1",
   "model_name": "Mixtral-8x22B-Instruct-v0.1",
   "display_name": "Mixtral 8x22B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8999999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8999999999999999"
      }
     },
     "provider_model_id": "mistralai/mixtral-8x22b-instruct-v0.1"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "mistralai/Mixtral-8x22B-Instruct-v0.1"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-12-11",
   "max_input_tokens": 65536,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mixtral",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/Mixtral-8x22B-Instruct-v0.1",
    "mistralai/mixtral-8x22b-instruct-v0.1"
   ],
   "intro_i18n": {
    "zh-CN": "Mixtral-8x22B Instruct（141B）是一款适用于重负载任务的超大语言模型。",
    "zh-TW": "Mixtral-8x22B Instruct（141B）是一款適用於重負載任務的超大型語言模型。",
    "ja-JP": "Mixtral-8x22B Instruct（141B）は、大規模なワークロードに対応する非常に大きなLLMです。",
    "ru-RU": "Mixtral-8x22B Instruct (141B) — очень крупная языковая модель для работы с тяжёлыми нагрузками."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mixtral 8x22B"
    }
   ]
  },
  {
   "slug": "mistral/mixtral-8x7b",
   "model_name": "mixtral-8x7b",
   "display_name": "Mixtral 8x7B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mixtral-8x7b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "knowledge_cutoff": "2023-09",
   "family": "Mixtral",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mixtral-8x7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mixtral 8x7B"
    }
   ]
  },
  {
   "slug": "mistral/mixtral-8x7b-32768",
   "model_name": "mixtral-8x7b-32768",
   "display_name": "Mixtral 8x7B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    }
   ],
   "capabilities": {
    "function_calling": true
   },
   "max_input_tokens": 32768,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Mixtral 8x7B 提供容错并行计算能力，适用于复杂任务。",
    "zh-TW": "Mixtral 8x7B 提供容錯的平行運算能力，適用於複雜任務。",
    "ja-JP": "Mixtral 8x7Bは、複雑なタスクに対してフォールトトレラントな並列計算を提供します。",
    "ru-RU": "Mixtral 8x7B обеспечивает отказоустойчивую параллельную обработку для сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mixtral 8x7B"
    }
   ]
  },
  {
   "slug": "mistral/mixtral-8x7b-instruct-hf",
   "model_name": "mixtral-8x7b-instruct-hf",
   "display_name": "Mixtral MoE 8x7B Instruct (HF version)",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mixtral-8x7b-instruct-hf"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mixtral-8x7b-instruct-hf"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mixtral MoE 8x7B Instruct (HF version)"
    }
   ]
  },
  {
   "slug": "mistral/Mixtral-8x7B-Instruct-v0.1",
   "model_name": "Mixtral-8x7B-Instruct-v0.1",
   "display_name": "Mixtral 8x7B Instruct v0.1",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.438"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "mixtral-8x7B-instruct-v0.1"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "mistralai/Mixtral-8x7B-Instruct-v0.1"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "mistralai/Mixtral-8x7B-Instruct-v0.1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "mistralai/mixtral-8x7b-instruct-v0.1"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "mixtral-8x7b-instruct-v0.1"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.54"
      }
     },
     "provider_model_id": "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "mistralai/Mixtral-8x7B-Instruct-v0.1"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2023-12-11",
   "knowledge_cutoff": "2023-09",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true
   },
   "family": "mixtral",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1",
    "mistralai/Mixtral-8x7B-Instruct-v0.1",
    "mistralai/mixtral-8x7b-instruct-v0.1",
    "mixtral-8x7B-instruct-v0.1",
    "mixtral-8x7b-instruct-v0.1"
   ],
   "intro_i18n": {
    "zh-CN": "Mixtral-8x7B Instruct（46.7B）为大规模数据处理提供高容量支持。",
    "zh-TW": "Mixtral-8x7B Instruct（46.7B）具備高容量，適合大規模資料處理。",
    "ja-JP": "Mixtral-8x7B Instruct（46.7B）は、大規模データ処理に対応する高容量モデルです。",
    "ru-RU": "Mixtral-8x7B Instruct (46.7B) обладает высокой пропускной способностью для обработки данных в крупном масштабе."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mixtral 8x7B Instruct v0.1"
    }
   ]
  },
  {
   "slug": "mistral/Mixtral-8x7B-Instruct-v0.1-FP8-Lora",
   "model_name": "Mixtral-8x7B-Instruct-v0.1-FP8-Lora",
   "display_name": "Mixtral-8x7B-Instruct-v0.1-FP8-Lora",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "mistralai/Mixtral-8x7B-Instruct-v0.1-FP8-Lora"
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/Mixtral-8x7B-Instruct-v0.1-FP8-Lora"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mixtral-8x7B-Instruct-v0.1-FP8-Lora"
    }
   ]
  },
  {
   "slug": "mistral/Mixtral-8x7B-v0.1",
   "model_name": "Mixtral-8x7B-v0.1",
   "display_name": "Mixtral-8x7B-v0.1",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "mistralai/Mixtral-8x7B-v0.1"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/Mixtral-8x7B-v0.1"
   ],
   "intro_i18n": {
    "zh-CN": "Mixtral 8x7B 是一款稀疏 MoE 模型，提升推理速度，适用于多语言和代码生成任务。",
    "zh-TW": "Mixtral 8x7B 是一款稀疏 MoE 模型，提升推理速度，適用於多語言與代碼生成任務。",
    "ja-JP": "Mixtral 8x7Bは、推論速度を向上させるスパースMoEモデルで、多言語およびコード生成タスクに適しています。",
    "ru-RU": "Mixtral 8x7B — разреженная модель MoE, ускоряющая вывод, подходит для многоязычных задач и генерации кода."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mixtral-8x7B-v0.1"
    }
   ]
  },
  {
   "slug": "mistral/Nous-Hermes-2-Mixtral-8x7B-DPO",
   "model_name": "Nous-Hermes-2-Mixtral-8x7B-DPO",
   "display_name": "Nouse Hermes 2 Mixtral 8x7B DPO",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "nous-hermes-2-mixtral-8x7b-dpo"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nous-hermes-2-mixtral-8x7b-dpo"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-01-15",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
    "accounts/fireworks/models/nous-hermes-2-mixtral-8x7b-dpo",
    "nous-hermes-2-mixtral-8x7b-dpo",
    "nousresearch/nous-hermes-2-mixtral-8x7b-dpo"
   ],
   "intro_i18n": {
    "zh-CN": "Nous Hermes 2 - Mixtral 8x7B-DPO（总参数 46.7B）是一款高精度指令模型，适用于复杂计算任务。",
    "zh-TW": "Nous Hermes 2 - Mixtral 8x7B-DPO（46.7B）是一款高精度指令模型，適用於複雜計算任務。",
    "ja-JP": "Nous Hermes 2 - Mixtral 8x7B-DPO（46.7B）は、複雑な計算に対応する高精度な命令モデルです。",
    "ru-RU": "Nous Hermes 2 - Mixtral 8x7B-DPO (46.7B) — высокоточная модель инструкций для сложных вычислений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nouse Hermes 2 Mixtral 8x7B DPO"
    }
   ]
  },
  {
   "slug": "mistral/Nous-Hermes-2-Mixtral-8x7B-SFT",
   "model_name": "Nous-Hermes-2-Mixtral-8x7B-SFT",
   "display_name": "Nous-Hermes-2-Mixtral-8x7B-SFT",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nous-Hermes-2-Mixtral-8x7B-SFT"
    }
   ]
  },
  {
   "slug": "mistral/open-codestral-mamba",
   "model_name": "open-codestral-mamba",
   "display_name": "open-codestral-mamba",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/technology/",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Codestral Mamba 是一款专注于代码生成的 Mamba 2 语言模型，支持高级编程与推理任务。",
    "zh-TW": "Codestral Mamba 是一款專注於程式碼生成的 Mamba 2 語言模型，支援進階程式設計與推理任務。",
    "ja-JP": "Codestral Mambaは、コード生成に特化したMamba 2言語モデルであり、高度なコーディングおよび推論タスクをサポートします。",
    "ru-RU": "Codestral Mamba — языковая модель Mamba 2, ориентированная на генерацию кода, поддерживающая сложные задачи программирования и рассуждения."
   }
  },
  {
   "slug": "mistral/open-mistral-7b",
   "model_name": "open-mistral-7b",
   "display_name": "Mistral 7B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "mistral/open-mistral-7b"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2023-09-27",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 8000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/open-mistral-7b"
   ],
   "intro_i18n": {
    "zh-CN": "Mistral 7B 是一款紧凑但高性能的模型，适合批量处理和分类、文本生成等简单任务，具备良好的推理能力。",
    "zh-TW": "Mistral 7B 體積小但效能強，適合批次處理與分類、文字生成等簡單任務，具備穩定推理能力。",
    "ja-JP": "Mistral 7Bはコンパクトながら高性能であり、バッチ処理や分類、テキスト生成などのシンプルなタスクに強く、堅実な推論能力を備えています。",
    "ru-RU": "Mistral 7B — компактная, но производительная модель, хорошо подходящая для пакетной обработки и простых задач, таких как классификация и генерация текста, с уверенными навыками рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/open-mistral-nemo",
   "model_name": "open-mistral-nemo",
   "display_name": "Open Mistral Nemo",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2024-07-01",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-nemo",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true
   },
   "docs_url": "https://mistral.ai/technology/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Mistral Nemo 是与 Nvidia 联合开发的 12B 模型，在推理和编程方面表现强劲，易于集成。",
    "zh-TW": "Mistral Nemo 是與 Nvidia 共同開發的 12B 模型，具備強大的推理與程式設計能力，易於整合。",
    "ja-JP": "Mistral Nemoは、Nvidiaと共同開発された12Bモデルで、優れた推論およびコーディング性能を持ち、統合も容易です。",
    "ru-RU": "Mistral Nemo — модель на 12B параметров, совместно разработанная с Nvidia, демонстрирующая высокие результаты в рассуждении и программировании, с легкой интеграцией."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "mistral/open-mistral-nemo-2407",
   "model_name": "open-mistral-nemo-2407",
   "display_name": "open-mistral-nemo-2407",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "docs_url": "https://mistral.ai/technology/",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "assistant_prefill": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    }
   ]
  },
  {
   "slug": "mistral/open-mixtral-8x22b",
   "model_name": "open-mixtral-8x22b",
   "display_name": "Mixtral 8x22B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2024-04-17",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 64000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mixtral",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Mixtral 8x22B 是一款大型 MoE 模型，适用于复杂任务，具备强大的推理能力和更高的吞吐量。",
    "zh-TW": "Mixtral 8x22B 是一款大型 MoE 模型，適用於複雜任務，具備強大推理能力與高吞吐量。",
    "ja-JP": "Mixtral 8x22Bは、複雑なタスクに対応する大型MoEモデルで、強力な推論能力と高いスループットを提供します。",
    "ru-RU": "Mixtral 8x22B — крупная модель MoE для сложных задач, обеспечивающая мощные рассуждения и высокую пропускную способность."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/open-mixtral-8x7b",
   "model_name": "open-mixtral-8x7b",
   "display_name": "Mixtral 8x7B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2023-12-11",
   "knowledge_cutoff": "2024-01",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mixtral",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "assistant_prefill": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Mixtral 8x7B 是一款稀疏 MoE 模型，提升了推理速度，适用于多语言和代码生成任务。",
    "zh-TW": "Mixtral 8x7B 是一款稀疏 MoE 模型，提升推理速度，適合多語言與程式碼生成任務。",
    "ja-JP": "Mixtral 8x7Bは、推論速度を向上させるスパースMoEモデルであり、多言語およびコード生成タスクに適しています。",
    "ru-RU": "Mixtral 8x7B — разреженная модель MoE, ускоряющая вывод, подходящая для многоязычных задач и генерации кода."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/OpenHermes-2-Mistral-7B",
   "model_name": "OpenHermes-2-Mistral-7B",
   "display_name": "OpenHermes 2 Mistral 7B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openhermes-2-mistral-7b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "teknium/OpenHermes-2-Mistral-7B"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/openhermes-2-mistral-7b",
    "openhermes-2-mistral-7b",
    "teknium/OpenHermes-2-Mistral-7B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenHermes 2 Mistral 7B"
    }
   ]
  },
  {
   "slug": "mistral/openhermes-2.5-mistral-7b",
   "model_name": "openhermes-2.5-mistral-7b",
   "display_name": "Openhermes2.5 Mistral 7B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.17"
      }
     },
     "provider_model_id": "teknium/openhermes-2.5-mistral-7b"
    }
   ],
   "released_at": "2024-04-24",
   "max_input_tokens": 4096,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "teknium/openhermes-2.5-mistral-7b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Openhermes2.5 Mistral 7B"
    }
   ]
  },
  {
   "slug": "mistral/OpenHermes-2p5-Mistral-7B",
   "model_name": "OpenHermes-2p5-Mistral-7B",
   "display_name": "OpenHermes 2.5 Mistral 7B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openhermes-2p5-mistral-7b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "teknium/OpenHermes-2p5-Mistral-7B"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/openhermes-2p5-mistral-7b",
    "openhermes-2p5-mistral-7b",
    "teknium/OpenHermes-2p5-Mistral-7B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenHermes 2.5 Mistral 7B"
    }
   ]
  },
  {
   "slug": "mistral/pixtral-12b",
   "model_name": "pixtral-12b",
   "display_name": "Pixtral 12B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+pydantic-prices+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "mistral/pixtral-12b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistralai/pixtral-12b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "mistral/pixtral-12b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "mistral/pixtral-12b"
    }
   ],
   "intro": "Mistral vision-language model for image understanding and multimodal chat",
   "released_at": "2024-09-01",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "pixtral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/pixtral-12b",
    "mistralai/pixtral-12b"
   ],
   "intro_i18n": {
    "zh-CN": "一款具备图像理解与文本处理能力的 120 亿参数模型。",
    "zh-TW": "一款具備圖像理解與文本處理能力的 12B 模型。",
    "ja-JP": "画像理解とテキスト処理を備えた12Bモデルです。",
    "ru-RU": "Модель на 12B параметров с пониманием изображений и текста."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/pixtral-12b-2409",
   "model_name": "pixtral-12b-2409",
   "display_name": "pixtral-12b-2409",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "open_weights": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "intro": "Mistral vision-language model for image understanding and multimodal chat",
   "released_at": "2024-09-25",
   "knowledge_cutoff": "2024-09",
   "family": "pixtral",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Pixtral 擅长图表/图像理解、文档问答、多模态推理和指令遵循。支持原始分辨率/比例图像输入，能在 128K 上下文窗口中处理任意数量图像。",
    "zh-TW": "Pixtral 擅長圖表/圖像理解、文件問答、多模態推理與指令遵循。可原生解析圖像解析度與比例，並在 128K 上下文中處理任意數量圖像。",
    "ja-JP": "Pixtralは、グラフや画像の理解、文書QA、マルチモーダル推論、指示の追従に優れています。ネイティブ解像度・アスペクト比で画像を処理し、128Kのコンテキストウィンドウ内で任意の数の画像を扱えます。",
    "ru-RU": "Pixtral отлично справляется с анализом графиков и изображений, вопросами по документам, мультимодальным рассуждением и выполнением инструкций. Он обрабатывает изображения в их исходном разрешении и соотношении сторон, поддерживая любое количество изображений в контексте до 128K."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "mistral/pixtral-large",
   "model_name": "pixtral-large",
   "display_name": "Pixtral Large",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistral/pixtral-large"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistral/pixtral-large"
    }
   ],
   "intro": "Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of Mistral Large 2. The model is able to understand documents, charts and natural images.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "released_at": "2024-11-01",
   "knowledge_cutoff": "2024-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "pixtral",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/pixtral-large"
   ],
   "intro_i18n": {
    "zh-CN": "Pixtral Large 是我们多模态系列的第二款模型，具备前沿级图像理解能力。可处理文档、图表和自然图像，同时保留 Mistral Large 2 的领先文本理解能力。",
    "zh-TW": "Pixtral Large 是我們多模態系列的第二款模型，具備前沿級圖像理解能力。可處理文件、圖表與自然圖像，同時保有 Mistral Large 2 的頂尖文本理解能力。",
    "ja-JP": "Pixtral Largeは、マルチモーダルファミリーの第2弾で、最先端の画像理解を備えています。文書、チャート、自然画像を処理しつつ、Mistral Large 2の優れたテキスト理解力を維持します。",
    "ru-RU": "Pixtral Large — вторая модель в нашей мультимодальной линейке с передовым пониманием изображений. Обрабатывает документы, графики и естественные изображения, сохраняя при этом выдающееся понимание текста от Mistral Large 2."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pixtral Large"
    }
   ]
  },
  {
   "slug": "mistral/pixtral-large-2411",
   "model_name": "pixtral-large-2411",
   "display_name": "pixtral-large-2411",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistralai/pixtral-large-2411"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/pixtral-large-2411"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "open_weights": true,
    "stream": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "intro": "Mistral vision-language model for image understanding and multimodal chat",
   "released_at": "2024-11-19",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistralai/pixtral-large-2411"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/pixtral-large-2502",
   "model_name": "pixtral-large-2502",
   "display_name": "Pixtral Large (25.02)",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistral.pixtral-large-2502-v1:0",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "eu.mistral.pixtral-large-2502-v1:0",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "eu.mistral.pixtral-large-2502-v1:0",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "eu.mistral.pixtral-large-2502-v1:0",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "eu.mistral.pixtral-large-2502-v1:0",
     "region": "eu-west-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "us.mistral.pixtral-large-2502-v1:0",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "us.mistral.pixtral-large-2502-v1:0",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "us.mistral.pixtral-large-2502-v1:0",
     "region": "us-west-2"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.789"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.366"
      }
     }
    }
   ],
   "intro": "Mistral vision-language model for image understanding and multimodal chat",
   "released_at": "2025-04-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "eu.mistral.pixtral-large-2502-v1:0",
    "mistral.pixtral-large-2502-v1:0",
    "us.mistral.pixtral-large-2502-v1:0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pixtral Large (25.02)"
    }
   ]
  },
  {
   "slug": "mistral/pixtral-large-latest",
   "model_name": "pixtral-large-latest",
   "display_name": "Pixtral Large",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistral/pixtral-large-latest"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "mistral/pixtral-large-latest"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "mistral/pixtral-large-latest"
    }
   ],
   "intro": "Mistral's larger vision model for document-heavy image understanding and chat",
   "released_at": "2024-11-01",
   "knowledge_cutoff": "2024-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "pixtral",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/pixtral-large-latest"
   ],
   "intro_i18n": {
    "zh-CN": "Pixtral Large 是基于 Mistral Large 2 构建的 124B 参数开源多模态模型，是我们多模态系列中的第二款，具备前沿级图像理解能力。",
    "zh-TW": "Pixtral Large 是一款擁有 124B 參數的開源多模態模型，基於 Mistral Large 2 架構，是我們多模態系列中的第二代，具備前沿級圖像理解能力。",
    "ja-JP": "Pixtral Largeは、Mistral Large 2を基盤とした124Bパラメータのオープンマルチモーダルモデルで、最先端の画像理解を備えたPixtralファミリーの第2世代です。",
    "ru-RU": "Pixtral Large — это открытая мультимодальная модель с 124 миллиардами параметров, построенная на базе Mistral Large 2. Это вторая модель в нашей мультимодальной линейке, обладающая передовыми возможностями понимания изображений."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "mistral/snorkel-mistral-7b-pairrm-dpo",
   "model_name": "snorkel-mistral-7b-pairrm-dpo",
   "display_name": "Snorkel Mistral PairRM DPO",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/snorkel-mistral-7b-pairrm-dpo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Snorkel Mistral PairRM DPO"
    }
   ]
  },
  {
   "slug": "mistral/Snorkel-Mistral-PairRM-DPO",
   "model_name": "Snorkel-Mistral-PairRM-DPO",
   "display_name": "Snorkel-Mistral-PairRM-DPO",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "snorkelai/Snorkel-Mistral-PairRM-DPO"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "snorkelai/Snorkel-Mistral-PairRM-DPO"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Snorkel-Mistral-PairRM-DPO"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-mini-2507",
   "model_name": "voxtral-mini-2507",
   "display_name": "voxtral-mini-2507",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0000166667"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "deprecated": true,
   "modalities": {
    "input": [
     "audio",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-mini-2507"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-mini-2602",
   "model_name": "voxtral-mini-2602",
   "display_name": "voxtral-mini-2602",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00005"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "structured_output": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-mini-2602"
    }
   ]
  },
  {
   "slug": "mistral/Voxtral-Mini-3B-2507",
   "model_name": "Voxtral-Mini-3B-2507",
   "display_name": "Voxtral Mini 3B 2507",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0412"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0412"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistral.voxtral-mini-3b-2507",
     "region": "us-west-2"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0000166666666666667"
      }
     },
     "provider_model_id": "mistralai/Voxtral-Mini-3B-2507"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "mistralai/Voxtral-Mini-3B-2507"
    }
   ],
   "intro": "Efficient Mistral model for fast chat, extraction, and production assistants",
   "released_at": "2024-12-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "audio",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral",
   "capabilities": {
    "function_calling": true,
    "audio_input": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral.voxtral-mini-3b-2507",
    "mistralai/Voxtral-Mini-3B-2507"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Voxtral Mini 3B 2507"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-mini-latest",
   "model_name": "voxtral-mini-latest",
   "display_name": "Voxtral Mini",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00001666666667"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "mistral/voxtral-mini-latest"
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "speech_recognition",
   "capabilities": {
    "pdf_input": true,
    "audio_input": true
   },
   "released_at": "2026-04-22",
   "modalities": {
    "input": [
     "audio",
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/voxtral-mini-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-mini-latest"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-mini-realtime-2602",
   "model_name": "voxtral-mini-realtime-2602",
   "display_name": "voxtral-mini-realtime-2602",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0001"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "realtime_omni",
   "capabilities": {
    "structured_output": true,
    "assistant_prefill": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-mini-realtime-2602"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-mini-realtime-latest",
   "model_name": "voxtral-mini-realtime-latest",
   "display_name": "voxtral-mini-realtime-latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0001"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "realtime_omni",
   "capabilities": {
    "structured_output": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-mini-realtime-latest"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-mini-transcribe-2507",
   "model_name": "voxtral-mini-transcribe-2507",
   "display_name": "voxtral-mini-transcribe-2507",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0000333333"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "deprecated": true,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-mini-transcribe-2507"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-mini-transcribe-realtime-2602",
   "model_name": "voxtral-mini-transcribe-realtime-2602",
   "display_name": "voxtral-mini-transcribe-realtime-2602",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0001"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "realtime_speech_recognition",
   "capabilities": {
    "structured_output": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-mini-transcribe-realtime-2602"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-mini-tts-260213",
   "model_name": "voxtral-mini-tts-260213",
   "display_name": "voxtral-mini-tts-260213",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "16"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_input": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-mini-tts-260213"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-mini-tts-2603",
   "model_name": "voxtral-mini-tts-2603",
   "display_name": "voxtral-mini-tts-2603",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "16"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "function_calling": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-mini-tts-2603"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-mini-tts-latest",
   "model_name": "voxtral-mini-tts-latest",
   "display_name": "voxtral-mini-tts-latest",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "16"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "function_calling": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-mini-tts-latest"
    }
   ]
  },
  {
   "slug": "mistral/Voxtral-Small-24B-2507",
   "model_name": "Voxtral-Small-24B-2507",
   "display_name": "Voxtral Small 24B",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "voxtral-small-24b-2507"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+computeprices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.333333",
        "completion": "0.428571"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.166667",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.333333",
        "completion": "0.428571"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.103"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.309"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.47"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.103"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.309"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.47"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral.voxtral-small-24b-2507",
     "region": "us-west-2"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00005"
      }
     },
     "provider_model_id": "mistralai/Voxtral-Small-24B-2507"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0023"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0023"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "mistralai/Voxtral-Small-24B-2507"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "mistralai/voxtral-small-24b-2507"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "audio_input": {
       "unit": "per_second",
       "price": "0.0001"
      }
     },
     "provider_model_id": "mistralai/voxtral-small-24b-2507"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+computeprices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "voxtral-small-24b-2507"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29999999999999993"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.009999999999999998"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.006"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mistralai/voxtral-small-24b-2507"
    }
   ],
   "intro": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "released_at": "2025-03-01",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "audio",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voxtral",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.2,
     "top_p": 0.95
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral.voxtral-small-24b-2507",
    "mistralai/Voxtral-Small-24B-2507",
    "mistralai/voxtral-small-24b-2507",
    "voxtral-small-24b-2507"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Voxtral Small 24B"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-small-2507",
   "model_name": "voxtral-small-2507",
   "display_name": "voxtral-small-2507",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0000666667"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": []
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "audio_input": true,
    "prompt_caching": true
   },
   "released_at": "2026-02-02",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-small-2507"
    }
   ]
  },
  {
   "slug": "mistral/voxtral-small-latest",
   "model_name": "voxtral-small-latest",
   "display_name": "Voxtral Small",
   "vendor": "mistral",
   "pricing": [
    {
     "provider": "mistral",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0000666667"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "mistral/voxtral-small-latest"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "audio",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "audio_input": true,
    "pdf_input": true
   },
   "released_at": "2026-04-22",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral/voxtral-small-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voxtral-small-latest"
    }
   ]
  },
  {
   "slug": "moonshotai/alicloud-kimi-k2-instruct",
   "model_name": "alicloud-kimi-k2-instruct",
   "display_name": "alicloud-kimi-k2-instruct",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.548"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.192"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "alicloud-kimi-k2-instruct"
    }
   ]
  },
  {
   "slug": "moonshotai/alicloud-kimi-k2-thinking",
   "model_name": "alicloud-kimi-k2-thinking",
   "display_name": "alicloud-kimi-k2-thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.548"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.192"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "alicloud-kimi-k2-thinking"
    }
   ]
  },
  {
   "slug": "moonshotai/alicloud-kimi-k2.5",
   "model_name": "alicloud-kimi-k2.5",
   "display_name": "alicloud-kimi-k2.5",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.548"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.877"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0959"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "alicloud-kimi-k2.5"
    }
   ]
  },
  {
   "slug": "moonshotai/azure-kimi-k2.5",
   "model_name": "azure-kimi-k2.5",
   "display_name": "azure-kimi-k2.5",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure-kimi-k2.5"
    }
   ]
  },
  {
   "slug": "moonshotai/cc-kimi-dev-72b",
   "model_name": "cc-kimi-dev-72b",
   "display_name": "cc-kimi-dev-72b",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.28"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-kimi-dev-72b"
    }
   ]
  },
  {
   "slug": "moonshotai/cc-kimi-for-coding",
   "model_name": "cc-kimi-for-coding",
   "display_name": "cc-kimi-for-coding",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-kimi-for-coding"
    }
   ]
  },
  {
   "slug": "moonshotai/cc-kimi-k2-instruct",
   "model_name": "cc-kimi-k2-instruct",
   "display_name": "cc-kimi-k2-instruct",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-kimi-k2-instruct"
    }
   ]
  },
  {
   "slug": "moonshotai/cc-kimi-k2-instruct-0905",
   "model_name": "cc-kimi-k2-instruct-0905",
   "display_name": "cc-kimi-k2-instruct-0905",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-kimi-k2-instruct-0905"
    }
   ]
  },
  {
   "slug": "moonshotai/cc-kimi-k2-thinking",
   "model_name": "cc-kimi-k2-thinking",
   "display_name": "cc-kimi-k2-thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.548"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.192"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-kimi-k2-thinking"
    }
   ]
  },
  {
   "slug": "moonshotai/chat-completion/models/Kimi-K2_6",
   "model_name": "chat-completion/models/Kimi-K2_6",
   "display_name": "Kimi K2.6",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "moonshotai/chat-completion/models/Kimi-K2_6"
    }
   ],
   "intro": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
   "released_at": "2026-04-21",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/chat-completion/models/Kimi-K2_6"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.6"
    }
   ]
  },
  {
   "slug": "moonshotai/fireworks/routers/kimi-k2p6-turbo",
   "model_name": "fireworks/routers/kimi-k2p6-turbo",
   "display_name": "Kimi K2.6 Turbo",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "accounts/fireworks/routers/kimi-k2p6-turbo"
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2026-04-17",
   "max_input_tokens": 262000,
   "max_output_tokens": 262000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/routers/kimi-k2p6-turbo"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.6 Turbo"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi K2.5",
   "model_name": "Kimi K2.5",
   "display_name": "deepinfra/Kimi K2.5",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "deepinfra/Kimi K2.5"
    }
   ],
   "released_at": "2026-03-31",
   "max_input_tokens": 262100,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/Kimi K2.5",
    "parasail/Kimi K2.5"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra/Kimi K2.5"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-2.6",
   "model_name": "kimi-2.6",
   "display_name": "moonshot/kimi-2.6",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.856229625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.99573825"
      }
     },
     "provider_model_id": "moonshot/kimi-2.6"
    }
   ],
   "released_at": "2026-04-14",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshot/kimi-2.6"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.00297618",
     "new": "3.99573825"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.85778061",
     "new": "0.856229625"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.001430895",
     "new": "4.00297618"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.8574494775",
     "new": "0.85778061"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.004495005",
     "new": "4.001430895"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.8581060725",
     "new": "0.8574494775"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.00288294",
     "new": "4.004495005"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.85776063",
     "new": "0.8581060725"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.003992545",
     "new": "4.00288294"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.8579984025",
     "new": "0.85776063"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "3.9833395",
     "new": "4.003992545"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.85357275",
     "new": "0.8579984025"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "moonshot/kimi-2.6"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-Dev-72B",
   "model_name": "Kimi-Dev-72B",
   "display_name": "moonshotai/Kimi-Dev-72B",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.28"
      }
     },
     "provider_model_id": "moonshotai/Kimi-Dev-72B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "kimi-dev-72b:free"
    }
   ],
   "max_input_tokens": 131072,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kimi-dev-72b:free",
    "moonshotai/Kimi-Dev-72B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "moonshotai/Kimi-Dev-72B"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2",
   "model_name": "Kimi-K2",
   "display_name": "Kimi K2",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "kimi-k2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.856229625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.99573825"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.285"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.31884"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "vertex/kimi-k2"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     },
     "provider_model_id": "kimi-k2"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2"
    }
   ],
   "intro": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "released_at": "2025-08-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "knowledge_cutoff": "2024-10",
   "deprecated": true,
   "status": "deprecated",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kimi-k2",
    "kimi-k2:free",
    "moonshotai/Kimi-K2",
    "moonshotai/kimi-k2",
    "vertex/kimi-k2"
   ],
   "intro_i18n": {
    "zh-CN": "Kimi K2 是 Moonshot AI 推出的超大规模 MoE 模型，拥有 1 万亿总参数和每次前向传播 320 亿激活参数，专为高级工具使用、推理和代码合成等智能体能力优化。",
    "zh-TW": "Kimi K2 是 Moonshot AI 推出的大型 MoE 模型，總參數達 1 兆，每次前向傳遞啟用 32B，針對智能代理能力（如進階工具使用、推理與程式碼合成）進行優化。",
    "ja-JP": "Kimi K2は、Moonshot AIによる大規模MoEモデルで、総パラメータ1兆、1回のフォワードパスで32Bのアクティブパラメータを持ち、高度なツール使用、推論、コード合成などのエージェント機能に最適化されています。",
    "ru-RU": "Kimi K2 — крупная модель MoE от Moonshot AI с 1 триллионом параметров и 32 миллиардами активных на проход, оптимизирована для агентных возможностей, включая продвинутую работу с инструментами, логическое мышление и синтез кода."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.00297618",
     "new": "3.99573825"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.85778061",
     "new": "0.856229625"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.001430895",
     "new": "4.00297618"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.8574494775",
     "new": "0.85778061"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.75",
     "new": "0.74"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "llmgateway",
     "charge": "completion",
     "old": "2.294",
     "new": "2.3"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "llmgateway",
     "charge": "prompt",
     "old": "0.574",
     "new": "0.57"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.004495005",
     "new": "4.001430895"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.8581060725",
     "new": "0.8574494775"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.74",
     "new": "0.75"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.00288294",
     "new": "4.004495005"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.85776063",
     "new": "0.8581060725"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.75",
     "new": "0.74"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.003992545",
     "new": "4.00288294"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.8579984025",
     "new": "0.85776063"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "3.9833395",
     "new": "4.003992545"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.85357275",
     "new": "0.8579984025"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.74",
     "new": "0.75"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-0711",
   "model_name": "kimi-k2-0711",
   "display_name": "Kimi K2 (07/11)",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.16"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5700000000000001"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.23"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-0711"
    }
   ],
   "intro": "Kimi model for long-context chat, coding, and agentic reasoning",
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/kimi-k2-0711"
   ],
   "intro_i18n": {
    "zh-CN": "Kimi K2 0711 是 Kimi 系列中的指令微调版本，适用于高质量代码生成和工具使用。",
    "zh-TW": "Kimi K2 0711 是 Kimi 系列中的指令變體，適用於高品質程式碼生成與工具使用。",
    "ja-JP": "Kimi K2 0711は、Kimiシリーズのインストラクションバリアントで、高品質なコード生成とツール使用に適しています。",
    "ru-RU": "Kimi K2 0711 — вариант instruct в серии Kimi, предназначен для высококачественного кода и использования инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 (07/11)"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-0711-preview",
   "model_name": "kimi-k2-0711-preview",
   "display_name": "Kimi K2 0711",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "moonshotai-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "intro": "Kimi model for long-context chat, coding, and agentic reasoning",
   "released_at": "2025-07-14",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "web_search": true,
    "stream": true
   },
   "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2",
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-05-25",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2-0905",
   "model_name": "Kimi-K2-0905",
   "display_name": "Kimi K2 0905",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.39999999999999997"
      }
     },
     "provider_model_id": "kimi-k2-0905"
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "kimi-k2-0905"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-0905"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-0905"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "kimi-k2-0905"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-0905"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-0905"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-0905"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-0905"
    }
   ],
   "intro": "Kimi model for long-context chat, coding, and agentic reasoning",
   "released_at": "2025-09-08",
   "max_input_tokens": 256000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-10",
   "family": "kimi-k2",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kimi-k2-0905",
    "moonshotai/kimi-k2-0905",
    "moonshotai/kimi-k2-0905:exacto"
   ],
   "intro_i18n": {
    "zh-CN": "Kimi K2 0905 是一次更新，扩展了上下文和推理能力，并进行了编程优化。",
    "zh-TW": "Kimi K2 0905 是一項更新，提升了上下文擴展與推理效能，並優化了程式碼能力。",
    "ja-JP": "Kimi K2 0905は、コンテキストと推論性能を拡張し、コーディング最適化を施したアップデート版です。",
    "ru-RU": "Kimi K2 0905 — обновление, расширяющее контекст и логические возможности с оптимизациями для программирования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 0905"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-0905-preview",
   "model_name": "kimi-k2-0905-preview",
   "display_name": "Kimi K2 0905",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.632"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.53"
      }
     }
    },
    {
     "provider": "moonshotai-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "intro": "Kimi model for long-context chat, coding, and agentic reasoning",
   "released_at": "2025-09-05",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "web_search": true,
    "stream": true
   },
   "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2",
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-05-25",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2-Instruct",
   "model_name": "Kimi-K2-Instruct",
   "display_name": "Kimi-K2-Instruct",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.16"
      }
     },
     "provider_model_id": "kimi-k2-instruct"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.551"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.646"
      }
     },
     "provider_model_id": "kimi-k2-instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "kimi-k2-instruct"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-instruct"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct"
    },
    {
     "provider": "hyperbolic",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-instruct"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "kimi-k2-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-instruct"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "novita/moonshotai/kimi-k2-instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "kimi-k2-instruct"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     },
     "provider_model_id": "kimi-k2-instruct"
    }
   ],
   "intro": "Kimi model for long-context chat, coding, and agentic reasoning",
   "released_at": "2025-07-14",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "docs_url": "https://fireworks.ai/models/fireworks/kimi-k2-instruct",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/kimi-k2-instruct",
    "kimi-k2-instruct",
    "moonshotai/Kimi-K2-Instruct",
    "moonshotai/kimi-k2-instruct",
    "novita/moonshotai/kimi-k2-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Kimi K2 Instruct 是 Kimi 官方推出的推理模型，支持长上下文，适用于代码、问答等任务。",
    "zh-TW": "Kimi K2 Instruct 是 Kimi 官方推出的推理模型，支援長上下文，適用於程式碼、問答等多種任務。",
    "ja-JP": "Kimi K2 Instruct は、コードやQAなどの長文コンテキストに対応した、Kimi公式の推論モデルです。",
    "ru-RU": "Kimi K2 Instruct — официальная модель логического мышления от Kimi с поддержкой длинного контекста для кода, вопросов-ответов и других задач."
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35934752",
     "new": "2.35686304"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35982928",
     "new": "2.35934752"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35899392",
     "new": "2.35982928"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.3548632",
     "new": "2.35899392"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi-K2-Instruct"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-instruct-0711",
   "model_name": "kimi-k2-instruct-0711",
   "display_name": "Kimi K2 0711",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-instruct-0711"
    }
   ],
   "intro": "Kimi model for long-context chat, coding, and agentic reasoning",
   "released_at": "2025-07-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/kimi-k2-instruct-0711"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 0711"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2-Instruct-0905",
   "model_name": "Kimi-K2-Instruct-0905",
   "display_name": "Kimi-K2-Instruct-0905",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "baseten",
     "official": false,
     "source": "helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct-0905"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.195"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct-0905"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct-0905"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "kimi-k2-instruct-0905"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "kimi-k2-instruct-0905"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct-0905"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.195"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct-0905"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct-0905"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-instruct-0905"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct-0905"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "hf:moonshotai/Kimi-K2-Instruct-0905"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     },
     "provider_model_id": "deepinfra/moonshotai/Kimi-K2-Instruct-0905"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Instruct-0905"
    }
   ],
   "intro": "Kimi model for long-context chat, coding, and agentic reasoning",
   "released_at": "2025-09-04",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "docs_url": "https://app.fireworks.ai/models/fireworks/kimi-k2-instruct-0905",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Pro/moonshotai/Kimi-K2-Instruct-0905",
    "accounts/fireworks/models/kimi-k2-instruct-0905",
    "deepinfra/moonshotai/Kimi-K2-Instruct-0905",
    "hf:moonshotai/Kimi-K2-Instruct-0905",
    "kimi-k2-instruct-0905",
    "moonshotai/Kimi-K2-Instruct-0905",
    "moonshotai/kimi-k2-instruct-0905"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi-K2-Instruct-0905"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-instruct-fast",
   "model_name": "kimi-k2-instruct-fast",
   "display_name": "Kimi K2 0711 Fast",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-07-15",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 0711 Fast"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2-Instruct-FP4",
   "model_name": "Kimi-K2-Instruct-FP4",
   "display_name": "Kimi K2 0711 Instruct FP4",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "baseten/Kimi-K2-Instruct-FP4"
    }
   ],
   "intro": "Kimi model for long-context chat, coding, and agentic reasoning",
   "released_at": "2025-07-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "baseten/Kimi-K2-Instruct-FP4"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 0711 Instruct FP4"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-thinking",
   "model_name": "kimi-k2-thinking",
   "display_name": "Kimi K2 Thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.575"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.548"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.192"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.137"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.294"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.294"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Thinking"
    },
    {
     "provider": "canopywave",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.656"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.731"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+helicone-registry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.141"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Thinking"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "fireworks/kimi-k2-thinking"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Thinking"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Thinking"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking"
    },
    {
     "provider": "kimi-for-coding",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     }
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Thinking"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking"
    },
    {
     "provider": "moonshotai-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Thinking"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6061"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5253"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1515"
      }
     },
     "provider_model_id": "novita/kimi-k2-thinking"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.31884"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Thinking"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     },
     "provider_model_id": "hf:moonshotai/Kimi-K2-Thinking"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.141"
      }
     },
     "provider_model_id": "deepinfra/moonshotai/Kimi-K2-Thinking"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.141"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking"
    }
   ],
   "intro": "Thinking Kimi model for slower research passes, planning, and hard technical questions",
   "released_at": "2025-11-06",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2",
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-25",
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 1
   },
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "benchmarks": {
    "intelligence_index": 17.3,
    "coding_index": 21,
    "agentic_index": 1.8
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Pro/moonshotai/Kimi-K2-Thinking",
    "accounts/fireworks/models/kimi-k2-thinking",
    "deepinfra/moonshotai/Kimi-K2-Thinking",
    "fireworks/kimi-k2-thinking",
    "hf:moonshotai/Kimi-K2-Thinking",
    "moonshotai/Kimi-K2-Thinking",
    "moonshotai/kimi-k2-thinking",
    "novita/kimi-k2-thinking"
   ],
   "intro_i18n": {
    "zh-CN": "kimi-k2-thinking 是 Moonshot AI 的推理模型，具有通用代理和推理能力。它擅长深度推理，并能通过多步工具使用解决复杂问题。",
    "zh-TW": "kimi-k2-thinking 是 Moonshot AI 的思考模型，具有通用代理和推理能力。它擅長深度推理，能通過多步工具使用解決難題。",
    "ja-JP": "kimi-k2-thinkingはMoonshot AIの思考モデルで、一般的なエージェント能力と推論能力を備えています。深い推論に優れ、マルチステップツールを使用して難しい問題を解決できます。",
    "ru-RU": "kimi-k2-thinking — это модель мышления от Moonshot AI с общими агентными и рассуждающими способностями. Она превосходно справляется с глубокими рассуждениями и может решать сложные задачи с использованием многошаговых инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "llmgateway",
     "charge": "cache_read",
     "old": "0.15",
     "new": "0.06"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "llmgateway",
     "charge": "completion",
     "old": "2.294",
     "new": "2.5"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "llmgateway",
     "charge": "prompt",
     "old": "0.574",
     "new": "0.6"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35934752",
     "new": "2.35686304"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35982928",
     "new": "2.35934752"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35899392",
     "new": "2.35982928"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.3548632",
     "new": "2.35899392"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.35499312",
     "new": "2.3548632"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58874828",
     "new": "0.5887158"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-thinking-maas",
   "model_name": "kimi-k2-thinking-maas",
   "display_name": "Kimi K2 Thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking-maas"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking-maas",
     "region": "global"
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2025-11-13",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/kimi-k2-thinking-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 Thinking"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-thinking-original",
   "model_name": "kimi-k2-thinking-original",
   "display_name": "Kimi K2 Thinking Original",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking-original"
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2025-11-06",
   "max_input_tokens": 256000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/kimi-k2-thinking-original"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 Thinking Original"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2-Thinking-TEE",
   "model_name": "Kimi-K2-Thinking-TEE",
   "display_name": "Kimi K2 Thinking TEE",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2-Thinking-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 262144,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "kimi-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/Kimi-K2-Thinking-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 Thinking TEE"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-thinking-turbo",
   "model_name": "kimi-k2-thinking-turbo",
   "display_name": "Kimi K2 Thinking Turbo",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.265"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.119"
      }
     }
    },
    {
     "provider": "moonshotai-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking-turbo"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking-turbo"
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2025-11-06",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true,
    "web_search": true,
    "stream": true
   },
   "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2",
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-25",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/kimi-k2-thinking-turbo"
   ],
   "intro_i18n": {
    "zh-CN": "Kimi K2 Thinking Turbo 是 Kimi K2 Thinking 的高速版本，在保持深度推理能力的同时显著降低延迟。",
    "zh-TW": "Kimi K2 Thinking Turbo 是 Kimi K2 Thinking 的高速版本，在保留深度推理能力的同時大幅降低延遲。",
    "ja-JP": "Kimi K2 Thinking Turboは、Kimi K2 Thinkingの高速バージョンで、深い推論能力を維持しながらレイテンシを大幅に低減します。",
    "ru-RU": "Kimi K2 Thinking Turbo — высокоскоростная версия Kimi K2 Thinking, значительно снижает задержку при сохранении глубины рассуждений."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-thinking-turbo-original",
   "model_name": "kimi-k2-thinking-turbo-original",
   "display_name": "Kimi K2 Thinking Turbo Original",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-thinking-turbo-original"
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2025-11-06",
   "max_input_tokens": 256000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/kimi-k2-thinking-turbo-original"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 Thinking Turbo Original"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-turbo",
   "model_name": "kimi-k2-turbo",
   "display_name": "Kimi K2 Turbo",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.65"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.84"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2-turbo"
    }
   ],
   "released_at": "2025-09-05",
   "knowledge_cutoff": "2024-08",
   "max_input_tokens": 256000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "kimi",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/kimi-k2-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 Turbo"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2-turbo-preview",
   "model_name": "kimi-k2-turbo-preview",
   "display_name": "Kimi K2 Turbo",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "moonshotai-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "intro": "Fast Kimi model for responsive chat, coding help, and agent loops",
   "released_at": "2025-09-05",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "web_search": true,
    "stream": true
   },
   "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2",
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-05-25",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2:1t",
   "model_name": "kimi-k2:1t",
   "display_name": "kimi-k2:1t",
   "vendor": "moonshotai",
   "pricing": [],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-07-11",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-k2:1t"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.5",
   "model_name": "kimi-k2.5",
   "display_name": "Kimi K2.5",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.411"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "kimi/kimi-k2.5"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.411"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.718"
      }
     },
     "provider_model_id": "kimi/kimi-k2.5"
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "kimi-k2-5"
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.98"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.95"
      }
     }
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     }
    },
    {
     "provider": "avian",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.225"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "workers-ai/@cf/moonshotai/kimi-k2.5"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.76"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.111"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.7"
      }
     }
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.9"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.070000002"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "kimi-k2-5"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "hpc-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.088235"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.088235"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.477"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.535"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2385"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.477"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.535"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2385"
      }
     },
     "provider_model_id": "kimi-k2-5"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.405"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.98"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.225"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "moonshot/kimi-k2.5"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.08975772"
      }
     },
     "provider_model_id": "Kimi-K2.5"
    },
    {
     "provider": "moonshotai-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.52"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.59"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "kimi-k2.5-free"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.025"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.203"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "kimi/kimi-k2.5"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "novita/kimi-k2.5"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.0434799999999997"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "fireworks/kimi-k2.5"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.462"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.42"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "route/kimi-k2.5"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      }
     },
     "provider_model_id": "Pro/moonshotai/Kimi-K2.5"
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.088235"
      }
     },
     "provider_model_id": "Kimi-K2.5"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     },
     "provider_model_id": "hf:moonshotai/Kimi-K2.5"
    },
    {
     "provider": "tencent-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.10000000000000002"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "kimi-k2-5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.02"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "4.4"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.5"
    }
   ],
   "intro": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
   "released_at": "2026-01",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "docs_url": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart",
   "model_type": "deep_thinking",
   "deprecated": true,
   "status": "deprecated",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Kimi-K2.5",
    "Pro/moonshotai/Kimi-K2.5",
    "TEE/kimi-k2.5",
    "fireworks/kimi-k2.5",
    "hf:moonshotai/Kimi-K2.5",
    "kimi-k2-5",
    "kimi-k2.5-free",
    "kimi/kimi-k2.5",
    "moonshot/kimi-k2.5",
    "moonshotai/Kimi-K2.5",
    "moonshotai/kimi-k2.5",
    "moonshotai/kimi-k2.5:thinking",
    "nebius/moonshotai/kimi-k2.5",
    "novita/kimi-k2.5",
    "route/kimi-k2.5",
    "workers-ai/@cf/moonshotai/kimi-k2.5"
   ],
   "intro_i18n": {
    "zh-CN": "Kimi K2.5 是目前最强大的 Kimi 模型，在智能体任务、编码与视觉理解方面达成开源 SOTA。支持多模态输入，并提供思维模式与非思维模式两种运行方式。",
    "zh-TW": "Kimi K2.5 是最強大的 Kimi 模型，在智能體任務、編碼與視覺理解上達到開源 SOTA。支援多模態輸入，並具備思考模式與非思考模式。",
    "ja-JP": "Kimi K2.5 は Kimi シリーズで最も高性能なモデルで、エージェントタスク、コーディング、画像理解においてオープンソース最先端性能を発揮します。マルチモーダル入力に対応し、思考モードと非思考モードの両方をサポートします。",
    "ru-RU": "Kimi K2.5 — самая мощная модель Kimi, обеспечивающая SOTA среди открытых моделей в агентных задачах, программировании и визуальном понимании. Поддерживает мультимодальные входы и режимы с размышлением и без него."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.259",
     "new": "0.2385"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.72",
     "new": "2.535"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.518",
     "new": "0.477"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.259",
     "new": "0.2385"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.72",
     "new": "2.535"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.518",
     "new": "0.477"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.09123528",
     "new": "3.08975772"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.244",
     "new": "0.259"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.57",
     "new": "2.72"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.488",
     "new": "0.518"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.244",
     "new": "0.259"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.57",
     "new": "2.72"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.488",
     "new": "0.518"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.09338274",
     "new": "3.09123528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "wandb",
     "charge": "completion",
     "old": "2.85",
     "new": "3"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "wandb",
     "charge": "prompt",
     "old": "0.5",
     "new": "0.6"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.26",
     "new": "0.244"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.74",
     "new": "2.57"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2.5-fast",
   "model_name": "Kimi-K2.5-fast",
   "display_name": "Kimi-K2.5-fast",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5-fast"
    },
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.52"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.59"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "kimi-k2.5-fast"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-12-15",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 256000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kimi-k2.5-fast",
    "moonshotai/Kimi-K2.5-fast"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi-K2.5-fast"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2.5-fp4",
   "model_name": "Kimi-K2.5-fp4",
   "display_name": "Kimi K2.5 Fp4",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5-fp4"
    }
   ],
   "max_input_tokens": 262144,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/Kimi-K2.5-fp4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.5 Fp4"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.5-fw",
   "model_name": "kimi-k2.5-fw",
   "display_name": "Kimi-K2.5-FW",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "fireworks-ai/kimi-k2.5-fw"
    }
   ],
   "intro": "Kimi multimodal agent model for visual understanding, coding, and planning",
   "released_at": "2026-01-27",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fireworks-ai/kimi-k2.5-fw"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi-K2.5-FW"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.5-lightning",
   "model_name": "kimi-k2.5-lightning",
   "display_name": "Kimi K2.5 (Lightning)",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "intro": "Kimi multimodal agent model for visual understanding, coding, and planning",
   "released_at": "2026-02-06",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.5 (Lightning)"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2.5-TEE",
   "model_name": "Kimi-K2.5-TEE",
   "display_name": "Kimi K2.5 TEE",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.44"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5-TEE"
    }
   ],
   "intro": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
   "released_at": "2026-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 262144,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/Kimi-K2.5-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.5 TEE"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.5-thinking",
   "model_name": "kimi-k2.5-thinking",
   "display_name": "Kimi K2.5 Thinking TEE",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     },
     "provider_model_id": "TEE/kimi-k2.5-thinking"
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2026-01-29",
   "max_input_tokens": 128000,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TEE/kimi-k2.5-thinking",
    "moonshotai/kimi-k2.5-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.5 Thinking TEE"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2.5-Turbo",
   "model_name": "Kimi-K2.5-Turbo",
   "display_name": "Kimi-K2.5-Turbo",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.5-Turbo"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "function_calling": true,
    "structured_output": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/Kimi-K2.5-Turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi-K2.5-Turbo"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.5@eu-north-1",
   "model_name": "kimi-k2.5@eu-north-1",
   "display_name": "bedrock/kimi-k2.5@eu-north-1",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "bedrock/kimi-k2.5@eu-north-1"
    }
   ],
   "released_at": "2026-03-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/kimi-k2.5@eu-north-1"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/kimi-k2.5@eu-north-1"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.5@eu-west-2",
   "model_name": "kimi-k2.5@eu-west-2",
   "display_name": "bedrock/kimi-k2.5@eu-west-2",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "bedrock/kimi-k2.5@eu-west-2"
    }
   ],
   "released_at": "2026-03-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/kimi-k2.5@eu-west-2"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/kimi-k2.5@eu-west-2"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.5@us-east-1",
   "model_name": "kimi-k2.5@us-east-1",
   "display_name": "bedrock/kimi-k2.5@us-east-1",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "bedrock/kimi-k2.5@us-east-1"
    }
   ],
   "released_at": "2026-03-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/kimi-k2.5@us-east-1"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/kimi-k2.5@us-east-1"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.5@us-east-2",
   "model_name": "kimi-k2.5@us-east-2",
   "display_name": "bedrock/kimi-k2.5@us-east-2",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "bedrock/kimi-k2.5@us-east-2"
    }
   ],
   "released_at": "2026-03-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/kimi-k2.5@us-east-2"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/kimi-k2.5@us-east-2"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.5@us-west-2",
   "model_name": "kimi-k2.5@us-west-2",
   "display_name": "bedrock/kimi-k2.5@us-west-2",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "bedrock/kimi-k2.5@us-west-2"
    }
   ],
   "released_at": "2026-03-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bedrock/kimi-k2.5@us-west-2"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/kimi-k2.5@us-west-2"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.6",
   "model_name": "kimi-k2.6",
   "display_name": "Kimi K2.6",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.955882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.970588"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.191176"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.929"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.858"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "avian",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.83"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "workers-ai/@cf/moonshotai/kimi-k2.6"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "@cf/moonshotai/kimi-k2.6"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.81"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.54"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.99"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.75"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "kimi-k2-6"
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.855"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.144"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.161765"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.955882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.970588"
      }
     }
    },
    {
     "provider": "inceptron",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.955882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.970588"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.98"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.475"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "kimi-k2-6"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "lilac",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "moonshot/kimi-k2.6"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95635358"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.97254564"
      }
     },
     "provider_model_id": "Kimi-K2.6"
    },
    {
     "provider": "moonshotai-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.73"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.69"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1725"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.4"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.41"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "kimi/kimi-k2.6"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.96"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.04"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "novita/kimi-k2.6"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9420299999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9130399999999996"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "deepinfra/moonshotai/Kimi-K2.6"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.462"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.42"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "route/kimi-k2.6"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.161765"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.955882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.970588"
      }
     },
     "provider_model_id": "Pro/moonshotai/Kimi-K2.6"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.77"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "Pro/moonshotai/Kimi-K2.6"
    },
    {
     "provider": "tinfoil",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.25"
      }
     },
     "provider_model_id": "kimi-k2-6"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16000000000000003"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.95"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "kimi-k2-6"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.15"
      }
     },
     "provider_model_id": "Kimi-K2.6"
    },
    {
     "provider": "wafer-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "Kimi-K2.6"
    },
    {
     "provider": "wafer.ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Kimi-K2.6"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.6"
    }
   ],
   "intro": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
   "released_at": "2026-04-21",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "assistant_prefill": true
   },
   "docs_url": "https://platform.kimi.ai/docs/pricing/chat-k26",
   "model_type": "deep_thinking",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "benchmarks": {
    "intelligence_index": 44.2,
    "coding_index": 61.8,
    "agentic_index": 30.3
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/moonshotai/kimi-k2.6",
    "Kimi-K2.6",
    "Pro/moonshotai/Kimi-K2.6",
    "TEE/kimi-k2.6",
    "deepinfra/moonshotai/Kimi-K2.6",
    "fireworks/kimi-k2.6",
    "inceptron/kimi-k2.6",
    "kimi-k2-6",
    "kimi/kimi-k2.6",
    "moonshot/kimi-k2.6",
    "moonshotai/Kimi-K2.6",
    "moonshotai/kimi-k2.6",
    "moonshotai/kimi-k2.6:free",
    "moonshotai/kimi-k2.6:thinking",
    "nebius/moonshotai/kimi-k2.6",
    "novita/kimi-k2.6",
    "route/kimi-k2.6",
    "workers-ai/@cf/moonshotai/kimi-k2.6"
   ],
   "intro_i18n": {
    "zh-CN": "Kimi K2.6是Moonshot AI推出的开源原生多模态代理模型，在多个主流基准测试中实现了开源领域的最先进性能，包括HLE（带工具）、SWE-Bench Pro和BrowseComp。该模型采用MoE架构，总参数量达1万亿，活跃参数量为320亿，支持256K标记上下文窗口，并集成了原生多模态功能。",
    "zh-TW": "Kimi K2.6 是 Moonshot AI 推出的開源原生多模態代理模型，在多個主流基準測試中達到開源最先進性能，包括 HLE（配合工具）、SWE-Bench Pro 和 BrowseComp。該模型採用 MoE 架構，擁有1萬億總參數和320億活躍參數，支持256K標記上下文窗口，並整合原生多模態能力。",
    "ja-JP": "Kimi K2.6はMoonshot AIによるオープンソースのネイティブマルチモーダルエージェントモデルで、HLE（ツール付き）、SWE-Bench Pro、BrowseCompを含む複数の主流ベンチマークでオープンソースの最先端性能を達成しています。このモデルは1Tの総パラメータと32Bのアクティブパラメータを持つMoEアーキテクチャを採用し、256Kトークンのコンテキストウィンドウをサポートし、ネイティブなマルチモーダル機能を統合しています。",
    "ru-RU": "Kimi K2.6 — это открытая мультимодальная агентная модель от Moonshot AI, демонстрирующая передовые результаты на нескольких основных бенчмарках, включая HLE (с инструментами), SWE-Bench Pro и BrowseComp. Модель использует архитектуру MoE с общим количеством параметров 1T и активными параметрами 32B, поддерживает контекстное окно на 256K токенов и интегрирует встроенные мультимодальные возможности."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.4655",
     "new": "0.475"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "3.92",
     "new": "3.98"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.931",
     "new": "0.95"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.97444536",
     "new": "3.97254564"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.95681092",
     "new": "0.95635358"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.475",
     "new": "0.4655"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "3.98",
     "new": "3.92"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.95",
     "new": "0.931"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.97720638",
     "new": "3.97444536"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.95747561",
     "new": "0.95681092"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "cache_read",
     "old": "0.14",
     "new": "0.3"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "cache_read",
     "old": "0.3",
     "new": "0.14"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "0.66",
     "new": "0.65"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.98139894",
     "new": "3.97720638"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.95848493",
     "new": "0.95747561"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "vultr",
     "charge": "completion",
     "old": "0.6",
     "new": "1.2"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "vultr",
     "charge": "prompt",
     "old": "0.15",
     "new": "0.3"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.98221191",
     "new": "3.98139894"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.958680645",
     "new": "0.95848493"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.98080224",
     "new": "3.98221191"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.6-6bit",
   "model_name": "kimi-k2.6-6bit",
   "display_name": "Kimi K2.6 6bit",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.462"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.42"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "route/kimi-k2.6-6bit"
    }
   ],
   "intro": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
   "released_at": "2026-04-21",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "route/kimi-k2.6-6bit"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.6 6bit"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2.6-Fast",
   "model_name": "Kimi-K2.6-Fast",
   "display_name": "Kimi K2.6 Fast",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "inceptron",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6-Fast"
    },
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.69"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1725"
      }
     },
     "provider_model_id": "kimi-k2.6-fast"
    }
   ],
   "intro": "Kimi multimodal agent model for visual understanding, coding, and planning",
   "released_at": "2026-04-21",
   "max_input_tokens": 262128,
   "max_output_tokens": 262128,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2025-01",
   "status": "alpha",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kimi-k2.6-fast",
    "moonshotai/Kimi-K2.6-Fast"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.6 Fast"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.6-flex",
   "model_name": "kimi-k2.6-flex",
   "display_name": "Kimi K2.6 Flex",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.345"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.61"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08625"
      }
     }
    }
   ],
   "intro": "Kimi multimodal agent model for visual understanding, coding, and planning",
   "released_at": "2026-04-21",
   "max_input_tokens": 262128,
   "max_output_tokens": 262128,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.6 Flex"
    }
   ]
  },
  {
   "slug": "moonshotai/Kimi-K2.6-TEE",
   "model_name": "Kimi-K2.6-TEE",
   "display_name": "Kimi K2.6 TEE",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.6-TEE"
    }
   ],
   "intro": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
   "released_at": "2026-04-21",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/Kimi-K2.6-TEE"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.6 TEE"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.6-thinking",
   "model_name": "kimi-k2.6-thinking",
   "display_name": "kimi-k2.6-thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "kimi-k2.6-thinking"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.7",
   "model_name": "kimi-k2.7",
   "display_name": "kimi-k2.7",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.73"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "kimi-k2.7"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.7-code",
   "model_name": "kimi-k2.7-code",
   "display_name": "Kimi K2.7 Code",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "models-dev+pydantic-prices+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9995"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.160835"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8939"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.7131"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0894"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.1174"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.73"
      }
     }
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.7-Code"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "@cf/moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.63"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.32"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.7-Code"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.7-Code"
    },
    {
     "provider": "inceptron",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.7-Code"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.566"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.7-Code"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "kimi-k2-7-code"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "moonshot/kimi-k2.7-code"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95635358"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.97254564"
      }
     },
     "provider_model_id": "Kimi-K2.7-Code"
    },
    {
     "provider": "moonshotai-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2375"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.7-Code"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "kimi/kimi-k2.7-code"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9596"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.0404"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1919"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9420299999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9130399999999996"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18841"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "fireworks/kimi-k2.7-code"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.191176"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.955882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.970588"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.7-Code"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.95"
      }
     },
     "provider_model_id": "hf:moonshotai/Kimi-K2.7-Code"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.7-Code"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.8570999999999995"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1857"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.9286"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.9286"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.9286"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "kimi-k2-7-code"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "Kimi-K2.7-Code"
    },
    {
     "provider": "wafer-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "Kimi-K2.7-Code"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.94"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "moonshotai/Kimi-K2.7-Code"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "2.24091"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code"
    }
   ],
   "intro": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
   "released_at": "2026-06-12",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 1
   },
   "benchmarks": {
    "intelligence_index": 41.9,
    "coding_index": 60.8,
    "agentic_index": 29.6
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/moonshotai/kimi-k2.7-code",
    "Kimi-K2.7-Code",
    "fireworks/kimi-k2.7-code",
    "hf:moonshotai/Kimi-K2.7-Code",
    "inceptron/kimi-k2.7-Code",
    "kimi-k2-7-code",
    "kimi/kimi-k2.7-code",
    "moonshot/kimi-k2.7-code",
    "moonshotai/Kimi-K2.7-Code",
    "moonshotai/kimi-k2.7-code",
    "moonshotai/kimi-k2.7-code-free",
    "parasail/kimi-k2.7-code",
    "tensorx/kimi-k2.7-code"
   ],
   "intro_i18n": {
    "zh-CN": "Kimi K2.7 Code是Moonshot AI基于Kimi K2.6开发的专注于编程的智能代理模型，在实际长周期编程任务上有显著提升，同时思考Token使用量减少约30%。",
    "zh-TW": "Kimi K2.7 Code 是 Moonshot AI 基於 Kimi K2.6 開發的專注於編程的代理模型，在真實世界的長期編程任務中有顯著改進，並將思考 token 的使用量降低了約 30%。",
    "ja-JP": "Kimi K2.7 Codeは、Moonshot AIが開発したコーディングに特化したエージェントモデルで、Kimi K2.6を基盤に、実世界の長期的なコーディングタスクにおいて大幅な改善を実現し、思考トークンの使用量を約30%削減しています。",
    "ru-RU": "Kimi K2.7 Code — это модель, ориентированная на программирование, от Moonshot AI, построенная на основе Kimi K2.6, с существенными улучшениями в реальных задачах программирования с длинным горизонтом и примерно на 30% меньшим использованием токенов для мышления."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.97444536",
     "new": "3.97254564"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.95681092",
     "new": "0.95635358"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.459",
     "new": "0.566"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "3.9",
     "new": "4.8"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.918",
     "new": "1.132"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.97720638",
     "new": "3.97444536"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.95747561",
     "new": "0.95681092"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.529",
     "new": "0.459"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "4.6",
     "new": "3.9"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "1.058",
     "new": "0.918"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.98139894",
     "new": "3.97720638"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.95848493",
     "new": "0.95747561"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "4.53",
     "new": "4.6"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.98221191",
     "new": "3.98139894"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.958680645",
     "new": "0.95848493"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.539",
     "new": "0.529"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "4.6",
     "new": "4.53"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "1.078",
     "new": "1.058"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.98080224",
     "new": "3.98221191"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.95834128",
     "new": "0.958680645"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.7-code-el",
   "model_name": "kimi-k2.7-code-el",
   "display_name": "Kimi-K2.7-Code-EL",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9596"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.0404"
      }
     }
    }
   ],
   "released_at": "2026-06-12",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi-K2.7-Code-EL"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.7-code-flex",
   "model_name": "kimi-k2.7-code-flex",
   "display_name": "Kimi K2.7 Code Flex",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.475"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11875"
      }
     }
    }
   ],
   "intro": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
   "released_at": "2026-06-12",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.7 Code Flex"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2.7-code-highspeed",
   "model_name": "kimi-k2.7-code-highspeed",
   "display_name": "Kimi K2.7 Code HighSpeed",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.999"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.32167"
      }
     }
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code-highspeed"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code-highspeed"
    },
    {
     "provider": "moonshotai-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code-highspeed"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code-highspeed"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "moonshotai/kimi-k2.7-code-highspeed"
    }
   ],
   "intro": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
   "released_at": "2026-06-12",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "budget_min": 1
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/kimi-k2.7-code-highspeed"
   ],
   "intro_i18n": {
    "zh-CN": "Kimi K2.7 Code HighSpeed 是 Kimi K2.7 Code 的高速版本。与 Kimi K2.7 Code 为同一模型，但输出速度约为 180 Tokens/s，短上下文场景下可达 260 Tokens/s，带来更极致的编程体验。",
    "zh-TW": "Kimi K2.7 Code HighSpeed 是 Kimi K2.7 Code 的高速版本。該模型與 Kimi K2.7 Code 相同，但輸出速度約為 180 Tokens/s，短上下文場景下可達 260 Tokens/s，帶來更極致的編程體驗。",
    "ja-JP": "Kimi K2.7 Code HighSpeedはKimi K2.7 Codeの高速モデルです。同じモデルですが、出力速度は約180トークン/秒で、短いコンテキストシナリオでは260トークン/秒に達し、より極限的なプログラミング体験を提供します。",
    "ru-RU": "Kimi K2.7 Code HighSpeed ​​— это высокоскоростная версия модели Kimi K2.7 Code. Это та же модель, что и Kimi K2.7 Code, но скорость вывода составляет около 180 токенов/с, а в сценариях с коротким контекстом достигает 260 токенов/с, обеспечивая более экстремальный опыт программирования."
   }
  },
  {
   "slug": "moonshotai/kimi-k2p5",
   "model_name": "kimi-k2p5",
   "display_name": "Kimi K2.5",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/kimi-k2p5"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true,
    "open_weights": true
   },
   "intro": "Moonshot AI's flagship agentic model. Unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. 1T parameter MoE model.",
   "knowledge_cutoff": "2025-01",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "released_at": "2026-01-27",
   "family": "kimi-thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/kimi-k2p5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.5"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2p6",
   "model_name": "kimi-k2p6",
   "display_name": "Kimi K2.6",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "accounts/fireworks/models/kimi-k2p6"
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2026-04-17",
   "max_input_tokens": 262000,
   "max_output_tokens": 262000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/kimi-k2p6"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.6"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2p6-fast",
   "model_name": "kimi-k2p6-fast",
   "display_name": "Kimi K2.6 Fast",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "accounts/fireworks/routers/kimi-k2p6-fast"
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2026-04-17",
   "max_input_tokens": 262000,
   "max_output_tokens": 262000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/routers/kimi-k2p6-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.6 Fast"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2p7-code",
   "model_name": "kimi-k2p7-code",
   "display_name": "Kimi K2.7 Code",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "accounts/fireworks/models/kimi-k2p7-code"
    }
   ],
   "intro": "Kimi coding model for software agents, refactors, and repository reasoning",
   "released_at": "2026-06-12",
   "max_input_tokens": 262000,
   "max_output_tokens": 262000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/kimi-k2p7-code"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.7 Code"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-k2p7-code-fast",
   "model_name": "kimi-k2p7-code-fast",
   "display_name": "Kimi K2.7 Code Fast",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "accounts/fireworks/routers/kimi-k2p7-code-fast"
    }
   ],
   "intro": "Kimi coding model for software agents, refactors, and repository reasoning",
   "released_at": "2026-06-12",
   "max_input_tokens": 262000,
   "max_output_tokens": 262000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/routers/kimi-k2p7-code-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.7 Code Fast"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-latest",
   "model_name": "kimi-latest",
   "display_name": "kimi-latest",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.49"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "~moonshotai/kimi-latest"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "moonshotai/kimi-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.41"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "~moonshotai/kimi-latest"
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "deprecated": true,
   "model_type": "vision_understanding",
   "deprecation_date": "2026-01-28",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "intro": "Kimi multimodal agent model for visual understanding, coding, and planning",
   "released_at": "2026-04-27",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/kimi-latest",
    "~moonshotai/kimi-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "cache_read",
     "old": "0.14",
     "new": "0.3"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "cache_read",
     "old": "0.3",
     "new": "0.14"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "0.66",
     "new": "0.65"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi-latest-128k",
   "model_name": "kimi-latest-128k",
   "display_name": "kimi-latest-128k",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "deprecated": true,
   "model_type": "vision_understanding",
   "deprecation_date": "2026-01-28",
   "capabilities": {
    "vision": true,
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "moonshotai/kimi-latest-32k",
   "model_name": "kimi-latest-32k",
   "display_name": "kimi-latest-32k",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "deprecated": true,
   "model_type": "vision_understanding",
   "deprecation_date": "2026-01-28",
   "capabilities": {
    "vision": true,
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "moonshotai/kimi-latest-8k",
   "model_name": "kimi-latest-8k",
   "display_name": "kimi-latest-8k",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "deprecated": true,
   "model_type": "vision_understanding",
   "deprecation_date": "2026-01-28",
   "capabilities": {
    "vision": true,
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "moonshotai/kimi-thinking-preview",
   "model_name": "kimi-thinking-preview",
   "display_name": "kimi-thinking-preview",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "31.46"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "31.46"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2025-11-11",
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-05-07",
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "moonshotai/kimi-vl-a3b-thinking:free",
   "model_name": "kimi-vl-a3b-thinking:free",
   "display_name": "kimi-vl-a3b-thinking:free",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-vl-a3b-thinking:free"
    }
   ]
  },
  {
   "slug": "moonshotai/kimi2.6",
   "model_name": "kimi2.6",
   "display_name": "kimi2.6",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.856229625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.99573825"
      }
     }
    }
   ],
   "released_at": "2026-04-14",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.00297618",
     "new": "3.99573825"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.85778061",
     "new": "0.856229625"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.001430895",
     "new": "4.00297618"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.8574494775",
     "new": "0.85778061"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.004495005",
     "new": "4.001430895"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.8581060725",
     "new": "0.8574494775"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.00288294",
     "new": "4.004495005"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.85776063",
     "new": "0.8581060725"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "4.003992545",
     "new": "4.00288294"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.8579984025",
     "new": "0.85776063"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "3.9833395",
     "new": "4.003992545"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.85357275",
     "new": "0.8579984025"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi2.6"
    }
   ]
  },
  {
   "slug": "moonshotai/Moonlight-16B-A3B-Instruct",
   "model_name": "Moonlight-16B-A3B-Instruct",
   "display_name": "moonshotai/Moonlight-16B-A3B-Instruct",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "moonshotai/Moonlight-16B-A3B-Instruct"
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshotai/Moonlight-16B-A3B-Instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "moonshotai/Moonlight-16B-A3B-Instruct"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-for-coding",
   "model_name": "moonshot-kimi-for-coding",
   "display_name": "kimi-for-coding",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.57"
      }
     }
    }
   ],
   "released_at": "2025-11-11",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-for-coding"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-k2-0711-preview",
   "model_name": "moonshot-kimi-k2-0711-preview",
   "display_name": "kimi-k2-0711-preview",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.575"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-07-11",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-k2-0711-preview"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-k2-0905-preview",
   "model_name": "moonshot-kimi-k2-0905-preview",
   "display_name": "kimi-k2-0905-preview",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5714"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2025-09-05",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-k2-0905-preview"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-k2-250711",
   "model_name": "moonshot-kimi-k2-250711",
   "display_name": "kimi-k2-250711",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.575"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-08-18",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-k2-250711"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-k2-5",
   "model_name": "moonshot-kimi-k2-5",
   "display_name": "kimi-k2.5",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.105"
      }
     },
     "provider_model_id": "moonshot-kimi-k2.5"
    }
   ],
   "released_at": "2026-01-27",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshot-kimi-k2.5"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-k2.5"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-k2-6",
   "model_name": "moonshot-kimi-k2-6",
   "display_name": "kimi-k2.6",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "released_at": "2026-04-20",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-k2.6"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-k2-7-code",
   "model_name": "moonshot-kimi-k2-7-code",
   "display_name": "kimi-k2.7-code",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "released_at": "2026-06-13",
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-k2.7-code"
    }
   ]
  },
  {
   "slug": "moonshotai/Moonshot-Kimi-K2-Instruct",
   "model_name": "Moonshot-Kimi-K2-Instruct",
   "display_name": "Moonshot Kimi K2 Instruct",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.294"
      }
     },
     "provider_model_id": "moonshot-kimi-k2-instruct"
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.574"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.294"
      }
     },
     "provider_model_id": "moonshot-kimi-k2-instruct"
    }
   ],
   "intro": "Kimi model for long-context chat, coding, and agentic reasoning",
   "released_at": "2025-01-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true,
    "web_search": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshot-kimi-k2-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "总参数 1 万亿，激活参数 320 亿。在非思维模型中，在前沿知识、数学和编程方面表现顶尖，通用智能体任务能力更强。专为智能体工作负载优化，具备行动能力而非仅限问答。适合即兴对话、通用聊天和智能体体验，具备反射级响应能力，无需长时间思考。",
    "zh-TW": "總參數 1 兆，啟用 320 億。在非思考模型中於前沿知識、數學與編碼方面表現頂尖，並在通用代理任務中更為強大。針對代理工作負載進行優化，具備行動能力而非僅能回答問題。作為一款反射級模型，特別適合即興對話、通用聊天與代理體驗。",
    "ja-JP": "総パラメータ1兆、アクティブパラメータ32Bの非思考型モデルで、最先端の知識、数学、コーディングにおいてトップクラスの性能を誇ります。一般的なエージェントタスクにも強く、質問に答えるだけでなく行動も可能です。即興的な会話や一般的なチャット、エージェント体験に最適な、反射レベルのモデルです。",
    "ru-RU": "1T общих параметров и 32B активных. Среди моделей без размышлений — одна из лучших по знаниям, математике и программированию, а также сильнее в общих задачах агентов. Оптимизирована для рабочих нагрузок агентов: может действовать, а не только отвечать. Идеальна для импровизационного общения, общего чата и агентных сценариев как модель рефлекторного уровня без длительного размышления."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Moonshot Kimi K2 Instruct"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-k2-thinking",
   "model_name": "moonshot-kimi-k2-thinking",
   "display_name": "Kimi K2 Thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.575"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshot.kimi-k2-thinking",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.73"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.03"
      }
     },
     "provider_model_id": "moonshot.kimi-k2-thinking",
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.94"
      }
     },
     "provider_model_id": "moonshot.kimi-k2-thinking",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.575"
      }
     },
     "provider_model_id": "moonshot.kimi-k2-thinking",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.73"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.03"
      }
     },
     "provider_model_id": "moonshot.kimi-k2-thinking",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshot.kimi-k2-thinking",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshot.kimi-k2-thinking",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "moonshot.kimi-k2-thinking",
     "region": "us-west-2"
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2025-12-02",
   "max_input_tokens": 262143,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "moonshot.kimi-k2-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2 Thinking"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-k2-thinking-turbo",
   "model_name": "moonshot-kimi-k2-thinking-turbo",
   "display_name": "kimi-k2-thinking-turbo",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.29"
      }
     }
    }
   ],
   "released_at": "2025-11-06",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-k2-thinking-turbo"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-k2-turbo-preview",
   "model_name": "moonshot-kimi-k2-turbo-preview",
   "display_name": "kimi-k2-turbo-preview",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.29"
      }
     }
    }
   ],
   "released_at": "2025-09-01",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-k2-turbo-preview"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-kimi-latest",
   "model_name": "moonshot-kimi-latest",
   "display_name": "kimi-latest",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.43"
      }
     }
    }
   ],
   "released_at": "2025-02-25",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kimi-latest"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-v1-128k",
   "model_name": "moonshot-v1-128k",
   "display_name": "moonshot-v1-128k",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm+pydantic-prices+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.78"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Moonshot V1 128K 提供超长上下文能力，支持最多 128,000 个 token 的文本生成，适用于科研、学术和长文档场景。",
    "zh-TW": "Moonshot V1 128K 提供超長上下文能力，支援最多 128,000 個 token，適用於研究、學術與長文檔場景。",
    "ja-JP": "Moonshot V1 128Kは、最大128,000トークンの超長文コンテキストに対応し、研究、学術、大規模文書の生成に最適です。",
    "ru-RU": "Moonshot V1 128K предоставляет сверхдлинный контекст для генерации очень длинных текстов, обрабатывая до 128 000 токенов — идеально для исследований, академических задач и работы с большими документами."
   }
  },
  {
   "slug": "moonshotai/moonshot-v1-128k-0430",
   "model_name": "moonshot-v1-128k-0430",
   "display_name": "moonshot-v1-128k-0430",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2024-04-30",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "moonshotai/moonshot-v1-128k-vision",
   "model_name": "moonshot-v1-128k-vision",
   "display_name": "moonshot-v1-128k-vision",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.78"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "moonshot-v1-128k-vision"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-v1-128k-vision-preview",
   "model_name": "moonshot-v1-128k-vision-preview",
   "display_name": "moonshot-v1-128k-vision-preview",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true
   },
   "released_at": "2025-01-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Kimi 视觉模型（包括 moonshot-v1-8k-vision-preview、moonshot-v1-32k-vision-preview、moonshot-v1-128k-vision-preview）可理解图像内容，如文字、颜色和物体形状。",
    "zh-TW": "Kimi 視覺模型（包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview）能理解圖像內容，如文字、顏色與物體形狀。",
    "ja-JP": "Kimi Visionモデル（moonshot-v1-8k-vision-preview / moonshot-v1-32k-vision-preview / moonshot-v1-128k-vision-preview）は、テキスト、色、物体の形状などの画像内容を理解できます。",
    "ru-RU": "Модели Kimi Vision (включая moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview) способны понимать содержимое изображений, включая текст, цвета и формы объектов."
   }
  },
  {
   "slug": "moonshotai/moonshot-v1-32k",
   "model_name": "moonshot-v1-32k",
   "display_name": "moonshot-v1-32k",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm+pydantic-prices+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.52"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Moonshot V1 32K 支持 32,768 个 token 的中等长度上下文，适用于内容创作、报告和聊天系统中的长文档与复杂对话。",
    "zh-TW": "Moonshot V1 32K 支援 32,768 個 token 的中長上下文，適合內容創作、報告與聊天系統中的長文檔與複雜對話。",
    "ja-JP": "Moonshot V1 32Kは、32,768トークンの中程度の長さのコンテキストをサポートし、長文ドキュメントや複雑な対話に最適で、コンテンツ制作、レポート、チャットシステムに適しています。",
    "ru-RU": "Moonshot V1 32K поддерживает 32 768 токенов для контекста средней длины, идеально подходит для длинных документов и сложных диалогов в создании контента, отчётах и чат-системах."
   }
  },
  {
   "slug": "moonshotai/moonshot-v1-32k-0430",
   "model_name": "moonshot-v1-32k-0430",
   "display_name": "moonshot-v1-32k-0430",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2024-04-30",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "moonshotai/moonshot-v1-32k-vision",
   "model_name": "moonshot-v1-32k-vision",
   "display_name": "moonshot-v1-32k-vision",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.52"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "moonshot-v1-32k-vision"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-v1-32k-vision-preview",
   "model_name": "moonshot-v1-32k-vision-preview",
   "display_name": "moonshot-v1-32k-vision-preview",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true
   },
   "released_at": "2025-01-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Kimi 视觉模型（包括 moonshot-v1-8k-vision-preview、moonshot-v1-32k-vision-preview、moonshot-v1-128k-vision-preview）可理解图像内容，如文字、颜色和物体形状。",
    "zh-TW": "Kimi 視覺模型（包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview）能理解圖像內容，如文字、顏色與物體形狀。",
    "ja-JP": "Kimi Visionモデル（moonshot-v1-8k-vision-preview / moonshot-v1-32k-vision-preview / moonshot-v1-128k-vision-preview）は、テキスト、色、物体の形状などの画像内容を理解できます。",
    "ru-RU": "Модели Kimi Vision (включая moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview) способны понимать содержимое изображений, включая текст, цвета и формы объектов."
   }
  },
  {
   "slug": "moonshotai/moonshot-v1-8k",
   "model_name": "moonshot-v1-8k",
   "display_name": "moonshot-v1-8k",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm+pydantic-prices+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.84"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.26"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "released_at": "2024-07-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Moonshot V1 8K 针对短文本生成进行了优化，性能高效，支持 8,192 个 token，适用于短对话、笔记和快速内容生成。",
    "zh-TW": "Moonshot V1 8K 針對短文本生成進行優化，支援 8,192 個 token，適用於短對話、筆記與快速內容生成。",
    "ja-JP": "Moonshot V1 8Kは、短文生成に最適化されており、効率的なパフォーマンスで8,192トークンを処理し、短いチャット、メモ、迅速なコンテンツ作成に適しています。",
    "ru-RU": "Moonshot V1 8K оптимизирована для генерации коротких текстов с высокой эффективностью, обрабатывает 8192 токена — подходит для коротких чатов, заметок и быстрого контента."
   }
  },
  {
   "slug": "moonshotai/moonshot-v1-8k-0430",
   "model_name": "moonshot-v1-8k-0430",
   "display_name": "moonshot-v1-8k-0430",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2024-04-30",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "moonshotai/moonshot-v1-8k-vision",
   "model_name": "moonshot-v1-8k-vision",
   "display_name": "moonshot-v1-8k-vision",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.84"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.26"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "moonshot-v1-8k-vision"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-v1-8k-vision-preview",
   "model_name": "moonshot-v1-8k-vision-preview",
   "display_name": "moonshot-v1-8k-vision-preview",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "released_at": "2025-01-14",
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Kimi 视觉模型（包括 moonshot-v1-8k-vision-preview、moonshot-v1-32k-vision-preview、moonshot-v1-128k-vision-preview）可理解图像内容，如文字、颜色和物体形状。",
    "zh-TW": "Kimi 視覺模型（包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview）能理解圖像內容，如文字、顏色與物體形狀。",
    "ja-JP": "Kimi Visionモデル（moonshot-v1-8k-vision-preview、moonshot-v1-32k-vision-preview、moonshot-v1-128k-vision-previewを含む）は、テキスト、色、物体の形状などの画像内容を理解できます。",
    "ru-RU": "Модели Kimi Vision (включая moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview) способны понимать содержимое изображений, включая текст, цвета и формы объектов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshot-v1-auto",
   "model_name": "moonshot-v1-auto",
   "display_name": "moonshot-v1-auto",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "moonshotai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "docs_url": "https://platform.moonshot.ai/docs/pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "moonshotai/moonshotai.kimi-k2-thinking",
   "model_name": "moonshotai.kimi-k2-thinking",
   "display_name": "moonshotai.kimi-k2-thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.73"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.03"
      }
     }
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.73"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.03"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.94"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.575"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.73"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.03"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "region": "us-west-2"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "moonshotai.kimi-k2-thinking"
    }
   ]
  },
  {
   "slug": "moonshotai/moonshotai.kimi-k2.5",
   "model_name": "moonshotai.kimi-k2.5",
   "display_name": "Kimi K2.5",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.09"
      }
     },
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "eu-north-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.09"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Kimi multimodal agent model for visual understanding, coding, and planning",
   "released_at": "2026-02-06",
   "max_input_tokens": 262143,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.5"
    }
   ]
  },
  {
   "slug": "moonshotai/ppio-moonshotai-kimi-k2-0905",
   "model_name": "ppio-moonshotai-kimi-k2-0905",
   "display_name": "moonshotai/kimi-k2-0905",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "moonshotai/kimi-k2-0905"
    }
   ]
  },
  {
   "slug": "moonshotai/ppio-moonshotai-kimi-k2-5",
   "model_name": "ppio-moonshotai-kimi-k2-5",
   "display_name": "moonshotai/kimi-k2.5",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "released_at": "2026-01-28",
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "moonshotai/kimi-k2.5"
    }
   ]
  },
  {
   "slug": "moonshotai/ppio-moonshotai-kimi-k2-instruct",
   "model_name": "ppio-moonshotai-kimi-k2-instruct",
   "display_name": "moonshotai/kimi-k2-instruct",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     }
    }
   ],
   "released_at": "2025-07-14",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "moonshotai/kimi-k2-instruct"
    }
   ]
  },
  {
   "slug": "moonshotai/ppio-moonshotai-kimi-k2-thinking",
   "model_name": "ppio-moonshotai-kimi-k2-thinking",
   "display_name": "moonshotai/kimi-k2-thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "moonshotai/kimi-k2-thinking"
    }
   ]
  },
  {
   "slug": "moonshotai/Pro-moonshotai-Kimi-K2-5",
   "model_name": "Pro-moonshotai-Kimi-K2-5",
   "display_name": "Pro/moonshotai/Kimi-K2.5",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "released_at": "2026-01-31",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/moonshotai/Kimi-K2.5"
    }
   ]
  },
  {
   "slug": "moonshotai/sf-kimi-k2-thinking",
   "model_name": "sf-kimi-k2-thinking",
   "display_name": "sf-kimi-k2-thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.548"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.192"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sf-kimi-k2-thinking"
    }
   ]
  },
  {
   "slug": "moonshotai/siliconflow-pro-moonshotai-kimi-k2-instruct-0905",
   "model_name": "siliconflow-pro-moonshotai-kimi-k2-instruct-0905",
   "display_name": "Pro/moonshotai/Kimi-K2-Instruct-0905",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2025-09-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/moonshotai/Kimi-K2-Instruct-0905"
    }
   ]
  },
  {
   "slug": "moonshotai/siliconflow-Pro-moonshotai-Kimi-K2-Thinking",
   "model_name": "siliconflow-Pro-moonshotai-Kimi-K2-Thinking",
   "display_name": "Pro/moonshotai/Kimi-K2-Thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/moonshotai/Kimi-K2-Thinking"
    }
   ]
  },
  {
   "slug": "moonshotai/sophnet-kimi-k2",
   "model_name": "sophnet-kimi-k2",
   "display_name": "sophnet/Kimi-K2",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     }
    }
   ],
   "released_at": "2025-07-16",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Kimi-K2"
    }
   ]
  },
  {
   "slug": "moonshotai/sophnet-kimi-k2-0905",
   "model_name": "sophnet-kimi-k2-0905",
   "display_name": "sophnet/Kimi-K2-0905",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2025-09-09",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/Kimi-K2-0905"
    }
   ]
  },
  {
   "slug": "moonshotai/sophnet-Kimi-K2-Thinking",
   "model_name": "sophnet-Kimi-K2-Thinking",
   "display_name": "sophnet/kimi-k2-thinking",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2026-01-06",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/kimi-k2-thinking"
    }
   ]
  },
  {
   "slug": "moonshotai/umans-kimi-k2.7",
   "model_name": "umans-kimi-k2.7",
   "display_name": "Kimi K2.7 Code",
   "vendor": "moonshotai",
   "pricing": [
    {
     "provider": "umans-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    },
    {
     "provider": "umans-ai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
   "released_at": "2026-06-12",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.7 Code"
    }
   ]
  },
  {
   "slug": "morph/auto",
   "model_name": "auto",
   "display_name": "Auto",
   "vendor": "morph",
   "pricing": [
    {
     "provider": "morph",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.55"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/auto"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/auto"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "orcarouter/auto"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2024-06-01",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "auto",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kilo/auto",
    "openrouter/auto",
    "orcarouter/auto"
   ],
   "intro_i18n": {
    "zh-CN": "根据上下文长度、主题和复杂度，自动将请求路由至 Llama 3 70B Instruct、Claude 3.5 Sonnet（自我审查）或 GPT-4o。",
    "zh-TW": "根據上下文長度、主題與複雜度，自動將請求路由至 Llama 3 70B Instruct、Claude 3.5 Sonnet（自我審核）或 GPT-4o。",
    "ja-JP": "コンテキスト長、トピック、複雑さに応じて、Llama 3 70B Instruct、Claude 3.5 Sonnet（自己モデレート）、またはGPT-4oにルーティングされます。",
    "ru-RU": "В зависимости от длины контекста, темы и сложности ваш запрос направляется в Llama 3 70B Instruct, Claude 3.5 Sonnet (с самомодерацией) или GPT-4o."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "morph/morph-v3-fast",
   "model_name": "morph-v3-fast",
   "display_name": "Morph v3 Fast",
   "vendor": "morph",
   "pricing": [
    {
     "provider": "morph",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "morph/morph-v3-fast"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "morph/morph-v3-fast"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "morph/morph-v3-fast"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "morph/morph-v3-fast"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-08-15",
   "max_input_tokens": 16000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "morph",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "morph/morph-v3-fast"
   ],
   "intro_i18n": {
    "zh-CN": "Morph 提供专用模型，将前沿模型（如 Claude 或 GPT-4o）建议的代码更改快速应用于现有文件，速度达 4500+ tokens/秒，是 AI 编程流程的最后一步，支持 16k 输入/输出。",
    "zh-TW": "Morph 提供專門模型，能以超過 4500 個 token/秒的速度，將前沿模型（如 Claude 或 GPT-4o）建議的程式碼變更應用至現有檔案。作為 AI 程式開發流程的最後一步，支援 16K 輸入/輸出 token。",
    "ja-JP": "Morphは、ClaudeやGPT-4oなどの先端モデルが提案したコード変更を既存ファイルに適用するための専用モデルで、FAST 4500+トークン/秒の速度で動作します。AIコーディングワークフローの最終ステップとして、16Kの入出力トークンをサポートします。",
    "ru-RU": "Morph — специализированная модель для применения изменений в коде, предложенных передовыми моделями (например, Claude или GPT-4o), к существующим файлам со скоростью более 4500 токенов/сек. Это финальный этап в AI-пайплайне программирования, поддерживает 16k токенов на вход/выход."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "morph/morph-v3-large",
   "model_name": "morph-v3-large",
   "display_name": "Morph v3 Large",
   "vendor": "morph",
   "pricing": [
    {
     "provider": "morph",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     },
     "provider_model_id": "morph/morph-v3-large"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     },
     "provider_model_id": "morph/morph-v3-large"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     },
     "provider_model_id": "morph/morph-v3-large"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     },
     "provider_model_id": "morph/morph-v3-large"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2024-08-15",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "morph",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "morph/morph-v3-large"
   ],
   "intro_i18n": {
    "zh-CN": "Morph 提供专用模型，将前沿模型（如 Claude 或 GPT-4o）建议的代码更改快速应用于现有文件，速度达 2500+ tokens/秒，是 AI 编程流程的最后一步，支持 16k 输入/输出。",
    "zh-TW": "Morph 提供專門模型，能以超過 2500 個 token/秒的速度，將前沿模型（如 Claude 或 GPT-4o）建議的程式碼變更應用至現有檔案。作為 AI 程式開發流程的最後一步，支援 16K 輸入/輸出 token。",
    "ja-JP": "Morphは、ClaudeやGPT-4oなどの先端モデルが提案したコード変更を既存ファイルに適用するための専用モデルで、FAST 2500+トークン/秒の速度で動作します。AIコーディングワークフローの最終ステップとして、16Kの入出力トークンをサポートします。",
    "ru-RU": "Morph — специализированная модель для применения изменений в коде, предложенных передовыми моделями (например, Claude или GPT-4o), к существующим файлам со скоростью более 2500 токенов/сек. Это финальный этап в AI-пайплайне программирования, поддерживает 16k токенов на вход/выход."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "myshell/@cf/myshell-ai/melotts",
   "model_name": "@cf/myshell-ai/melotts",
   "display_name": "MyShell MeloTTS",
   "vendor": "myshell",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/myshell-ai/melotts"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-11-14",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "melotts",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "workers-ai/@cf/myshell-ai/melotts"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MyShell MeloTTS"
    }
   ]
  },
  {
   "slug": "nousresearch/Hermes-4-14B",
   "model_name": "Hermes-4-14B",
   "display_name": "Hermes 4 14B",
   "vendor": "nousresearch",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "NousResearch/Hermes-4-14B"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 40960,
   "max_output_tokens": 40960,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "nousresearch",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Hermes-4-14B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes 4 14B"
    }
   ]
  },
  {
   "slug": "nousresearch/Hermes-4-405B",
   "model_name": "Hermes-4-405B",
   "display_name": "Hermes-4-405B",
   "vendor": "nousresearch",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.894"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.683"
      }
     },
     "provider_model_id": "hermes-4-405b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "nousresearch/hermes-4-405b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "NousResearch/hermes-4-405b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "NousResearch/Hermes-4-405B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "nousresearch/hermes-4-405b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "nebius/nousresearch/hermes-4-405b"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-01-30",
   "knowledge_cutoff": "2025-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "family": "hermes",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Hermes-4-405B",
    "NousResearch/hermes-4-405b",
    "NousResearch/hermes-4-405b:thinking",
    "hermes-4-405b",
    "nebius/nousresearch/hermes-4-405b",
    "nousresearch/hermes-4-405b",
    "nousresearch/hermes-4-405b:thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes-4-405B"
    }
   ]
  },
  {
   "slug": "nousresearch/Hermes-4-405B-FP8-TEE",
   "model_name": "Hermes-4-405B-FP8-TEE",
   "display_name": "Hermes 4 405B FP8 TEE",
   "vendor": "nousresearch",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "NousResearch/Hermes-4-405B-FP8-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "nousresearch",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Hermes-4-405B-FP8-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes 4 405B FP8 TEE"
    }
   ]
  },
  {
   "slug": "nousresearch/Hermes-4-70B",
   "model_name": "Hermes-4-70B",
   "display_name": "Hermes 4 70B",
   "vendor": "nousresearch",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "NousResearch/Hermes-4-70B"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.116"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.358"
      }
     },
     "provider_model_id": "hermes-4-70b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.055"
      }
     },
     "provider_model_id": "nousresearch/hermes-4-70b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3995"
      }
     },
     "provider_model_id": "NousResearch/hermes-4-70b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.013"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "NousResearch/Hermes-4-70B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "nousresearch/hermes-4-70b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "nebius/nousresearch/hermes-4-70b"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-08-26",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "family": "hermes",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Hermes-4-70B",
    "NousResearch/Hermes-4-70B:thinking",
    "NousResearch/hermes-4-70b",
    "hermes-4-70b",
    "nebius/nousresearch/hermes-4-70b",
    "nousresearch/hermes-4-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes 4 70B"
    }
   ]
  },
  {
   "slug": "nousresearch/Hermes-4.3-36B",
   "model_name": "Hermes-4.3-36B",
   "display_name": "Hermes 4.3 36B",
   "vendor": "nousresearch",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     },
     "provider_model_id": "NousResearch/Hermes-4.3-36B"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nousresearch",
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Hermes-4.3-36B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes 4.3 36B"
    }
   ]
  },
  {
   "slug": "nousresearch/Nous-Capybara-7B-V1p9",
   "model_name": "Nous-Capybara-7B-V1p9",
   "display_name": "Nous Capybara 7B V1.9",
   "vendor": "nousresearch",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "nous-capybara-7b-v1p9"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "NousResearch/Nous-Capybara-7B-V1p9"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NousResearch/Nous-Capybara-7B-V1p9",
    "accounts/fireworks/models/nous-capybara-7b-v1p9",
    "nous-capybara-7b-v1p9"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nous Capybara 7B V1.9"
    }
   ]
  },
  {
   "slug": "nvidia/active-speaker-detection",
   "model_name": "active-speaker-detection",
   "display_name": "Active Speaker Detection",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/active-speaker-detection"
    }
   ],
   "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
   "released_at": "2026-04-16",
   "max_input_tokens": 0,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "video_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/active-speaker-detection"
   ],
   "model_type": "vision_understanding"
  },
  {
   "slug": "nvidia/bevformer",
   "model_name": "bevformer",
   "display_name": "bevformer",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/bevformer"
    }
   ],
   "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
   "released_at": "2025-03-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "video_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/bevformer"
   ],
   "model_type": "vision_understanding"
  },
  {
   "slug": "nvidia/cosmos-predict1-5b",
   "model_name": "cosmos-predict1-5b",
   "display_name": "cosmos-predict1-5b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/cosmos-predict1-5b"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-03-18",
   "max_input_tokens": 0,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "video_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/cosmos-predict1-5b"
   ],
   "model_type": "vision_understanding"
  },
  {
   "slug": "nvidia/cosmos-transfer1-7b",
   "model_name": "cosmos-transfer1-7b",
   "display_name": "cosmos-transfer1-7b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/cosmos-transfer1-7b"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-06-13",
   "max_input_tokens": 0,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "video_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/cosmos-transfer1-7b"
   ],
   "model_type": "vision_understanding"
  },
  {
   "slug": "nvidia/cosmos-transfer2_5-2b",
   "model_name": "cosmos-transfer2_5-2b",
   "display_name": "cosmos-transfer2.5-2b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/cosmos-transfer2_5-2b"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-02-26",
   "max_input_tokens": 0,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "video"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "video_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/cosmos-transfer2_5-2b"
   ],
   "model_type": "vision_understanding"
  },
  {
   "slug": "nvidia/Cosmos3-Nano",
   "model_name": "Cosmos3-Nano",
   "display_name": "Cosmos3-Nano",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.0108"
      }
     },
     "provider_model_id": "nvidia/Cosmos3-Nano"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text",
     "image",
     "video",
     "audio"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "video_input": true,
    "audio_output": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Cosmos3-Nano"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cosmos3-Nano"
    }
   ]
  },
  {
   "slug": "nvidia/deepinfra-nvidia-nemotron-3-nano-30b-a3b2",
   "model_name": "deepinfra-nvidia-nemotron-3-nano-30b-a3b2",
   "display_name": "deepinfra-nvidia-nemotron-3-nano-30b-a3b2",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.066"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.264"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra-nvidia-nemotron-3-nano-30b-a3b2"
    }
   ]
  },
  {
   "slug": "nvidia/DeepSeek-V3.2-NVFP4",
   "model_name": "DeepSeek-V3.2-NVFP4",
   "display_name": "DeepSeek V3.2",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "vultr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.65"
      }
     },
     "provider_model_id": "nvidia/DeepSeek-V3.2-NVFP4"
    }
   ],
   "intro": "DeepSeek chat model for instruction following, coding, and analysis",
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "deepseek",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/DeepSeek-V3.2-NVFP4"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepSeek V3.2"
    }
   ]
  },
  {
   "slug": "nvidia/fireworks/models/nemotron-3-super-120b-a12b-bf16",
   "model_name": "fireworks/models/nemotron-3-super-120b-a12b-bf16",
   "display_name": "NVIDIA Nemotron 3 Super 120B A12B BF16",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nemotron-3-super-120b-a12b-bf16"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nemotron-3-super-120b-a12b-bf16"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron 3 Super 120B A12B BF16"
    }
   ]
  },
  {
   "slug": "nvidia/fireworks/models/nemotron-3-ultra-bf16",
   "model_name": "fireworks/models/nemotron-3-ultra-bf16",
   "display_name": "NVIDIA Nemotron 3 Ultra BF16",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nemotron-3-ultra-bf16"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nemotron-3-ultra-bf16"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron 3 Ultra BF16"
    }
   ]
  },
  {
   "slug": "nvidia/fireworks/models/nemotron-nano-3-30b-a3b",
   "model_name": "fireworks/models/nemotron-nano-3-30b-a3b",
   "display_name": "NVIDIA Nemotron Nano 3 30B A3B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nemotron-nano-3-30b-a3b"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nemotron-nano-3-30b-a3b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron Nano 3 30B A3B"
    }
   ]
  },
  {
   "slug": "nvidia/fireworks/models/nvidia-nemotron-3-nano-omni-30b-a3b",
   "model_name": "fireworks/models/nvidia-nemotron-3-nano-omni-30b-a3b",
   "display_name": "NVIDIA Nemotron 3 Nano Omni 30B A3B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nvidia-nemotron-3-nano-omni-30b-a3b"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nvidia-nemotron-3-nano-omni-30b-a3b"
   ],
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron 3 Nano Omni 30B A3B"
    }
   ]
  },
  {
   "slug": "nvidia/gliner-pii",
   "model_name": "gliner-pii",
   "display_name": "gliner-pii",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/gliner-pii"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2026-03-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/gliner-pii"
   ],
   "model_type": "text_generation"
  },
  {
   "slug": "nvidia/Kimi-K2.5-NVFP4",
   "model_name": "Kimi-K2.5-NVFP4",
   "display_name": "Kimi K2.5 (NVFP4)",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     },
     "provider_model_id": "hf:nvidia/Kimi-K2.5-NVFP4"
    }
   ],
   "released_at": "2026-01",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "family": "kimi",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hf:nvidia/Kimi-K2.5-NVFP4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.5 (NVFP4)"
    }
   ]
  },
  {
   "slug": "nvidia/llama-3_1-nemotron-safety-guard-8b-v3",
   "model_name": "llama-3_1-nemotron-safety-guard-8b-v3",
   "display_name": "llama-3.1-nemotron-safety-guard-8b-v3",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/llama-3_1-nemotron-safety-guard-8b-v3"
    }
   ],
   "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows",
   "released_at": "2025-10-28",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/llama-3_1-nemotron-safety-guard-8b-v3"
   ],
   "model_type": "safety_detection"
  },
  {
   "slug": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1",
   "model_name": "Llama-3_1-Nemotron-Ultra-253B-v1",
   "display_name": "Llama-3.1-Nemotron-Ultra-253B-v1",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1"
    }
   ],
   "intro": "Flagship Nemotron model for high-throughput reasoning and complex agents",
   "released_at": "2025-01-15",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Llama-3_1-Nemotron-Ultra-253B-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.1-Nemotron-Ultra-253B-v1"
    }
   ]
  },
  {
   "slug": "nvidia/llama-3_2-nemoretriever-300m-embed-v1",
   "model_name": "llama-3_2-nemoretriever-300m-embed-v1",
   "display_name": "llama-3_2-nemoretriever-300m-embed-v1",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/llama-3_2-nemoretriever-300m-embed-v1"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2025-07-24",
   "max_input_tokens": 32768,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/llama-3_2-nemoretriever-300m-embed-v1"
   ],
   "model_type": "text_embedding"
  },
  {
   "slug": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5",
   "model_name": "Llama-3_3-Nemotron-Super-49B-v1_5",
   "display_name": "Nvidia Nemotron Super 49B v1.5",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2025-08-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Llama-3_3-Nemotron-Super-49B-v1_5",
    "nvidia/llama-3_3-nemotron-super-49b-v1_5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nvidia Nemotron Super 49B v1.5"
    }
   ]
  },
  {
   "slug": "nvidia/llama-3-1-nemotron-70b",
   "model_name": "llama-3-1-nemotron-70b",
   "display_name": "Llama 3.1 Nemotron 70B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "family": "Nemotron",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 Nemotron 70B"
    }
   ]
  },
  {
   "slug": "nvidia/llama-3-3-nemotron-super-49b-v1-5",
   "model_name": "llama-3-3-nemotron-super-49b-v1-5",
   "display_name": "Llama 3.3 Nemotron Super 49B v1.5",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+litellm+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "nvidia/Llama-3.3-Nemotron-Super-49B-v1.5"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "nvidia/llama-3.3-nemotron-super-49b-v1.5"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "nvidia/llama-3.3-nemotron-super-49b-v1.5"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2025-07-25",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2024-03",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.6,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Llama-3.3-Nemotron-Super-49B-v1.5",
    "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5",
    "nvidia/Llama-3.3-Nemotron-Super-49B-v1.5",
    "nvidia/llama-3.3-nemotron-super-49b-v1.5"
   ],
   "price_history": [
    {
     "date": "2026-07-04",
     "kind": "limit",
     "old": "26215",
     "new": "131072",
     "note": "max_output_tokens"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.1",
     "new": "0.4"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5"
    }
   ]
  },
  {
   "slug": "nvidia/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B",
   "model_name": "Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B",
   "display_name": "Nemotron Tenyxchat Storybreaker 70b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2024-12-01",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron Tenyxchat Storybreaker 70b"
    }
   ]
  },
  {
   "slug": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
   "model_name": "Llama-3.1-Nemotron-70B-Instruct-HF",
   "display_name": "Nvidia Nemotron 70b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.357"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      }
     },
     "provider_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      }
     },
     "provider_model_id": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2025-04-15",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF"
   ],
   "intro_i18n": {
    "zh-CN": "Llama 3.1 Nemotron 70B 是 NVIDIA 定制的大语言模型，旨在提升有用性。在 Arena Hard、AlpacaEval 2 LC 和 GPT-4-Turbo MT-Bench 三项自动对齐基准测试中均排名第一（截至 2024 年 10 月 1 日）。该模型基于 Llama-3.1-70B-Instruct，通过 RLHF（REINFORCE）、Llama-3.1-Nemotron-70B-Reward 和 HelpSteer2-Preference 提示训练。",
    "zh-TW": "Llama 3.1 Nemotron 70B 是 NVIDIA 客製化的大型語言模型，旨在提升回應的有用性。於 2024 年 10 月 1 日，在 Arena Hard、AlpacaEval 2 LC 和 GPT-4-Turbo MT-Bench 三項自動對齊基準測試中皆排名第一。該模型基於 Llama-3.1-70B-Instruct，並透過 RLHF（REINFORCE）、Llama-3.1-Nemotron-70B-Reward 與 HelpSteer2-Preference 提示進行訓練。",
    "ja-JP": "Llama 3.1 Nemotron 70Bは、NVIDIAがカスタマイズしたLLMで、応答の有用性を向上させるよう設計されています。Arena Hard、AlpacaEval 2 LC、GPT-4-Turbo MT-Benchでトップの成績を収め、2024年10月1日時点で3つの自動アライメントベンチマークすべてで1位を獲得しています。Llama-3.1-70B-Instructをベースに、RLHF（REINFORCE）、Llama-3.1-Nemotron-70B-Reward、HelpSteer2-Preferenceプロンプトでトレーニングされています。",
    "ru-RU": "Llama 3.1 Nemotron 70B — кастомизированная модель от NVIDIA, улучшающая полезность. Демонстрирует высокие результаты на Arena Hard, AlpacaEval 2 LC и GPT-4-Turbo MT-Bench, занимая первое место на всех трёх бенчмарках авто-выравнивания по состоянию на 1 октября 2024 года. Обучена на основе Llama-3.1-70B-Instruct с использованием RLHF (REINFORCE), Llama-3.1-Nemotron-70B-Reward и HelpSteer2-Preference prompts."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nvidia Nemotron 70b"
    }
   ]
  },
  {
   "slug": "nvidia/llama-3.1-nemotron-ultra-253b",
   "model_name": "llama-3.1-nemotron-ultra-253b",
   "display_name": "Llama 3.1 Nemotron Ultra 253B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    }
   ],
   "intro": "Flagship Nemotron model for high-throughput reasoning and complex agents",
   "released_at": "2025-04-07",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 Nemotron Ultra 253B"
    }
   ]
  },
  {
   "slug": "nvidia/llama-3.1-nemotron-ultra-253b-v1:free",
   "model_name": "llama-3.1-nemotron-ultra-253b-v1:free",
   "display_name": "NVIDIA: Llama 3.1 Nemotron Ultra 253B v1",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.537"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.61"
      }
     },
     "provider_model_id": "llama-3.1-nemotron-ultra-253b-v1"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "nvidia/llama-3.1-nemotron-ultra-253b-v1"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "Llama-3.1-Nemotron-Ultra-253B-v1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "llama-3.1-nemotron-ultra-253b-v1"
    }
   ],
   "docs_url": "https://nebius.com/prices-ai-studio",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-07-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Llama-3.1-Nemotron-Ultra-253B-v1",
    "llama-3.1-nemotron-ultra-253b-v1",
    "nvidia/llama-3.1-nemotron-ultra-253b-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA: Llama 3.1 Nemotron Ultra 253B v1"
    }
   ]
  },
  {
   "slug": "nvidia/Llama-3.3-70B-Instruct-FP8",
   "model_name": "Llama-3.3-70B-Instruct-FP8",
   "display_name": "Llama-3.3-70B-Instruct",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "nvidia/Llama-3.3-70B-Instruct-FP8"
    }
   ],
   "intro": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting",
   "released_at": "2024-12-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Llama-3.3-70B-Instruct-FP8"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama-3.3-70B-Instruct"
    }
   ]
  },
  {
   "slug": "nvidia/Llama-3.3-Nemotron-Super-49B-v1",
   "model_name": "Llama-3.3-Nemotron-Super-49B-v1",
   "display_name": "Nvidia Nemotron Super 49B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "nvidia/Llama-3.3-Nemotron-Super-49B-v1"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "llama-3.3-nemotron-super-49b-v1"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2025-08-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true
   },
   "docs_url": "https://nebius.com/prices-ai-studio",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llama-3.3-nemotron-super-49b-v1",
    "nvidia/Llama-3.3-Nemotron-Super-49B-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nvidia Nemotron Super 49B"
    }
   ]
  },
  {
   "slug": "nvidia/llama-nemotron-embed-vl-1b-v2",
   "model_name": "llama-nemotron-embed-vl-1b-v2",
   "display_name": "llama-nemotron-embed-vl-1b-v2",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2026-02-10",
   "max_input_tokens": 32768,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "multimodal_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/llama-nemotron-embed-vl-1b-v2"
   ]
  },
  {
   "slug": "nvidia/llama-nemotron-rerank-vl-1b-v2",
   "model_name": "llama-nemotron-rerank-vl-1b-v2",
   "display_name": "llama-nemotron-rerank-vl-1b-v2",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/llama-nemotron-rerank-vl-1b-v2"
    }
   ],
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2026-03-31",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/llama-nemotron-rerank-vl-1b-v2"
   ],
   "model_type": "text_rerank"
  },
  {
   "slug": "nvidia/llama-v3p1-nemotron-70b-instruct",
   "model_name": "llama-v3p1-nemotron-70b-instruct",
   "display_name": "Llama 3.1 Nemotron 70B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/llama-v3p1-nemotron-70b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 Nemotron 70B"
    }
   ]
  },
  {
   "slug": "nvidia/llama3.1-nemotron-70b-instruct-fp8",
   "model_name": "llama3.1-nemotron-70b-instruct-fp8",
   "display_name": "llama3.1-nemotron-70b-instruct-fp8",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama3.1-nemotron-70b-instruct-fp8"
    }
   ]
  },
  {
   "slug": "nvidia/magpie-tts-zeroshot",
   "model_name": "magpie-tts-zeroshot",
   "display_name": "magpie-tts-zeroshot",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/magpie-tts-zeroshot"
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-05-22",
   "max_input_tokens": 0,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "audio"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "audio_input": true,
    "audio_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/magpie-tts-zeroshot"
   ],
   "model_type": "speech_synthesis"
  },
  {
   "slug": "nvidia/Nemotron-120B-A12B",
   "model_name": "Nemotron-120B-A12B",
   "display_name": "Nemotron Super",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "nvidia/Nemotron-120B-A12B"
    }
   ],
   "intro": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
   "released_at": "2026-03-11",
   "knowledge_cutoff": "2026-02",
   "max_input_tokens": 202800,
   "max_output_tokens": 202800,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Nemotron-120B-A12B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron Super"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-asr-streaming-0.6b",
   "model_name": "nemotron-3-asr-streaming-0.6b",
   "display_name": "Nvidia Nemotron 3 ASR Streaming 0.6B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.000075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-asr-streaming-0.6b"
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "realtime_speech_recognition",
   "capabilities": {
    "audio_input": true,
    "pdf_input": true
   },
   "max_input_tokens": 448,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nemotron-3-asr-streaming-0.6b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nvidia Nemotron 3 ASR Streaming 0.6B"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-content-safety",
   "model_name": "nemotron-3-content-safety",
   "display_name": "nemotron-3-content-safety",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-content-safety"
    }
   ],
   "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows",
   "released_at": "2026-04-16",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nemotron-3-content-safety"
   ],
   "model_type": "safety_detection"
  },
  {
   "slug": "nvidia/nemotron-3-nano-30b",
   "model_name": "nemotron-3-nano-30b",
   "display_name": "Nemotron 3 Nano 30B A3B",
   "vendor": "nvidia",
   "pricing": [],
   "intro": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
   "released_at": "2025-04-14",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron 3 Nano 30B A3B"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-nano-30b-a3b",
   "model_name": "nemotron-3-nano-30b-a3b",
   "display_name": "nemotron-3-nano-30b-a3b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-30b-a3b"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-30b-a3b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "nvidia/Nemotron-3-Nano-30B-A3B"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-30b-a3b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-30b-a3b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-30b-a3b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-30b-a3b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-30b-a3b"
    }
   ],
   "intro": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
   "released_at": "2024-12",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "benchmarks": {
    "intelligence_index": 14.2,
    "coding_index": 14.4,
    "agentic_index": 2
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B",
    "nvidia/Nemotron-3-Nano-30B-A3B",
    "nvidia/nemotron-3-nano-30b-a3b",
    "nvidia/nemotron-3-nano-30b-a3b:free"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "nvidia/Nemotron-3-Nano-Omni",
   "model_name": "Nemotron-3-Nano-Omni",
   "display_name": "Nemotron-3-Nano-Omni",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "nemotron-3-nano-omni"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.006"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "nvidia/Nemotron-3-Nano-Omni"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "nebius/nvidia/nemotron-3-nano-omni"
    }
   ],
   "intro": "Open Nemotron omni model combining reasoning with text, vision, and audio",
   "released_at": "2025-01-20",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 65536,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nebius/nvidia/nemotron-3-nano-omni",
    "nemotron-3-nano-omni",
    "nvidia/Nemotron-3-Nano-Omni"
   ],
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron-3-Nano-Omni"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
   "model_name": "nemotron-3-nano-omni-30b-a3b-reasoning",
   "display_name": "Nemotron 3 Nano Omni",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.105"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free"
    }
   ],
   "intro": "Open Nemotron omni model combining reasoning with text, vision, and audio",
   "released_at": "2026-04-28",
   "max_input_tokens": 256000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "reasoning_config": {
    "budget_min": -1
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "omni",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning",
    "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
    "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free"
   ]
  },
  {
   "slug": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16",
   "model_name": "Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16",
   "display_name": "NVIDIA Nemotron 3 Nano Omni",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "vultr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16"
    }
   ],
   "intro": "Open Nemotron omni model combining reasoning with text, vision, and audio",
   "released_at": "2026-04-28",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16"
   ],
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron 3 Nano Omni"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-fp8",
   "model_name": "nemotron-3-nano-omni-30b-a3b-reasoning-fp8",
   "display_name": "nemotron-3-nano-omni-30b-a3b-reasoning-fp8",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-fp8"
    }
   ],
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "doc"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "omni",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning-fp8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nemotron-3-nano-omni-30b-a3b-reasoning-fp8"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-nano:30b",
   "model_name": "nemotron-3-nano:30b",
   "display_name": "nemotron-3-nano:30b",
   "vendor": "nvidia",
   "pricing": [],
   "intro": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
   "released_at": "2025-12-15",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nemotron-3-nano:30b"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-super",
   "model_name": "nemotron-3-super",
   "display_name": "nemotron-3-super",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nemotron-3-super-free"
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nemotron-3-super-free"
    }
   ],
   "intro": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
   "released_at": "2026-03-11",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2026-02",
   "deprecated": true,
   "status": "deprecated",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nemotron-3-super-free"
   ],
   "intro_i18n": {
    "zh-CN": "Nvidia 的 Nemotron 3 Super Free —— 免费推理模型，具备强大编码能力。",
    "zh-TW": "Nvidia Nemotron 3 Super Free —— 免費級推理模型，擅長程式任務。",
    "ja-JP": "Nemotron 3 Super Free by Nvidia — 強力なコーディングサポートを備えた無料の推論モデル。",
    "ru-RU": "Nemotron 3 Super Free от Nvidia — бесплатная модель рассуждения с высокими возможностями в программировании."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nemotron-3-super"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-super-120b-a12b",
   "model_name": "nemotron-3-super-120b-a12b",
   "display_name": "Nemotron 3 Super",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-super-120b-a12b"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.266"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.799"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.067"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.085"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-super-120b-a12b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-super-120b-a12b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-super-120b-a12b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-super-120b-a12b"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-super-120b-a12b"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-super-120b-a12b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "nebius/nvidia/nemotron-3-super-120b-a12b"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-super-120b-a12b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-super-120b-a12b"
    }
   ],
   "intro": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
   "released_at": "2026-03-11",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "benchmarks": {
    "intelligence_index": 25.4,
    "coding_index": 37.7,
    "agentic_index": 8.7
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nebius/nvidia/nemotron-3-super-120b-a12b",
    "nvidia/nemotron-3-super-120b-a12b",
    "nvidia/nemotron-3-super-120b-a12b:free",
    "nvidia/nemotron-3-super-120b-a12b:thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "perplexity",
     "charge": "completion",
     "old": "0.4",
     "new": "0.45"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "perplexity",
     "charge": "prompt",
     "old": "0.085",
     "new": "0.08"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "openrouter",
     "charge": "completion",
     "old": "0.4",
     "new": "0.45"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "0.085",
     "new": "0.08"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-ultra",
   "model_name": "nemotron-3-ultra",
   "display_name": "nemotron-3-ultra",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nemotron-3-ultra-free"
    }
   ],
   "intro": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
   "released_at": "2026-06-04",
   "max_input_tokens": 262144,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2026-02",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nemotron-3-ultra-free"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nemotron-3-ultra"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-ultra-550b",
   "model_name": "nemotron-3-ultra-550b",
   "display_name": "Nemotron 3 Ultra",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "intro": "Flagship Nemotron model for high-throughput reasoning and complex agents",
   "released_at": "2026-06-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron 3 Ultra"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3-ultra-550b-a55b",
   "model_name": "nemotron-3-ultra-550b-a55b",
   "display_name": "Nemotron 3 Ultra 550B A55B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-ultra-550b-a55b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-ultra-550b-a55b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-ultra-550b-a55b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-ultra-550b-a55b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "nebius/nvidia/nemotron-3-ultra-550b-a55b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-ultra-550b-a55b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "nvidia/nemotron-3-ultra-550b-a55b"
    }
   ],
   "intro": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
   "released_at": "2026-06-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "benchmarks": {
    "intelligence_index": 37.8,
    "coding_index": 49.3,
    "agentic_index": 27.4
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nebius/nvidia/nemotron-3-ultra-550b-a55b",
    "nvidia/nemotron-3-ultra-550b-a55b",
    "nvidia/nemotron-3-ultra-550b-a55b:free",
    "nvidia/nemotron-3-ultra-550b-a55b:thinking"
   ]
  },
  {
   "slug": "nvidia/nemotron-3-ultra-nvfp4",
   "model_name": "nemotron-3-ultra-nvfp4",
   "display_name": "NVIDIA Nemotron 3 Ultra NVFP4",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nemotron-3-ultra-nvfp4"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "fireworks/nemotron-3-ultra-nvfp4"
    }
   ],
   "intro": "Frontier-scale LLM from NVIDIA using a hybrid Latent Mixture-of-Experts (LatentMoE) architecture with interleaved Mamba-2 and MoE layers plus select Attention layers. Features 55B active parameters out of 550B total and Multi-Token Prediction layers for faster generation, optimized for complex multi-step agents, long-context analysis, and high-accuracy reasoning over code, math, and science.",
   "max_input_tokens": 262000,
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-06-13",
   "max_output_tokens": 262144,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nemotron-3-ultra-nvfp4",
    "fireworks/nemotron-3-ultra-nvfp4"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron 3 Ultra NVFP4"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3.5-asr-streaming-0.6b",
   "model_name": "nemotron-3.5-asr-streaming-0.6b",
   "display_name": "nemotron-3.5-asr-streaming-0.6b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.000075"
      }
     },
     "provider_model_id": "nvidia/nemotron-3.5-asr-streaming-0.6b"
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "realtime_speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nemotron-3.5-asr-streaming-0.6b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nemotron-3.5-asr-streaming-0.6b"
    }
   ]
  },
  {
   "slug": "nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b",
   "model_name": "Nemotron-3.5-ASR-Streaming-Multilingual-0.6b",
   "display_name": "Nemotron-3.5-ASR-Streaming-Multilingual-0.6b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0000033333333333"
      }
     },
     "provider_model_id": "nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b"
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "realtime_speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron-3.5-ASR-Streaming-Multilingual-0.6b"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-3.5-content-safety:free",
   "model_name": "nemotron-3.5-content-safety:free",
   "display_name": "Nemotron 3.5 Content Safety (free)",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-3.5-content-safety:free"
    }
   ],
   "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows",
   "released_at": "2026-06-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "safety_detection",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nemotron-3.5-content-safety:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron 3.5 Content Safety (free)"
    }
   ]
  },
  {
   "slug": "nvidia/Nemotron-Cascade-2-30B-A3B",
   "model_name": "Nemotron-Cascade-2-30B-A3B",
   "display_name": "NVIDIA Nemotron Cascade 2",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "vultr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia/Nemotron-Cascade-2-30B-A3B"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Nemotron-Cascade-2-30B-A3B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron Cascade 2"
    }
   ]
  },
  {
   "slug": "nvidia/Nemotron-Content-Safety-3.5",
   "model_name": "Nemotron-Content-Safety-3.5",
   "display_name": "nvidia/Nemotron-Content-Safety-3.5",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "nvidia/Nemotron-Content-Safety-3.5"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "model_type": "safety_detection",
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "max_output_tokens": 131072,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/Nemotron-Content-Safety-3.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia/Nemotron-Content-Safety-3.5"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-content-safety-reasoning-4b",
   "model_name": "nemotron-content-safety-reasoning-4b",
   "display_name": "nemotron-content-safety-reasoning-4b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-content-safety-reasoning-4b"
    }
   ],
   "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows",
   "released_at": "2026-01-22",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nemotron-content-safety-reasoning-4b"
   ],
   "model_type": "safety_detection"
  },
  {
   "slug": "nvidia/nemotron-mini-4b-instruct",
   "model_name": "nemotron-mini-4b-instruct",
   "display_name": "nemotron-mini-4b-instruct",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-mini-4b-instruct"
    }
   ],
   "intro": "Compact Nemotron model for efficient reasoning and deployable AI agents",
   "released_at": "2024-08-21",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nemotron-mini-4b-instruct"
   ],
   "model_type": "text_generation"
  },
  {
   "slug": "nvidia/nemotron-nano-12b-v2-vl",
   "model_name": "nemotron-nano-12b-v2-vl",
   "display_name": "Nvidia Nemotron Nano 12B V2 VL",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia/nemotron-nano-12b-v2-vl"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-nano-12b-v2-vl:free"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia/nemotron-nano-12b-v2-vl"
    }
   ],
   "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
   "released_at": "2025-10-28",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nemotron-nano-12b-v2-vl",
    "nvidia/nemotron-nano-12b-v2-vl:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nvidia Nemotron Nano 12B V2 VL"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-nano-9b-v2",
   "model_name": "nemotron-nano-9b-v2",
   "display_name": "Nvidia Nemotron Nano 9B V2",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.521739"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "nvidia/nemotron-nano-9b-v2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+computeprices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-nano-9b-v2:free"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "nvidia/nemotron-nano-9b-v2"
    }
   ],
   "intro": "Compact Nemotron model for efficient reasoning and deployable AI agents",
   "released_at": "2025-08-18",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nemotron-nano-9b-v2",
    "nvidia/nemotron-nano-9b-v2:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nvidia Nemotron Nano 9B V2"
    }
   ]
  },
  {
   "slug": "nvidia/Nemotron-Nano-V2-12b",
   "model_name": "Nemotron-Nano-V2-12b",
   "display_name": "Nemotron-Nano-V2-12b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.215"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.635"
      }
     },
     "provider_model_id": "nemotron-nano-v2-12b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.007"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "nvidia/Nemotron-Nano-V2-12b"
    }
   ],
   "released_at": "2025-03-15",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nemotron-nano-v2-12b",
    "nvidia/Nemotron-Nano-V2-12b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron-Nano-V2-12b"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-nano-v2-12b-vl",
   "model_name": "nemotron-nano-v2-12b-vl",
   "display_name": "NVIDIA Nemotron Nano 2 VL",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nemotron-nano-v2-12b-vl"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nemotron-nano-v2-12b-vl"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron Nano 2 VL"
    }
   ]
  },
  {
   "slug": "nvidia/nemotron-voicechat",
   "model_name": "nemotron-voicechat",
   "display_name": "nemotron-voicechat",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nemotron-voicechat"
    }
   ],
   "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
   "released_at": "2026-03-16",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "audio_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nemotron-voicechat"
   ],
   "model_type": "text_generation"
  },
  {
   "slug": "nvidia/nv-embed-v1",
   "model_name": "nv-embed-v1",
   "display_name": "nv-embed-v1",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nv-embed-v1"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2024-06-07",
   "max_input_tokens": 32768,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nv-embed-v1"
   ],
   "model_type": "text_embedding"
  },
  {
   "slug": "nvidia/nv-embedcode-7b-v1",
   "model_name": "nv-embedcode-7b-v1",
   "display_name": "nv-embedcode-7b-v1",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nv-embedcode-7b-v1"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2025-03-17",
   "max_input_tokens": 32768,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/nv-embedcode-7b-v1"
   ],
   "model_type": "text_embedding"
  },
  {
   "slug": "nvidia/nvidia-llama-3.1-nemotron-70b-instruct",
   "model_name": "nvidia-llama-3.1-nemotron-70b-instruct",
   "display_name": "nvidia-llama-3.1-nemotron-70b-instruct",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia-llama-3.1-nemotron-70b-instruct"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia-llama-3.3-nemotron-super-49b-v1.5",
   "model_name": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
   "display_name": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia-llama-3.3-nemotron-super-49b-v1.5"
    }
   ]
  },
  {
   "slug": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B",
   "model_name": "NVIDIA-Nemotron-3-Nano-30B-A3B",
   "display_name": "Nemotron-3-Nano-30B-A3B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.066"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.264"
      }
     },
     "provider_model_id": "nvidia-nemotron-3-nano-30b-a3b"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.054"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.215"
      }
     },
     "provider_model_id": "nvidia-nemotron-3-nano-30b-a3b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.006"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "nvidia-nemotron-3-nano-30b-a3b"
    }
   ],
   "intro": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
   "released_at": "2025-08-10",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia-nemotron-3-nano-30b-a3b",
    "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron-3-Nano-30B-A3B"
    }
   ]
  },
  {
   "slug": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
   "model_name": "NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
   "display_name": "NVIDIA Nemotron 3 Nano 30B A3B BF16",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron 3 Nano 30B A3B BF16"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia-nemotron-3-nano-omni",
   "model_name": "nvidia-nemotron-3-nano-omni",
   "display_name": "nvidia-nemotron-3-nano-omni",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.053"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.213"
      }
     }
    }
   ],
   "released_at": "2026-04-29",
   "max_input_tokens": 300000,
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia-nemotron-3-nano-omni"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia-nemotron-3-super-120b",
   "model_name": "nvidia-nemotron-3-super-120b",
   "display_name": "Nemotron-3-Super-120B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     }
    }
   ],
   "intro": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
   "released_at": "2026-03-11",
   "knowledge_cutoff": "2026-02",
   "max_input_tokens": 256000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "status": "beta",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron-3-Super-120B"
    }
   ]
  },
  {
   "slug": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B",
   "model_name": "NVIDIA-Nemotron-3-Super-120B-A12B",
   "display_name": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0275"
      }
     },
     "provider_model_id": "nvidia-nemotron-3-super-120b-a12b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.085"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "max_output_tokens": 262144,
   "released_at": "2026-05-27",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B",
    "nvidia-nemotron-3-super-120b-a12b",
    "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B"
   ],
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "completion",
     "old": "0.5",
     "new": "0.4"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.1",
     "new": "0.085"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B"
    }
   ]
  },
  {
   "slug": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
   "model_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
   "display_name": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA-Nemotron-3-Super-120B-A12B-BF16"
    }
   ]
  },
  {
   "slug": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8",
   "model_name": "NVIDIA-Nemotron-3-Super-120B-A12B-FP8",
   "display_name": "Nemotron 3 Super",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-fp8"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"
    }
   ],
   "intro": "Nemotron 3 is a LatentMoE model designed to deliver strong agentic, reasoning, and conversational capabilities.",
   "released_at": "2026-03-11",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-fp8",
    "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron 3 Super 120B"
    }
   ]
  },
  {
   "slug": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",
   "model_name": "NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4",
   "display_name": "Nemotron 3 Super 120B A12B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-nvfp4"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4"
    }
   ],
   "intro": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
   "released_at": "2026-03-11",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nvidia-nemotron-3-super-120b-a12b-nvfp4",
    "hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron 3 Super 120B A12B"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia-nemotron-3-ultra",
   "model_name": "nvidia-nemotron-3-ultra",
   "display_name": "doubleword/nvidia-nemotron-3-ultra",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "doubleword/nvidia-nemotron-3-ultra"
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubleword/nvidia-nemotron-3-ultra"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubleword/nvidia-nemotron-3-ultra"
    }
   ]
  },
  {
   "slug": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B",
   "model_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B",
   "display_name": "NVIDIA Nemotron 3 Ultra",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.125"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1875"
      }
     },
     "provider_model_id": "nvidia-nemotron-3-ultra-550b-a55b"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B"
    }
   ],
   "intro": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
   "released_at": "2026-06-04",
   "max_input_tokens": 256000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia-nemotron-3-ultra-550b-a55b",
    "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron 3 Ultra"
    }
   ]
  },
  {
   "slug": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16",
   "model_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16",
   "display_name": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "prompt_caching": true,
    "function_calling": true,
    "vision": true,
    "structured_output": true
   },
   "released_at": "2026-06-03",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16"
    }
   ]
  },
  {
   "slug": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4",
   "model_name": "NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4",
   "display_name": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4"
    }
   ],
   "released_at": "2026-06-03",
   "max_input_tokens": 512288,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia-nemotron-3-ultra:flex",
   "model_name": "nvidia-nemotron-3-ultra:flex",
   "display_name": "doubleword/nvidia-nemotron-3-ultra:flex",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.37"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.87"
      }
     },
     "provider_model_id": "doubleword/nvidia-nemotron-3-ultra:flex"
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubleword/nvidia-nemotron-3-ultra:flex"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubleword/nvidia-nemotron-3-ultra:flex"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia-nemotron-cascade-2-30b-a3b",
   "model_name": "nvidia-nemotron-cascade-2-30b-a3b",
   "display_name": "Nemotron Cascade 2 30B A3B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2026-03-24",
   "max_input_tokens": 256000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron Cascade 2 30B A3B"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia-nemotron-nano-12b-v2",
   "model_name": "nvidia-nemotron-nano-12b-v2",
   "display_name": "NVIDIA Nemotron Nano 12B v2 VL BF16",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.73"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.206"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.618"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.93"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.73"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "us-gov-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.73"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.206"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.618"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.93"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.73"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "us-gov-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-12b-v2",
     "region": "us-west-2"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nvidia-nemotron-nano-12b-v2"
    }
   ],
   "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
   "released_at": "2024-12-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/nvidia-nemotron-nano-12b-v2",
    "nvidia.nemotron-nano-12b-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron Nano 12B v2 VL BF16"
    }
   ]
  },
  {
   "slug": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL",
   "model_name": "NVIDIA-Nemotron-Nano-12B-v2-VL",
   "display_name": "nvidia-nemotron-nano-12b-v2-vl",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     },
     "provider_model_id": "nvidia-nemotron-nano-12b-v2-vl"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "deepinfra/nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL"
    }
   ],
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "reasoning": true,
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "released_at": "2025-11-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL",
    "nvidia-nemotron-nano-12b-v2-vl",
    "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia-nemotron-nano-12b-v2-vl"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia-nemotron-nano-9b-v2",
   "model_name": "nvidia-nemotron-nano-9b-v2",
   "display_name": "nvidia-nemotron-nano-9b-v2",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/nvidia-nemotron-nano-9b-v2"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.176"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2369"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.276"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "us-gov-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2369"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "nvidia.nemotron-nano-9b-v2",
     "region": "us-west-2"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "NVIDIA-Nemotron-Nano-9B-v2"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/nvidia-nemotron-nano-9b-v2"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "nvidia/nvidia-nemotron-nano-9b-v2"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.060000000000000005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "nvidia/NVIDIA-Nemotron-Nano-9B-v2"
    }
   ],
   "intro": "Compact Nemotron model for efficient reasoning and deployable AI agents",
   "released_at": "2025-08-18",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NVIDIA-Nemotron-Nano-9B-v2",
    "accounts/fireworks/models/nvidia-nemotron-nano-9b-v2",
    "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2",
    "nvidia.nemotron-nano-9b-v2",
    "nvidia/NVIDIA-Nemotron-Nano-9B-v2",
    "nvidia/nvidia-nemotron-nano-9b-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia.nemotron-nano-3-30b",
   "model_name": "nvidia.nemotron-nano-3-30b",
   "display_name": "NVIDIA Nemotron Nano 3 30B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2472"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.37"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.288"
      }
     },
     "region": "us-gov-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0618"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2472"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.37"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.288"
      }
     },
     "region": "us-gov-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents",
   "released_at": "2025-12-23",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron Nano 3 30B"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia.nemotron-nano-3-30b:0",
   "model_name": "nvidia.nemotron-nano-3-30b:0",
   "display_name": "nvidia.nemotron-nano-3-30b:0",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia.nemotron-nano-3-30b:0"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia.nemotron-nano-9b-v2:0",
   "model_name": "nvidia.nemotron-nano-9b-v2:0",
   "display_name": "nvidia.nemotron-nano-9b-v2:0",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia.nemotron-nano-9b-v2:0"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia.nemotron-super-3-120b",
   "model_name": "nvidia.nemotron-super-3-120b",
   "display_name": "NVIDIA Nemotron 3 Super 120B A12B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.67"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.01"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "us-gov-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.67"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.01"
      }
     },
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.78"
      }
     },
     "region": "us-gov-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
   "released_at": "2026-03-11",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://aws.amazon.com/bedrock/pricing/",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA Nemotron 3 Super 120B A12B"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia.nemotron-super-3-120b:0",
   "model_name": "nvidia.nemotron-super-3-120b:0",
   "display_name": "nvidia.nemotron-super-3-120b:0",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "nvidia.nemotron-super-3-120b:0"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia/Llama-3.1-Nemotron-70B-Instruct",
   "model_name": "nvidia/Llama-3.1-Nemotron-70B-Instruct",
   "display_name": "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "Llama-3.1-Nemotron-70B-Instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "nvidia/llama-3.1-nemotron-70b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "llama-3.1-nemotron-70b-instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-10-15",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Llama-3.1-Nemotron-70B-Instruct",
    "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct",
    "llama-3.1-nemotron-70b-instruct",
    "nvidia/llama-3.1-nemotron-70b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Llama-3.1-Nemotron-70B-Instruct 是 NVIDIA 定制的大语言模型，旨在提升模型响应的有用性。",
    "zh-TW": "Llama-3.1-Nemotron-70B-Instruct 是 NVIDIA 客製化模型，旨在提升大型語言模型回應的有用性。",
    "ja-JP": "Llama-3.1-Nemotron-70B-Instructは、NVIDIAがカスタマイズしたモデルで、LLMの応答の有用性を向上させるよう設計されています。",
    "ru-RU": "Llama-3.1-Nemotron-70B-Instruct — кастомизированная модель от NVIDIA, созданная для повышения полезности ответов LLM."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NVIDIA: Llama 3.1 Nemotron 70B Instruct"
    }
   ]
  },
  {
   "slug": "nvidia/nvidia/nemotron-3-120b-a12b",
   "model_name": "nvidia/nemotron-3-120b-a12b",
   "display_name": "Nemotron 3 Super 120B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "workers-ai/@cf/nvidia/nemotron-3-120b-a12b"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "@cf/nvidia/nemotron-3-120b-a12b"
    }
   ],
   "intro": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
   "released_at": "2026-03-11",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/nvidia/nemotron-3-120b-a12b",
    "workers-ai/@cf/nvidia/nemotron-3-120b-a12b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nemotron 3 Super 120B"
    }
   ]
  },
  {
   "slug": "nvidia/OpenReasoning-Nemotron-32B",
   "model_name": "OpenReasoning-Nemotron-32B",
   "display_name": "OpenReasoning Nemotron 32B",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "pamanseau/OpenReasoning-Nemotron-32B"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2025-08-21",
   "max_input_tokens": 32768,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nemotron",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pamanseau/OpenReasoning-Nemotron-32B"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenReasoning Nemotron 32B"
    }
   ]
  },
  {
   "slug": "nvidia/parakeet-tdt-0.6b-v3",
   "model_name": "parakeet-tdt-0.6b-v3",
   "display_name": "parakeet-tdt-0.6b-v3",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.000025"
      }
     },
     "provider_model_id": "nvidia/parakeet-tdt-0.6b-v3"
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/parakeet-tdt-0.6b-v3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "parakeet-tdt-0.6b-v3"
    }
   ]
  },
  {
   "slug": "nvidia/rerank-qa-mistral-4b",
   "model_name": "rerank-qa-mistral-4b",
   "display_name": "rerank-qa-mistral-4b",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/rerank-qa-mistral-4b"
    }
   ],
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2024-03-17",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/rerank-qa-mistral-4b"
   ],
   "model_type": "text_rerank"
  },
  {
   "slug": "nvidia/riva-translate-4b-instruct-v1_1",
   "model_name": "riva-translate-4b-instruct-v1_1",
   "display_name": "riva-translate-4b-instruct-v1_1",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/riva-translate-4b-instruct-v1_1"
    }
   ],
   "intro": "Translation model for multilingual conversion, localization, and cross-language workflows",
   "released_at": "2025-12-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/riva-translate-4b-instruct-v1_1"
   ],
   "model_type": "text_generation"
  },
  {
   "slug": "nvidia/sarvam-m",
   "model_name": "sarvam-m",
   "display_name": "sarvam-m",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "sarvamai/sarvam-m"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "sarvam-m:free"
    }
   ],
   "intro": "Efficient Indian-language reasoning model for chat, coding, and multilingual work",
   "released_at": "2025-07-25",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sarvam-m:free",
    "sarvamai/sarvam-m"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sarvam-m"
    }
   ]
  },
  {
   "slug": "nvidia/sparsedrive",
   "model_name": "sparsedrive",
   "display_name": "sparsedrive",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/sparsedrive"
    }
   ],
   "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
   "released_at": "2025-03-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "video_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/sparsedrive"
   ],
   "model_type": "vision_understanding"
  },
  {
   "slug": "nvidia/streampetr",
   "model_name": "streampetr",
   "display_name": "streampetr",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/streampetr"
    }
   ],
   "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows",
   "released_at": "2025-11-13",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "video_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/streampetr"
   ],
   "model_type": "vision_understanding"
  },
  {
   "slug": "nvidia/studiovoice",
   "model_name": "studiovoice",
   "display_name": "studiovoice",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/studiovoice"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2024-10-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/studiovoice"
   ],
   "model_type": "text_generation"
  },
  {
   "slug": "nvidia/synthetic-video-detector",
   "model_name": "synthetic-video-detector",
   "display_name": "synthetic-video-detector",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/synthetic-video-detector"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2026-04-16",
   "max_input_tokens": 0,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "video_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/synthetic-video-detector"
   ],
   "model_type": "vision_understanding"
  },
  {
   "slug": "nvidia/usdcode",
   "model_name": "usdcode",
   "display_name": "usdcode",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/usdcode"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2026-01-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/usdcode"
   ],
   "model_type": "text_generation"
  },
  {
   "slug": "nvidia/usdvalidate",
   "model_name": "usdvalidate",
   "display_name": "usdvalidate",
   "vendor": "nvidia",
   "pricing": [
    {
     "provider": "nvidia",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "nvidia/usdvalidate"
    }
   ],
   "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
   "released_at": "2024-07-24",
   "max_input_tokens": 0,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nvidia/usdvalidate"
   ],
   "model_type": "text_generation"
  },
  {
   "slug": "openai/120b",
   "model_name": "120b",
   "display_name": "openai/120b",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2283279"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.856229625"
      }
     },
     "provider_model_id": "openai/120b"
    }
   ],
   "released_at": "2025-08-05",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/120b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.85778061",
     "new": "0.856229625"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.228741496",
     "new": "0.2283279"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.8574494775",
     "new": "0.85778061"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.228653194",
     "new": "0.228741496"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.8581060725",
     "new": "0.8574494775"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.228828286",
     "new": "0.228653194"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.85776063",
     "new": "0.8581060725"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.228736168",
     "new": "0.228828286"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.8579984025",
     "new": "0.85776063"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.228799574",
     "new": "0.228736168"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.85357275",
     "new": "0.8579984025"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2276194",
     "new": "0.228799574"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/120b"
    }
   ]
  },
  {
   "slug": "openai/ada",
   "model_name": "ada",
   "display_name": "ada",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "capabilities": {},
   "max_input_tokens": 8191,
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ada"
    }
   ]
  },
  {
   "slug": "openai/ada-v2",
   "model_name": "ada-v2",
   "display_name": "ada-v2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ada-v2"
    }
   ]
  },
  {
   "slug": "openai/azure-gpt-4-turbo",
   "model_name": "azure-gpt-4-turbo",
   "display_name": "Azure gpt-4-turbo",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30.005"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-11-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Azure gpt-4-turbo"
    }
   ]
  },
  {
   "slug": "openai/azure-gpt-4o",
   "model_name": "azure-gpt-4o",
   "display_name": "Azure gpt-4o",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.499"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.996"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-05-13",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Azure gpt-4o"
    }
   ]
  },
  {
   "slug": "openai/azure-gpt-4o-mini",
   "model_name": "azure-gpt-4o-mini",
   "display_name": "Azure gpt-4o-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1496"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.595"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-07-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Azure gpt-4o-mini"
    }
   ]
  },
  {
   "slug": "openai/azure-o3-mini",
   "model_name": "azure-o3-mini",
   "display_name": "Azure o3-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.088"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.3996"
      }
     }
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2025-01-31",
   "max_input_tokens": 200000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Azure o3-mini"
    }
   ]
  },
  {
   "slug": "openai/babbage",
   "model_name": "babbage",
   "display_name": "babbage",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "babbage"
    }
   ]
  },
  {
   "slug": "openai/babbage-002",
   "model_name": "babbage-002",
   "display_name": "babbage-002",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "capabilities": {},
   "released_at": "2023-08-21",
   "knowledge_cutoff": "2021-09",
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "babbage-002"
    }
   ]
  },
  {
   "slug": "openai/chat-completion/models/gpt-oss-120b-high-throughput",
   "model_name": "chat-completion/models/gpt-oss-120b-high-throughput",
   "display_name": "GPT OSS 120B High Throughput",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "openai/chat-completion/models/gpt-oss-120b-high-throughput"
    }
   ],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/chat-completion/models/gpt-oss-120b-high-throughput"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT OSS 120B High Throughput"
    }
   ]
  },
  {
   "slug": "openai/chat-latest",
   "model_name": "chat-latest",
   "display_name": "Chat Latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey+lobehub-modelbank+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/chat-latest"
    }
   ],
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "vision": true,
    "web_search": true,
    "pdf_input": true
   },
   "released_at": "2026-05-05",
   "knowledge_cutoff": "2025-08",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/chat-latest"
   ],
   "intro_i18n": {
    "zh-CN": "ChatGPT 使用的最新即时模型。",
    "zh-TW": "ChatGPT 使用的最新即時模型。",
    "ja-JP": "ChatGPTで使用される最新のインスタントモデル。",
    "ru-RU": "Последняя мгновенная модель, используемая в ChatGPT."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Chat Latest"
    }
   ]
  },
  {
   "slug": "openai/chatgpt-4o-latest",
   "model_name": "chatgpt-4o-latest",
   "display_name": "chatgpt-4o-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "openai/chatgpt-4o-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/chatgpt-4o-latest"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     },
     "provider_model_id": "openai/chatgpt-4o-latest"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "intro": "OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of GPT-4o in that it has additional RLHF. It is intended for research and evaluation.",
   "modalities": {
    "input": [
     "image",
     "pdf"
    ],
    "output": []
   },
   "knowledge_cutoff": "2024-08",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "released_at": "2024-08-08",
   "family": "gpt",
   "deprecated": true,
   "status": "deprecated",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/chatgpt-4o-latest"
   ],
   "intro_i18n": {
    "zh-CN": "ChatGPT-4o是一个实时更新的动态模型，结合了强大的语言理解和生成能力，适用于客户支持、教育和技术协助等大规模应用场景。",
    "zh-TW": "ChatGPT-4o 是一個實時更新的動態模型，結合了強大的語言理解和生成能力，適用於大規模使用場景，如客戶支持、教育和技術協助。",
    "ja-JP": "ChatGPT-4oはリアルタイムで更新される動的モデルです。強力な言語理解と生成能力を組み合わせ、カスタマーサポート、教育、技術支援などの大規模なユースケースに対応します。",
    "ru-RU": "ChatGPT-4o — это динамическая модель, обновляемая в реальном времени. Она сочетает в себе мощное понимание языка и генерацию для масштабных сценариев использования, таких как поддержка клиентов, образование и техническая помощь."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/chatgpt-image-latest",
   "model_name": "chatgpt-image-latest",
   "display_name": "chatgpt-image-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-12-16",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "gpt-image",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/code-davinci-edit-001",
   "model_name": "code-davinci-edit-001",
   "display_name": "code-davinci-edit-001",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-davinci-edit-001"
    }
   ]
  },
  {
   "slug": "openai/codex-mini",
   "model_name": "codex-mini",
   "display_name": "Codex Mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "codex-mini-2025-05-16"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     },
     "provider_model_id": "openai/codex-mini"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "openai/codex-mini"
    }
   ],
   "intro": "codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "released_at": "2025-05-16",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "aliases": [
    "codex-mini-2025-05-16",
    "openai/codex-mini"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Codex Mini"
    }
   ]
  },
  {
   "slug": "openai/codex-mini-latest",
   "model_name": "codex-mini-latest",
   "display_name": "codex-mini-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+helicone-registry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.375"
      }
     }
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "intro": "Latest version of Codex Mini, a compact specialized model for code generation and analysis",
   "knowledge_cutoff": "2025-01",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_completion_tokens",
     "response_format",
     "seed",
     "stop",
     "tool_choice",
     "tools"
    ],
    "unsupported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "temperature",
     "top_logprobs",
     "top_p",
     "verbosity"
    ]
   },
   "released_at": "2025-01-01",
   "family": "gpt-codex-mini",
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/computer-use",
   "model_name": "computer-use",
   "display_name": "computer-use",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "computer-use"
    }
   ]
  },
  {
   "slug": "openai/computer-use-preview",
   "model_name": "computer-use-preview",
   "display_name": "Computer Use Preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "computer-use-preview-2025-03-11",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "computer-use-preview-2025-04-15"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 1024,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "released_at": "2025-03-11",
   "knowledge_cutoff": "2023-10",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "aliases": [
    "computer-use-preview-2025-03-11",
    "computer-use-preview-2025-04-15"
   ],
   "intro_i18n": {
    "zh-CN": "computer-use-preview 是为“计算机使用工具”专门训练的模型，能够理解并执行与计算机相关的任务。",
    "zh-TW": "computer-use-preview 是一款專為「電腦使用工具」訓練的模型，能理解並執行與電腦相關的任務。",
    "ja-JP": "computer-use-previewは「コンピュータ使用ツール」専用に訓練されたモデルであり、コンピュータ関連のタスクを理解し実行する能力を持ちます。",
    "ru-RU": "computer-use-preview — специализированная модель для инструмента \"использование компьютера\", обученная понимать и выполнять задачи, связанные с компьютером."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Computer Use Preview"
    }
   ]
  },
  {
   "slug": "openai/curie",
   "model_name": "curie",
   "display_name": "curie",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "curie"
    }
   ]
  },
  {
   "slug": "openai/dall-e-2",
   "model_name": "dall-e-2",
   "display_name": "dall-e-2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey+llmdb",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.02"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.02"
      },
      "image_output_512px": {
       "unit": "per_image",
       "price": "0.018"
      },
      "image_output_256x256": {
       "unit": "per_image",
       "price": "0.016"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.02"
      },
      "image_output_512px": {
       "unit": "per_image",
       "price": "0.018"
      },
      "image_output_256x256": {
       "unit": "per_image",
       "price": "0.016"
      }
     }
    }
   ],
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "stream": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "released_at": "2022-04-06",
   "deprecated": true,
   "family": "dall-e",
   "status": "deprecated",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/dall-e-3",
   "model_name": "dall-e-3",
   "display_name": "dall-e-3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey+llmdb",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.04"
      },
      "image_output_1024x1792": {
       "unit": "per_image",
       "price": "0.08"
      },
      "image_output_1792x1024": {
       "unit": "per_image",
       "price": "0.08"
      },
      "image_output_hd": {
       "unit": "per_image",
       "price": "0.08"
      },
      "image_output_1024px_hd": {
       "unit": "per_image",
       "price": "0.08"
      },
      "image_output_1024x1792_hd": {
       "unit": "per_image",
       "price": "0.12"
      },
      "image_output_1792x1024_hd": {
       "unit": "per_image",
       "price": "0.12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.04"
      },
      "image_output_1024x1792": {
       "unit": "per_image",
       "price": "0.08"
      },
      "image_output_1792x1024": {
       "unit": "per_image",
       "price": "0.08"
      },
      "image_output_hd": {
       "unit": "per_image",
       "price": "0.08"
      },
      "image_output_1024px_hd": {
       "unit": "per_image",
       "price": "0.08"
      },
      "image_output_1024x1792_hd": {
       "unit": "per_image",
       "price": "0.12"
      },
      "image_output_1792x1024_hd": {
       "unit": "per_image",
       "price": "0.12"
      }
     }
    }
   ],
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "released_at": "2023-10-01",
   "deprecated": true,
   "family": "dall-e",
   "status": "deprecated",
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "max_input_tokens": 800,
   "max_output_tokens": 0,
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/dall-e-3"
   ],
   "intro_i18n": {
    "zh-CN": "DALL·E 3",
    "zh-TW": "DALL·E 3",
    "ja-JP": "DALL·E 3",
    "ru-RU": "DALL·E 3"
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-5",
   "model_name": "databricks-gpt-5",
   "display_name": "GPT-5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "intro": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-5-1",
   "model_name": "databricks-gpt-5-1",
   "display_name": "GPT-5.1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "intro": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
   "released_at": "2025-11-13",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.1"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-5-2",
   "model_name": "databricks-gpt-5-2",
   "display_name": "GPT-5.2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    }
   ],
   "intro": "Reliable GPT generation for broad coding, writing, and tool-assisted product work",
   "released_at": "2025-12-11",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.2"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-5-4",
   "model_name": "databricks-gpt-5-4",
   "display_name": "GPT-5.4",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
   "released_at": "2026-03-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-5-4-mini",
   "model_name": "databricks-gpt-5-4-mini",
   "display_name": "GPT-5.4 mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    }
   ],
   "intro": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
   "released_at": "2026-03-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4 mini"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-5-4-nano",
   "model_name": "databricks-gpt-5-4-nano",
   "display_name": "GPT-5.4 nano",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    }
   ],
   "intro": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
   "released_at": "2026-03-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-nano",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4 nano"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-5-5",
   "model_name": "databricks-gpt-5-5",
   "display_name": "GPT-5.5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Default frontier GPT for coding, computer use, research, and knowledge work",
   "released_at": "2026-04-23",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.5"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-5-mini",
   "model_name": "databricks-gpt-5-mini",
   "display_name": "GPT-5 Mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    }
   ],
   "intro": "Small GPT-5 for responsive agents, coding help, and everyday automation",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5 Mini"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-5-nano",
   "model_name": "databricks-gpt-5-nano",
   "display_name": "GPT-5 Nano",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     }
    }
   ],
   "intro": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-nano",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5 Nano"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-oss-120b",
   "model_name": "databricks-gpt-oss-120b",
   "display_name": "GPT OSS 120B",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    }
   ],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT OSS 120B"
    }
   ]
  },
  {
   "slug": "openai/databricks-gpt-oss-20b",
   "model_name": "databricks-gpt-oss-20b",
   "display_name": "GPT OSS 20B",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT OSS 20B"
    }
   ]
  },
  {
   "slug": "openai/davinci",
   "model_name": "davinci",
   "display_name": "davinci",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "davinci"
    }
   ]
  },
  {
   "slug": "openai/davinci-002",
   "model_name": "davinci-002",
   "display_name": "davinci-002",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "capabilities": {},
   "released_at": "2023-08-21",
   "knowledge_cutoff": "2021-09",
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "davinci-002"
    }
   ]
  },
  {
   "slug": "openai/distil-whisper-large-v3-en",
   "model_name": "distil-whisper-large-v3-en",
   "display_name": "distil-whisper-large-v3-en",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.556"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.556"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": []
   },
   "capabilities": {
    "pdf_input": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "speech_recognition",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "distil-whisper-large-v3-en"
    }
   ]
  },
  {
   "slug": "openai/duo-chat-gpt-5-1",
   "model_name": "duo-chat-gpt-5-1",
   "display_name": "Agentic Chat (GPT-5.1)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2026-01-22",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (GPT-5.1)"
    }
   ]
  },
  {
   "slug": "openai/duo-chat-gpt-5-2",
   "model_name": "duo-chat-gpt-5-2",
   "display_name": "Agentic Chat (GPT-5.2)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2026-01-23",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (GPT-5.2)"
    }
   ]
  },
  {
   "slug": "openai/duo-chat-gpt-5-2-codex",
   "model_name": "duo-chat-gpt-5-2-codex",
   "display_name": "Agentic Chat (GPT-5.2 Codex)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2026-01-22",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (GPT-5.2 Codex)"
    }
   ]
  },
  {
   "slug": "openai/duo-chat-gpt-5-3-codex",
   "model_name": "duo-chat-gpt-5-3-codex",
   "display_name": "Agentic Chat (GPT-5.3 Codex)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (GPT-5.3 Codex)"
    }
   ]
  },
  {
   "slug": "openai/duo-chat-gpt-5-4",
   "model_name": "duo-chat-gpt-5-4",
   "display_name": "Agentic Chat (GPT-5.4)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2026-03-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (GPT-5.4)"
    }
   ]
  },
  {
   "slug": "openai/duo-chat-gpt-5-4-mini",
   "model_name": "duo-chat-gpt-5-4-mini",
   "display_name": "Agentic Chat (GPT-5.4 Mini)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2026-03-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (GPT-5.4 Mini)"
    }
   ]
  },
  {
   "slug": "openai/duo-chat-gpt-5-4-nano",
   "model_name": "duo-chat-gpt-5-4-nano",
   "display_name": "Agentic Chat (GPT-5.4 Nano)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2026-03-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-nano",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (GPT-5.4 Nano)"
    }
   ]
  },
  {
   "slug": "openai/duo-chat-gpt-5-5",
   "model_name": "duo-chat-gpt-5-5",
   "display_name": "Agentic Chat (GPT-5.5)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2026-04-23",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (GPT-5.5)"
    }
   ]
  },
  {
   "slug": "openai/duo-chat-gpt-5-codex",
   "model_name": "duo-chat-gpt-5-codex",
   "display_name": "Agentic Chat (GPT-5 Codex)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2026-01-22",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (GPT-5 Codex)"
    }
   ]
  },
  {
   "slug": "openai/duo-chat-gpt-5-mini",
   "model_name": "duo-chat-gpt-5-mini",
   "display_name": "Agentic Chat (GPT-5 Mini)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2026-01-22",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (GPT-5 Mini)"
    }
   ]
  },
  {
   "slug": "openai/e2ee-gpt-oss-120b-p",
   "model_name": "e2ee-gpt-oss-120b-p",
   "display_name": "GPT OSS 120B",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     }
    }
   ],
   "released_at": "2026-03-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT OSS 120B"
    }
   ]
  },
  {
   "slug": "openai/e2ee-gpt-oss-20b-p",
   "model_name": "e2ee-gpt-oss-20b-p",
   "display_name": "GPT OSS 20B",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    }
   ],
   "released_at": "2026-03-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT OSS 20B"
    }
   ]
  },
  {
   "slug": "openai/ft:gpt-3.5-turbo",
   "model_name": "ft:gpt-3.5-turbo",
   "display_name": "ft:gpt-3.5-turbo",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "max_input_tokens": 16385,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   }
  },
  {
   "slug": "openai/ft:gpt-3.5-turbo-",
   "model_name": "ft:gpt-3.5-turbo-",
   "display_name": "ft:gpt-3.5-turbo-",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "intro": "GPT-3.5 Turbo fine tuned.",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ft:gpt-3.5-turbo-"
    }
   ]
  },
  {
   "slug": "openai/ft:gpt-3.5-turbo-0125",
   "model_name": "ft:gpt-3.5-turbo-0125",
   "display_name": "ft:gpt-3.5-turbo-0125",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "max_input_tokens": 16385,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   }
  },
  {
   "slug": "openai/ft:gpt-3.5-turbo-0613",
   "model_name": "ft:gpt-3.5-turbo-0613",
   "display_name": "ft:gpt-3.5-turbo-0613",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   }
  },
  {
   "slug": "openai/ft:gpt-3.5-turbo-1106",
   "model_name": "ft:gpt-3.5-turbo-1106",
   "display_name": "ft:gpt-3.5-turbo-1106",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "max_input_tokens": 16385,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   }
  },
  {
   "slug": "openai/ft:gpt-4-0613",
   "model_name": "ft:gpt-4-0613",
   "display_name": "ft:gpt-4-0613",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    }
   ],
   "docs_url": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing",
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   }
  },
  {
   "slug": "openai/ft:gpt-4.1-2025-04-14",
   "model_name": "ft:gpt-4.1-2025-04-14",
   "display_name": "ft:gpt-4.1-2025-04-14",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ft:gpt-4.1"
    }
   ],
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "ft:gpt-4.1"
   ]
  },
  {
   "slug": "openai/ft:gpt-4.1-mini-2025-04-14",
   "model_name": "ft:gpt-4.1-mini-2025-04-14",
   "display_name": "ft:gpt-4.1-mini-2025-04-14",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ft:gpt-4.1-mini"
    }
   ],
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "ft:gpt-4.1-mini"
   ]
  },
  {
   "slug": "openai/ft:gpt-4.1-nano-2025-04-14",
   "model_name": "ft:gpt-4.1-nano-2025-04-14",
   "display_name": "ft:gpt-4.1-nano-2025-04-14",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   }
  },
  {
   "slug": "openai/ft:gpt-4o-2024-11-20",
   "model_name": "ft:gpt-4o-2024-11-20",
   "display_name": "ft:gpt-4o-2024-11-20",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.875"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.875"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "ft:gpt-4o-2024-08-06"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "intro": "GPT-4o fine tuned.",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "ft:gpt-4o",
    "ft:gpt-4o-2024-08-06"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "openai/ft:gpt-4o-mini-2024-07-18",
   "model_name": "ft:gpt-4o-mini-2024-07-18",
   "display_name": "ft:gpt-4o-mini-2024-07-18",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ft:gpt-4o-mini"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "intro": "GPT-4o Mini fine tuned.",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "ft:gpt-4o-mini"
   ]
  },
  {
   "slug": "openai/ft:o4-mini-2025-04-16",
   "model_name": "ft:o4-mini-2025-04-16",
   "display_name": "ft:o4-mini-2025-04-16",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   }
  },
  {
   "slug": "openai/gpt-3-5",
   "model_name": "gpt-3-5",
   "display_name": "GPT-3.5 Turbo",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     },
     "provider_model_id": "gpt-3.5"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "capabilities": {},
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-3.5"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-3.5 Turbo"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-0301",
   "model_name": "gpt-3.5-0301",
   "display_name": "gpt-3.5-0301",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "1",
        "completion": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-3.5-0301"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-turbo",
   "model_name": "gpt-3.5-turbo",
   "display_name": "GPT-3.5-turbo",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-03-01",
   "knowledge_cutoff": "2021-09",
   "max_input_tokens": 16385,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": null,
    "coding_index": 10.7,
    "agentic_index": null
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-3.5-turbo"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-3.5 Turbo 用于文本生成与理解；当前指向 gpt-3.5-turbo-0125。",
    "zh-TW": "GPT 3.5 Turbo 用於文字生成與理解，目前指向 gpt-3.5-turbo-0125。",
    "ja-JP": "GPT-3.5 Turbo はテキスト生成と理解のためのモデルで、現在は gpt-3.5-turbo-0125 を指しています。",
    "ru-RU": "GPT 3.5 Turbo для генерации и понимания текста; в настоящее время указывает на gpt-3.5-turbo-0125."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-turbo-0125",
   "model_name": "gpt-3.5-turbo-0125",
   "display_name": "gpt-3.5-turbo-0125",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-0125"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-0125"
    }
   ],
   "max_input_tokens": 16385,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-01-25",
   "knowledge_cutoff": "2021-09",
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "family": "gpt",
   "deprecated": true,
   "deprecation_date": "2025-03-31",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-3.5-turbo-0125"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-3.5 Turbo 用于文本生成与理解；当前指向 gpt-3.5-turbo-0125。",
    "zh-TW": "GPT 3.5 Turbo 用於文字生成與理解，目前指向 gpt-3.5-turbo-0125。",
    "ja-JP": "GPT-3.5 Turbo はテキスト生成と理解のためのモデルで、現在は gpt-3.5-turbo-0125 を指しています。",
    "ru-RU": "GPT 3.5 Turbo для генерации и понимания текста; в настоящее время указывает на gpt-3.5-turbo-0125."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-turbo-0301",
   "model_name": "gpt-3.5-turbo-0301",
   "display_name": "GPT-3.5 Turbo 0301",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-03-01",
   "knowledge_cutoff": "2021-08",
   "max_input_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-3.5 Turbo 0301"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-turbo-0613",
   "model_name": "gpt-3.5-turbo-0613",
   "display_name": "GPT-3.5 Turbo 0613",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9999999995"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-0613"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-0613"
    }
   ],
   "max_input_tokens": 16385,
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "pdf_input": true
   },
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-06-13",
   "knowledge_cutoff": "2021-08",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_completion_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-3.5-turbo-0613"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-3.5 Turbo 0613"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-turbo-1106",
   "model_name": "gpt-3.5-turbo-1106",
   "display_name": "gpt-3.5-turbo-1106",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-1106"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-1106"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-1106"
    }
   ],
   "max_input_tokens": 16385,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "deprecation_date": "2026-09-28",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "released_at": "2023-11-06",
   "knowledge_cutoff": "2021-09",
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-3.5-turbo-1106"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-3.5 Turbo 用于文本生成与理解；当前指向 gpt-3.5-turbo-0125。",
    "zh-TW": "GPT 3.5 Turbo 用於文字生成與理解，目前指向 gpt-3.5-turbo-0125。",
    "ja-JP": "GPT-3.5 Turbo はテキスト生成と理解のためのモデルで、現在は gpt-3.5-turbo-0125 を指しています。",
    "ru-RU": "GPT 3.5 Turbo для генерации и понимания текста; в настоящее время указывает на gpt-3.5-turbo-0125."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-turbo-16k",
   "model_name": "gpt-3.5-turbo-16k",
   "display_name": "gpt-3.5-turbo-16k",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.999999999"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20.52"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-16k"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-16k"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-16k"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-16k"
    }
   ],
   "max_input_tokens": 16385,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "intro": "This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.",
   "released_at": "2023-08-28",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2021-09",
   "family": "gpt",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_completion_tokens",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-3.5-turbo-16k"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "completion",
     "old": "14.01",
     "new": "20.52"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "prompt",
     "old": "6.99",
     "new": "10.26"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-turbo-16k-0613",
   "model_name": "gpt-3.5-turbo-16k-0613",
   "display_name": "gpt-3.5-turbo-16k-0613",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.999999999"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-3.5-turbo-16k-0613"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-turbo-instruct",
   "model_name": "gpt-3.5-turbo-instruct",
   "display_name": "GPT-3.5 Turbo Instruct",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9999999995"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-instruct"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-instruct"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-instruct"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-instruct"
    }
   ],
   "intro": "GPT-3.5 Turbo offers a balance between cost and performance.",
   "max_input_tokens": 16385,
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "stream": true,
    "structured_output": true,
    "pdf_input": true
   },
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "knowledge_cutoff": "2021-09",
   "released_at": "2023-08-24",
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-3.5-turbo-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-3.5 Turbo 优化用于指令跟随的文本生成与理解任务。",
    "zh-TW": "GPT 3.5 Turbo 用於文字生成與理解任務，針對指令遵循進行最佳化。",
    "ja-JP": "GPT-3.5 Turbo は、指示に従うタスクに最適化されたテキスト生成・理解モデルです。",
    "ru-RU": "GPT 3.5 Turbo для задач генерации и понимания текста, оптимизирован для выполнения инструкций."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-3.5 Turbo Instruct"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-turbo-instruct-0914",
   "model_name": "gpt-3.5-turbo-instruct-0914",
   "display_name": "gpt-3.5-turbo-instruct-0914",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-3.5-turbo-instruct-0914"
    }
   ]
  },
  {
   "slug": "openai/gpt-3.5-turbo-raw",
   "model_name": "gpt-3.5-turbo-raw",
   "display_name": "GPT-3.5-Turbo-Raw",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "openai/gpt-3.5-turbo-raw"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-09-27",
   "max_input_tokens": 4524,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-3.5-turbo-raw"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-3.5-Turbo-Raw"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo",
   "model_name": "gpt-35-turbo",
   "display_name": "gpt-35-turbo",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "max_input_tokens": 4097,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GPT-3.5 Turbo 是 OpenAI 高效的聊天与文本生成模型，支持并行函数调用。",
    "zh-TW": "GPT-3.5 Turbo 是 OpenAI 推出的高效模型，支援聊天與文字生成，具備平行函數呼叫能力。",
    "ja-JP": "GPT-3.5 Turbo は OpenAI の効率的なチャット・テキスト生成モデルで、並列関数呼び出しをサポートします。",
    "ru-RU": "GPT-3.5 Turbo — эффективная модель от OpenAI для чатов и генерации текста с поддержкой параллельного вызова функций."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-0125",
   "model_name": "gpt-35-turbo-0125",
   "display_name": "gpt-35-turbo-0125",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 4096,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2025-05-31",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-0125"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-0125.ft",
   "model_name": "gpt-35-turbo-0125.ft",
   "display_name": "gpt-35-turbo-0125.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-0125.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-0301",
   "model_name": "gpt-35-turbo-0301",
   "display_name": "gpt-35-turbo-0301",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-0301"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-0613",
   "model_name": "gpt-35-turbo-0613",
   "display_name": "gpt-35-turbo-0613",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-0613"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-0613.ft",
   "model_name": "gpt-35-turbo-0613.ft",
   "display_name": "gpt-35-turbo-0613.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-0613.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-1106",
   "model_name": "gpt-35-turbo-1106",
   "display_name": "gpt-35-turbo-1106",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 4096,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2025-03-31",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-1106"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-1106.ft",
   "model_name": "gpt-35-turbo-1106.ft",
   "display_name": "gpt-35-turbo-1106.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-1106.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-16k",
   "model_name": "gpt-35-turbo-16k",
   "display_name": "gpt-35-turbo-16k",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "max_input_tokens": 16385,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GPT-3.5 Turbo 16k 是一款高容量文本生成模型，适用于复杂任务。",
    "zh-TW": "GPT-3.5 Turbo 16k 是一款高容量文字生成模型，適用於複雜任務。",
    "ja-JP": "GPT-3.5 Turbo 16k は、複雑なタスクに対応する高容量のテキスト生成モデルです。",
    "ru-RU": "GPT-3.5 Turbo 16k — высокоёмкая модель генерации текста для сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-16k"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-16k-0613",
   "model_name": "gpt-35-turbo-16k-0613",
   "display_name": "gpt-35-turbo-16k-0613",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    }
   ],
   "max_input_tokens": 16385,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-16k-0613"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-instruct",
   "model_name": "gpt-35-turbo-instruct",
   "display_name": "gpt-35-turbo-instruct",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "max_input_tokens": 4097,
   "max_output_tokens": 4097,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-instruct"
    }
   ]
  },
  {
   "slug": "openai/gpt-35-turbo-instruct-0914",
   "model_name": "gpt-35-turbo-instruct-0914",
   "display_name": "gpt-35-turbo-instruct-0914",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "max_input_tokens": 4097,
   "max_output_tokens": 4097,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-35-turbo-instruct-0914"
    }
   ]
  },
  {
   "slug": "openai/gpt-4",
   "model_name": "gpt-4",
   "display_name": "GPT-4",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.84"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/gpt-4"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/gpt-4"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/gpt-4"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/gpt-4"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/gpt-4"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    }
   ],
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2023-11-06",
   "knowledge_cutoff": "2023-11",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": null,
    "coding_index": 13.1,
    "agentic_index": null
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_completion_tokens",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-4"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4 提供更大的上下文窗口，适用于信息整合与数据分析等任务。",
    "zh-TW": "GPT-4 提供更大的上下文視窗，能處理更長的輸入，適合廣泛資訊整合與資料分析。",
    "ja-JP": "GPT-4 はより大きなコンテキストウィンドウを提供し、長文入力に対応。広範な情報統合やデータ分析に適しています。",
    "ru-RU": "GPT-4 предоставляет расширенное контекстное окно для обработки длинных входных данных, что делает его подходящим для комплексного анализа информации и синтеза данных."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-0125",
   "model_name": "gpt-4-0125",
   "display_name": "gpt-4-0125",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.29"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "gpt-4-0125"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-0125-preview",
   "model_name": "gpt-4-0125-preview",
   "display_name": "gpt-4-0125-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "gpt-4-0125-Preview"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-03-26",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2023-12",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4-0125-Preview"
   ],
   "intro_i18n": {
    "zh-CN": "最新的 GPT-4 Turbo 模型支持视觉功能。视觉请求可以使用 JSON 模式和函数调用。GPT-4 Turbo 是增强版，平衡了准确性和效率，适用于具有成本效益的多模态任务和实时交互。",
    "zh-TW": "最新的 GPT-4 Turbo 模型包含視覺功能。視覺請求可使用 JSON 模式和函數調用。GPT-4 Turbo 是一個增強版，平衡了準確性和效率，適用於成本效益高的多模態任務和即時交互。",
    "ja-JP": "最新のGPT-4 Turboモデルにはビジョンが含まれています。ビジョンリクエストはJSONモードと関数呼び出しを使用できます。GPT-4 Turboは、コスト効率の高いマルチモーダルタスクとリアルタイムインタラクションのために、精度と効率のバランスを取った強化版です。",
    "ru-RU": "Последняя модель GPT-4 Turbo включает поддержку зрения. Запросы с использованием зрения могут использовать режим JSON и вызов функций. GPT-4 Turbo — это улучшенная версия, которая балансирует точность и эффективность для экономичных мультимодальных задач и взаимодействий в реальном времени."
   }
  },
  {
   "slug": "openai/gpt-4-0314",
   "model_name": "gpt-4-0314",
   "display_name": "gpt-4-0314",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/gpt-4-0314"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/gpt-4-0314"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-03-26",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2023-05-28",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-4-0314"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-0613",
   "model_name": "gpt-4-0613",
   "display_name": "gpt-4-0613",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/gpt-4-0613"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2025-06-06",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2023-06-13",
   "knowledge_cutoff": "2021-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-4-0613"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4 提供更大的上下文窗口，适用于处理更长的输入，适合信息整合与数据分析。",
    "zh-TW": "GPT-4 提供更大的上下文視窗，能處理更長的輸入，適合廣泛資訊整合與資料分析。",
    "ja-JP": "GPT-4 はより大きなコンテキストウィンドウを提供し、長文入力に対応。広範な情報統合やデータ分析に適しています。",
    "ru-RU": "GPT-4 предоставляет расширенное контекстное окно для обработки длинных входных данных, что делает его подходящим для комплексного анализа информации и синтеза данных."
   }
  },
  {
   "slug": "openai/gpt-4-1106",
   "model_name": "gpt-4-1106",
   "display_name": "gpt-4-1106",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.29"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "gpt-4-1106"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-1106-preview",
   "model_name": "gpt-4-1106-preview",
   "display_name": "gpt-4-1106-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "gpt-4-1106-Preview"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-1106-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-1106-preview"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-03-26",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-11-06",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2023-04",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4-1106-Preview",
    "openai/gpt-4-1106-preview"
   ],
   "intro_i18n": {
    "zh-CN": "最新的 GPT-4 Turbo 模型支持视觉功能。视觉请求可以使用 JSON 模式和函数调用。GPT-4 Turbo 是增强版，平衡了准确性和效率，适用于具有成本效益的多模态任务和实时交互。",
    "zh-TW": "最新的 GPT-4 Turbo 模型包含視覺功能。視覺請求可使用 JSON 模式和函數調用。GPT-4 Turbo 是一個增強版，平衡了準確性和效率，適用於成本效益高的多模態任務和即時交互。",
    "ja-JP": "最新のGPT-4 Turboモデルにはビジョンが含まれています。ビジョンリクエストはJSONモードと関数呼び出しを使用できます。GPT-4 Turboは、コスト効率の高いマルチモーダルタスクとリアルタイムインタラクションのために、精度と効率のバランスを取った強化版です。",
    "ru-RU": "Последняя модель GPT-4 Turbo включает поддержку зрения. Запросы с использованием зрения могут использовать режим JSON и вызов функций. GPT-4 Turbo — это улучшенная версия, которая балансирует точность и эффективность для экономичных мультимодальных задач и взаимодействий в реальном времени."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-1106-vision-preview",
   "model_name": "gpt-4-1106-vision-preview",
   "display_name": "gpt-4-1106-vision-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4-1106-vision-preview"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-32k",
   "model_name": "gpt-4-32k",
   "display_name": "GPT-4 32K",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "205.32"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "410.67"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     },
     "provider_model_id": "openai/gpt-4-32k"
    }
   ],
   "intro": "GPT-4 is the latest and most advanced model in the GPT series, demonstrating sophisticated capabilities in complex reasoning, theory of mind, and narrative understanding.",
   "max_input_tokens": 32000,
   "capabilities": {
    "prompt_caching": true,
    "function_calling": true,
    "stream": true
   },
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "released_at": "2023-03-14",
   "knowledge_cutoff": "2023-11",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-4-32k"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4 提供更大的上下文窗口，适用于需要广泛信息整合与数据分析的场景。",
    "zh-TW": "GPT-4 提供更大的上下文視窗，能處理更長的輸入，適合需要廣泛資訊整合與資料分析的場景。",
    "ja-JP": "GPT-4 はより大きなコンテキストウィンドウを提供し、長文入力に対応。広範な情報統合やデータ分析に適しています。",
    "ru-RU": "GPT-4 предоставляет расширенное контекстное окно для обработки длинных входных данных, что делает его подходящим для интеграции информации и анализа данных в сложных сценариях."
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "completion",
     "old": "279.99",
     "new": "410.67"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "prompt",
     "old": "140.01",
     "new": "205.32"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4 32K"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-32k-0314",
   "model_name": "gpt-4-32k-0314",
   "display_name": "gpt-4-32k-0314",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    }
   ],
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4-32k-0314"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-32k-0613",
   "model_name": "gpt-4-32k-0613",
   "display_name": "GPT-4 32K 0613",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    }
   ],
   "capabilities": {
    "function_calling": true
   },
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "knowledge_cutoff": "2021-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GPT-4 提供更大的上下文窗口，适用于需要广泛信息整合与数据分析的场景。",
    "zh-TW": "GPT-4 提供更大的上下文視窗，能處理更長的輸入，適合需要廣泛資訊整合與資料分析的場景。",
    "ja-JP": "GPT-4 はより大きなコンテキストウィンドウを提供し、長文入力に対応。広範な情報統合やデータ分析に適しています。",
    "ru-RU": "GPT-4 предоставляет расширенное контекстное окно для обработки длинных входных данных, что делает его подходящим для интеграции информации и анализа данных в сложных сценариях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4 32K 0613"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-classic",
   "model_name": "gpt-4-classic",
   "display_name": "GPT-4-Classic",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "54"
      }
     },
     "provider_model_id": "openai/gpt-4-classic"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2024-03-25",
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-4-classic"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4-Classic"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-classic-0314",
   "model_name": "gpt-4-classic-0314",
   "display_name": "GPT-4-Classic-0314",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "54"
      }
     },
     "provider_model_id": "openai/gpt-4-classic-0314"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2024-08-26",
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-4-classic-0314"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4-Classic-0314"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-turbo",
   "model_name": "gpt-4-turbo",
   "display_name": "GPT-4 Turbo",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4-turbo-2024-04-09",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "gpt-4-turbo-2024-04-09"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.42"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "gpt-4-turbo-2024-04-09"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "gpt-4-turbo-2024-04-09"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-11-06",
   "knowledge_cutoff": "2023-12",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "deprecated": true,
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "benchmarks": {
    "intelligence_index": null,
    "coding_index": 21.5,
    "agentic_index": null
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4-turbo-2024-04-09",
    "openai/gpt-4-turbo",
    "openai/gpt-4-turbo-2024-04-09"
   ],
   "intro_i18n": {
    "zh-CN": "最新的 GPT-4 Turbo 增加了视觉能力。视觉请求支持 JSON 模式与函数调用。该模型在实时应用中兼顾准确性与效率，性价比高。",
    "zh-TW": "最新 GPT-4 Turbo 加入視覺功能。視覺請求支援 JSON 模式與函數呼叫。這是一款具成本效益的多模態模型，兼顧準確性與效率，適用於即時應用。",
    "ja-JP": "最新の GPT-4 Turbo は視覚機能を追加。ビジュアルリクエストは JSON モードと関数呼び出しに対応。リアルタイムアプリケーション向けに精度と効率のバランスを取ったコスト効率の高いマルチモーダルモデルです。",
    "ru-RU": "Последняя версия GPT-4 Turbo теперь поддерживает обработку изображений. Визуальные запросы поддерживают режим JSON и вызов функций. Это экономичный мультимодальный ИИ, сочетающий точность и эффективность для приложений в реальном времени."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-turbo-jp",
   "model_name": "gpt-4-turbo-jp",
   "display_name": "gpt-4-turbo-jp",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4-turbo-jp"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-turbo-preview",
   "model_name": "gpt-4-turbo-preview",
   "display_name": "gpt-4-turbo-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo-preview"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30.004999999999995"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-4-turbo-preview"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-01-25",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2023-12",
   "family": "gpt",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-4-turbo-preview"
   ],
   "intro_i18n": {
    "zh-CN": "最新的 GPT-4 Turbo 模型支持视觉功能。视觉请求可以使用 JSON 模式和函数调用。GPT-4 Turbo 是增强版，平衡了准确性和效率，适用于具有成本效益的多模态任务和实时交互。",
    "zh-TW": "最新的 GPT-4 Turbo 模型包含視覺功能。視覺請求可使用 JSON 模式和函數調用。GPT-4 Turbo 是一個增強版，平衡了準確性和效率，適用於成本效益高的多模態任務和即時交互。",
    "ja-JP": "最新のGPT-4 Turboモデルにはビジョンが含まれています。ビジョンリクエストはJSONモードと関数呼び出しを使用できます。GPT-4 Turboは、コスト効率の高いマルチモーダルタスクとリアルタイムインタラクションのために、精度と効率のバランスを取った強化版です。",
    "ru-RU": "Последняя модель GPT-4 Turbo включает поддержку зрения. Запросы с использованием зрения могут использовать режим JSON и вызов функций. GPT-4 Turbo — это улучшенная версия, которая балансирует точность и эффективность для экономичных мультимодальных задач и взаимодействий в реальном времени."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-turbo-vision",
   "model_name": "gpt-4-turbo-vision",
   "display_name": "GPT-4 Turbo Vision",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-11-06",
   "knowledge_cutoff": "2023-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4 Turbo Vision"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-turbo-vision-preview",
   "model_name": "gpt-4-turbo-vision-preview",
   "display_name": "gpt-4-turbo-vision-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4-turbo-vision-preview"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-vision",
   "model_name": "gpt-4-vision",
   "display_name": "gpt-4-vision",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.29"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "gpt-4-vision"
    }
   ]
  },
  {
   "slug": "openai/gpt-4-vision-preview",
   "model_name": "gpt-4-vision-preview",
   "display_name": "gpt-4-vision-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    }
   ],
   "intro": "GPT-4 Vision is a model that offers a balance between cost and performance.",
   "max_input_tokens": 128000,
   "capabilities": {
    "vision": true
   },
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GPT-4 Vision 预览版，专为图像分析与处理任务设计。",
    "zh-TW": "GPT-4 Vision 預覽版，專為圖像分析與處理任務設計。",
    "ja-JP": "GPT-4 Vision プレビューは、画像解析および処理タスク向けに設計されたモデルです。",
    "ru-RU": "Предварительная версия GPT-4 Vision, предназначенная для анализа и обработки изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4-vision-preview"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1-2025-04-14",
   "model_name": "gpt-4.1-2025-04-14",
   "display_name": "gpt-4.1-2025-04-14",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4.1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "1.75",
        "completion": "1.75",
        "cache_read": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-4.1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.8"
      }
     },
     "provider_model_id": "gpt-4.1",
     "region": "datazone_eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.8"
      }
     },
     "provider_model_id": "gpt-4.1",
     "region": "datazone_us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "gpt-4.1",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.354"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.417"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.49"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "github",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-4.1"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4.1",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75",
        "cache_read": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "openai/gpt-4.1"
    }
   ],
   "intro": "Long-lived GPT workhorse for coding, instruction following, and production apps",
   "released_at": "2025-04-14",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "deprecation_date": "2026-11-04",
   "deprecated": true,
   "aliases": [
    "azure/gpt-4.1",
    "azure/openai-responses/gpt-4.1",
    "gpt-4-1",
    "gpt-4.1",
    "openai-responses/gpt-4.1",
    "openai/gpt-4.1",
    "openai/gpt-4.1-2025-04-14"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4.1 是我们面向复杂任务与跨领域问题解决的旗舰模型。",
    "zh-TW": "GPT-4.1 是我們的旗艦模型，適用於複雜任務與跨領域問題解決。",
    "ja-JP": "GPT-4.1 は複雑なタスクや分野横断的な問題解決に対応するフラッグシップモデルです。",
    "ru-RU": "GPT-4.1 — наша флагманская модель для решения сложных задач и междисциплинарных проблем."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1-2025-04-14-text",
   "model_name": "gpt-4.1-2025-04-14-text",
   "display_name": "gpt-4.1-2025-04-14-text",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.8"
      }
     },
     "region": "datazone_us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4.1-2025-04-14-text"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1-2025-04-14.ft",
   "model_name": "gpt-4.1-2025-04-14.ft",
   "display_name": "gpt-4.1-2025-04-14.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4.1-2025-04-14.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1-mini-2025-04-14",
   "model_name": "gpt-4.1-mini-2025-04-14",
   "display_name": "gpt-4.1-mini-2025-04-14",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4.1-mini",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "1.75",
        "completion": "1.75",
        "cache_read": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-4.1-mini",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.44"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76"
      }
     },
     "provider_model_id": "gpt-4.1-mini",
     "region": "datazone_us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.53"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "github",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39999999999999997"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5999999999999999"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09999999999999999"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "gpt-4.1-mini"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75",
        "cache_read": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "openai/gpt-4.1-mini"
    }
   ],
   "intro": "Affordable GPT-4.1 lane for fast coding help and structured extraction",
   "released_at": "2025-04-14",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "deprecation_date": "2026-11-04",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 14.8,
    "coding_index": 20.2,
    "agentic_index": 1.7
   },
   "aliases": [
    "gpt-4-1-mini",
    "gpt-4.1-mini",
    "openai-responses/gpt-4.1-mini",
    "openai/gpt-4.1-mini",
    "openai/gpt-4.1-mini-2025-04-14"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4.1 mini 在智能、速度与成本之间实现平衡，适用于多种场景。",
    "zh-TW": "GPT-4.1 mini 在智慧、速度與成本之間取得平衡，適用於多種應用場景。",
    "ja-JP": "GPT-4.1 mini は知能、速度、コストのバランスが取れたモデルで、多様なユースケースに適しています。",
    "ru-RU": "GPT-4.1 mini сочетает интеллект, скорость и экономичность, что делает его привлекательным для множества сценариев использования."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1-mini-2025-04-14.ft",
   "model_name": "gpt-4.1-mini-2025-04-14.ft",
   "display_name": "gpt-4.1-mini-2025-04-14.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4.1-mini-2025-04-14.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1-mini.ft",
   "model_name": "gpt-4.1-mini.ft",
   "display_name": "gpt-4.1-mini.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4.1-mini.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1-mini@uksouth",
   "model_name": "gpt-4.1-mini@uksouth",
   "display_name": "azure/gpt-4.1-mini@uksouth",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "azure/gpt-4.1-mini@uksouth"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1-mini@uksouth"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1-mini@uksouth"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1-nano-2025-04-14",
   "model_name": "gpt-4.1-nano-2025-04-14",
   "display_name": "gpt-4.1-nano-2025-04-14",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4.1-nano",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-4.1-nano",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     },
     "provider_model_id": "gpt-4.1-nano",
     "region": "datazone_us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.545455",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "github",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09999999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39999999999999997"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.024999999999999998"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.095"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "azure/gpt-4.1-nano"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "gpt-4.1-nano"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/gpt-4.1-nano"
    }
   ],
   "intro": "Tiny GPT-4.1 option for classification, routing, and very high-volume tasks",
   "released_at": "2025-04-14",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-nano",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "deprecation_date": "2026-11-04",
   "benchmarks": {
    "intelligence_index": 9.6,
    "coding_index": 11.1,
    "agentic_index": 1.2
   },
   "aliases": [
    "azure/gpt-4.1-nano",
    "azure/openai-responses/gpt-4.1-nano",
    "gpt-4-1-nano",
    "gpt-4.1-nano",
    "openai-responses/gpt-4.1-nano",
    "openai/gpt-4.1-nano",
    "openai/gpt-4.1-nano-2025-04-14"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4.1 nano 是最快且最具性价比的 GPT-4.1 模型。",
    "zh-TW": "GPT-4.1 nano 是 GPT-4.1 系列中最快且最具成本效益的模型。",
    "ja-JP": "GPT-4.1 nano は GPT-4.1 モデルの中で最も高速かつコスト効率の高いモデルです。",
    "ru-RU": "GPT-4.1 nano — самая быстрая и экономичная модель в линейке GPT-4.1."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1-nano@uksouth",
   "model_name": "gpt-4.1-nano@uksouth",
   "display_name": "azure/gpt-4.1-nano@uksouth",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "azure/gpt-4.1-nano@uksouth"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1-nano@uksouth"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1-nano@uksouth"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1.ft",
   "model_name": "gpt-4.1.ft",
   "display_name": "gpt-4.1.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4.1.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.1@uksouth",
   "model_name": "gpt-4.1@uksouth",
   "display_name": "azure/gpt-4.1@uksouth",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "azure/gpt-4.1@uksouth"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1@uksouth"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1@uksouth"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.5",
   "model_name": "gpt-4.5",
   "display_name": "GPT-4.5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "37.5"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4.5"
    }
   ]
  },
  {
   "slug": "openai/gpt-4.5-preview-2025-02-27",
   "model_name": "gpt-4.5-preview-2025-02-27",
   "display_name": "GPT 4.5 Preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "37.5"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-4.5-preview"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "37.5"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-4.5-preview"
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "37.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      }
     },
     "provider_model_id": "gpt-4.5-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "37.5"
      }
     },
     "provider_model_id": "gpt-4.5-preview"
    }
   ],
   "intro": "GPT-4.5 (Preview) is a research preview of OpenAI's latest language model, designed to advance capabilities in reasoning, creativity, and multi-turn conversation. It builds on previous iterations with improvements in world knowledge, contextual coherence, and the ability to follow user intent more effectively.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "released_at": "2025-02-27",
   "knowledge_cutoff": "2023-10",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4.5-preview",
    "openai/gpt-4.5-preview"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4.5-preview 是最新的通用模型，具备更深的世界知识与更强的意图理解能力，擅长创意任务与智能体规划。知识截止时间为 2023 年 10 月。",
    "zh-TW": "GPT-4.5-preview 是最新的通用模型，具備深厚的世界知識與更佳的意圖理解能力，擅長創意任務與智能代理規劃。知識截止時間為 2023 年 10 月。",
    "ja-JP": "GPT-4.5-preview は最新の汎用モデルで、深い世界知識と意図理解を備え、創造的なタスクやエージェント計画に強みを持ちます。知識のカットオフは 2023年10月です。",
    "ru-RU": "GPT-4.5-preview — последняя универсальная модель с глубокими знаниями о мире и улучшенным пониманием намерений. Отлично справляется с творческими задачами и планированием агентов. Актуальность знаний — октябрь 2023 года."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT 4.5 Preview"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o",
   "model_name": "gpt-4o",
   "display_name": "GPT-4o",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-2024-05-13",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "1.7",
        "completion": "1.7",
        "cache_read": "1.7"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "gpt-4o-2024-11-20"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "gpt-4o-2024-05-13"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-2024-05-13",
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.38"
      }
     },
     "provider_model_id": "gpt-4o-2024-08-06",
     "region": "datazone_eu"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.38"
      }
     },
     "provider_model_id": "gpt-4o-2024-11-20",
     "region": "datazone_us"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-4o-2024-08-06",
     "region": "global"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.387"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.547"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.194"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-4o-2024-05-13"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.5"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.499"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.996"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "gpt-4o-2024-05-13"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.7",
        "completion": "1.7",
        "cache_read": "1.7"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "openai/gpt-4o"
    }
   ],
   "intro": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
   "released_at": "2024-05-13",
   "knowledge_cutoff": "2023-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "deprecation_date": "2026-02-27",
   "benchmarks": {
    "intelligence_index": null,
    "coding_index": 24.2,
    "agentic_index": null
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4o-2024-05-13",
    "gpt-4o-2024-08-06",
    "gpt-4o-2024-11-20",
    "gpt-4o:extended",
    "openai/gpt-4o",
    "openai/gpt-4o-2024-05-13",
    "openai/gpt-4o-2024-08-06",
    "openai/gpt-4o-2024-11-20",
    "openai/gpt-4o:extended"
   ],
   "intro_i18n": {
    "zh-CN": "ChatGPT-4o 是一款实时更新的动态模型，结合强大的理解与生成能力，适用于客户支持、教育与技术支持等大规模应用场景。",
    "zh-TW": "ChatGPT-4o 是一款即時更新的動態模型，結合強大的理解與生成能力，適用於客服、教育與技術支援等大規模應用場景。",
    "ja-JP": "ChatGPT-4o はリアルタイムで更新される動的モデルで、カスタマーサポート、教育、技術支援などの大規模ユースケースにおいて高い理解力と生成力を発揮します。",
    "ru-RU": "ChatGPT-4o — это динамическая модель с обновлением в реальном времени, сочетающая глубокое понимание и генерацию текста для масштабных сценариев, таких как поддержка клиентов, образование и техническая помощь."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "cache_write",
     "old": "0",
     "new": "1.38"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-2024-08-06-global",
   "model_name": "gpt-4o-2024-08-06-global",
   "display_name": "gpt-4o-2024-08-06-global",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-2024-08-06-global"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-2024-08-06.ft",
   "model_name": "gpt-4o-2024-08-06.ft",
   "display_name": "gpt-4o-2024-08-06.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.875"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-2024-08-06.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-audio",
   "model_name": "gpt-4o-audio",
   "display_name": "gpt-4o-audio",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "52.89"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "gpt-4o-audio"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-audio-mai",
   "model_name": "gpt-4o-audio-mai",
   "display_name": "gpt-4o-audio-mai",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "80"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "model_type": "omni",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "audio_input": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-audio-mai"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-audio-preview",
   "model_name": "gpt-4o-audio-preview",
   "display_name": "gpt-4o-audio-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "80"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-audio-preview-2024-12-17"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-4o-audio-preview-2025-06-03"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "80"
      },
      "cache_creation_input_audio": {
       "unit": "per_M_tokens",
       "price": "22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     },
     "provider_model_id": "gpt-4o-audio-preview-2024-12-17"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_creation_input_audio": {
       "unit": "per_M_tokens",
       "price": "22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "110"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "220"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "22"
      }
     },
     "provider_model_id": "gpt-4o-audio-preview-2024-10-01",
     "region": "datazone_eu"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o-audio-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "80"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o-audio-preview"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "omni",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "audio_input": true,
    "audio_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "intro": "Audio model for gpt-4o",
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "deprecated": true,
   "released_at": "2025-08-15",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "gpt-4o-audio-preview-2024-10-01",
    "gpt-4o-audio-preview-2024-12-17",
    "gpt-4o-audio-preview-2025-06-03",
    "openai/gpt-4o-audio-preview"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-aug",
   "model_name": "gpt-4o-aug",
   "display_name": "GPT-4o-Aug",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "openai/gpt-4o-aug"
    }
   ],
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2024-11-21",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-4o-aug"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4o-Aug"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-latest",
   "model_name": "gpt-4o-latest",
   "display_name": "gpt-4o-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.25",
        "completion": "0.333333"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.85",
        "completion": "1.133333",
        "cache_read": "1.7"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-latest"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini",
   "model_name": "gpt-4o-mini",
   "display_name": "GPT-4o mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "27.5"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-mini-2024-07-18",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "0.363636",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "0.363636",
        "file_search_call": "1",
        "prompt": "1.666667",
        "completion": "1.666667",
        "cache_read": "1.666667"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ],
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-4o-mini-2024-07-18"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-4o-mini-2024-07-18",
     "finetune_charges": {
      "train": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.083"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.165"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     },
     "provider_model_id": "gpt-4o-mini-2024-07-18",
     "region": "datazone_eu"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.083"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.165"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      }
     },
     "provider_model_id": "gpt-4o-mini-2024-07-18",
     "region": "datazone_us"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "gpt-4o-mini-2024-07-18",
     "region": "global"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.573"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.073"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1425"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1496"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.595"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.666667",
        "completion": "1.666667",
        "cache_read": "1.666667"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini"
    }
   ],
   "intro": "Small omni GPT for cheap multimodal assistance and production-scale traffic",
   "released_at": "2024-07-18",
   "knowledge_cutoff": "2023-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": null,
    "coding_index": 11.4,
    "agentic_index": 1
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4o-mini-2024-07-18",
    "openai/gpt-4o-mini",
    "openai/gpt-4o-mini-2024-07-18"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4o mini 是 OpenAI 在 GPT-4 Omni 之后推出的最新模型，支持文本+图像输入与文本输出。作为最先进的小型模型，其价格远低于前沿模型，比 GPT-3.5 Turbo 便宜 60% 以上，同时保持顶级智能水平（MMLU 达 82%）。",
    "zh-TW": "GPT-4o mini 是 OpenAI 在 GPT-4 Omni 之後推出的最新模型，支援文字+圖片輸入與文字輸出。作為最先進的小型模型，其價格遠低於最新前沿模型，比 GPT-3.5 Turbo 便宜超過 60%，同時保有頂尖智慧（82% MMLU）。",
    "ja-JP": "GPT-4o mini は GPT-4 Omni の後継となる最新モデルで、テキスト＋画像入力とテキスト出力に対応。最先端の小型モデルであり、最近の先端モデルより大幅に安価（GPT-3.5 Turbo の 60%以上安）ながら、トップクラスの知能（MMLU 82%）を維持しています。",
    "ru-RU": "GPT-4o mini — новейшая модель OpenAI после GPT-4 Omni, поддерживающая ввод текста и изображений с текстовым выводом. Это самая продвинутая компактная модель, значительно дешевле современных передовых моделей и более чем на 60% дешевле GPT-3.5 Turbo, при этом сохраняет высокий уровень интеллекта (82% MMLU)."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "openai",
     "charge": "web_search",
     "old": "10",
     "new": "27.5"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini-2024-07-18.ft",
   "model_name": "gpt-4o-mini-2024-07-18.ft",
   "display_name": "gpt-4o-mini-2024-07-18.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-mini-2024-07-18.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini-2024-07-18.ft-",
   "model_name": "gpt-4o-mini-2024-07-18.ft-",
   "display_name": "gpt-4o-mini-2024-07-18.ft-",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "intro": "GPT-4o Mini fine tuned.",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-mini-2024-07-18.ft-"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini-audio",
   "model_name": "gpt-4o-mini-audio",
   "display_name": "gpt-4o-mini-audio",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.59"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "gpt-4o-mini-audio"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini-audio-preview",
   "model_name": "gpt-4o-mini-audio-preview",
   "display_name": "gpt-4o-mini-audio-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-mini-audio-preview-2024-12-17"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "gpt-4o-mini-audio-preview-2024-12-17"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     },
     "provider_model_id": "gpt-4o-mini-audio-preview-2024-12-17"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "omni",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "audio_input": true,
    "audio_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "intro": "Audio model for gpt-4o mini",
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "gpt-4o-mini-audio-preview-2024-12-17"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "audio_input",
     "old": "20",
     "new": "40"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "audio_output",
     "old": "10",
     "new": "80"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "completion",
     "old": "0.6",
     "new": "10"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "prompt",
     "old": "15",
     "new": "2.5"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini-global",
   "model_name": "gpt-4o-mini-global",
   "display_name": "gpt-4o-mini-global",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-mini-global"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini-realtime",
   "model_name": "gpt-4o-mini-realtime",
   "display_name": "gpt-4o-mini-realtime",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.02"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "realtime_omni",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "cache_read",
     "old": "0.69",
     "new": "1.02"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "completion",
     "old": "5.61",
     "new": "8.22"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "prompt",
     "old": "1.41",
     "new": "2.04"
    },
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "gpt-4o-mini-realtime"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini-realtime-preview",
   "model_name": "gpt-4o-mini-realtime-preview",
   "display_name": "gpt-4o-mini-realtime-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-mini-realtime-preview-2024-12-17"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "11"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "22"
      },
      "cache_creation_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "gpt-4o-mini-realtime-preview-2024-12-17"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_creation_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "gpt-4o-mini-realtime-preview-2024-12-17",
     "region": "global"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "realtime_omni",
   "capabilities": {
    "function_calling": true,
    "audio_input": true,
    "audio_output": true,
    "parallel_function_calling": true
   },
   "released_at": "2024-12-17",
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4o-mini-realtime-preview-2024-12-17"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4o-mini 实时变体，支持音频与文本的实时输入输出。",
    "zh-TW": "GPT-4o-mini 即時變體，支援音訊與文字的即時輸入/輸出。",
    "ja-JP": "GPT-4o-mini リアルタイムバリアントは、音声とテキストのリアルタイム入出力に対応しています。",
    "ru-RU": "Вариант GPT-4o-mini с поддержкой аудио и текста в режиме реального времени."
   }
  },
  {
   "slug": "openai/gpt-4o-mini-search",
   "model_name": "gpt-4o-mini-search",
   "display_name": "GPT-4o-mini-Search",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.54"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini-search"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-03-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-4o-mini-search"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4o-mini-Search"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini-search-preview",
   "model_name": "gpt-4o-mini-search-preview",
   "display_name": "gpt-4o-mini-search-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "27.5"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-mini-search-preview-2025-03-11"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "gpt-4o-mini-search-preview-2025-03-11"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini-search-preview"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini-search-preview"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini-search-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "27.5"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini-search-preview"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini-search-preview"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini-search-preview"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-03-11",
   "knowledge_cutoff": "2023-10",
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "family": "gpt-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4o-mini-search-preview-2025-03-11",
    "openai/gpt-4o-mini-search-preview",
    "openai/gpt-4o-mini-search-preview-2025-03-11"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4o mini 搜索预览版，训练用于理解并执行网页搜索请求，通过 Chat Completions API 实现。网页搜索按工具调用计费，另加 token 成本。",
    "zh-TW": "GPT-4o mini 搜尋預覽模型，透過 Chat Completions API 訓練以理解並執行網頁搜尋查詢。網頁搜尋按工具呼叫次數額外計費。",
    "ja-JP": "GPT-4o mini Search Preview は、Chat Completions API を通じてウェブ検索クエリの理解と実行に特化して訓練されたモデルです。ウェブ検索はツール呼び出しごとに課金され、トークンコストとは別に請求されます。",
    "ru-RU": "Предварительная версия GPT-4o mini Search обучена понимать и выполнять веб-поисковые запросы через API Chat Completions. Поиск в интернете тарифицируется отдельно за каждый вызов инструмента, помимо стоимости токенов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini-transcribe",
   "model_name": "gpt-4o-mini-transcribe",
   "display_name": "gpt-4o-mini-transcribe",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-mini-transcribe-2025-03-20"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.29"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-4o-mini-transcribe-2025-03-20"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini-transcribe"
    }
   ],
   "max_input_tokens": 16000,
   "max_output_tokens": 2000,
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "audio",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-03-15",
   "knowledge_cutoff": "2024-06",
   "intro": "Speech transcription model for accurate audio-to-text and captioning workflows",
   "family": "o-mini",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4o-mini-transcribe-2025-03-20",
    "gpt-4o-mini-transcribe-2025-12-15",
    "openai/gpt-4o-mini-transcribe"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4o Mini 转录模型是一款语音转文本模型，使用 GPT-4o 进行音频转录，在词错误率、语言识别与准确性方面优于原始 Whisper 模型。",
    "zh-TW": "GPT-4o Mini Transcribe 是一款語音轉文字模型，使用 GPT-4o 進行音訊轉錄，提升詞錯率、語言識別與準確性，優於原始 Whisper 模型。",
    "ja-JP": "GPT-4o Mini Transcribe は音声をテキストに変換するモデルで、元の Whisper モデルよりも単語誤認率、言語識別、精度が向上しています。",
    "ru-RU": "GPT-4o Mini Transcribe — это модель преобразования речи в текст, которая транскрибирует аудио с помощью GPT-4o, улучшая точность распознавания слов, определение языка и общую точность по сравнению с оригинальной моделью Whisper."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini-tts",
   "model_name": "gpt-4o-mini-tts",
   "display_name": "GPT-4o Mini TTS",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-mini-tts-2025-03-20"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "31.74"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-4o-mini-tts-2025-03-20"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     },
     "provider_model_id": "openai/gpt-4o-mini-tts"
    }
   ],
   "capabilities": {
    "audio_output": true,
    "pdf_input": true,
    "audio_input": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "deprecated": true,
   "released_at": "2025-03-19",
   "max_input_tokens": 2000,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4o-mini-tts-2025-03-20",
    "gpt-4o-mini-tts-2025-12-15",
    "openai/gpt-4o-mini-tts",
    "openai/gpt-4o-mini-tts-2025-03-20",
    "openai/gpt-4o-mini-tts-2025-12-15"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4o mini TTS 是一款基于 GPT-4o mini 的文本转语音模型，可将文本转换为自然语音，最大输入为 2000 个 token。",
    "zh-TW": "GPT-4o mini TTS 是一款基於 GPT-4o mini 的文字轉語音模型，將文字轉換為自然語音，最多支援 2000 個 token 輸入。",
    "ja-JP": "GPT-4o mini TTS は GPT-4o mini をベースにしたテキスト読み上げモデルで、最大 2000 トークンのテキストを自然な音声に変換します。",
    "ru-RU": "GPT-4o mini TTS — это модель преобразования текста в речь, основанная на GPT-4o mini, преобразующая текст в естественно звучащую речь с максимальным входом до 2000 токенов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4o Mini TTS"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini.ft",
   "model_name": "gpt-4o-mini.ft",
   "display_name": "gpt-4o-mini.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-mini.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini@eastus2",
   "model_name": "gpt-4o-mini@eastus2",
   "display_name": "azure/gpt-4o-mini@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "azure/gpt-4o-mini@eastus2"
    }
   ],
   "released_at": "2025-07-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4o-mini@eastus2"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4o-mini@eastus2"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-mini@swedencentral",
   "model_name": "gpt-4o-mini@swedencentral",
   "display_name": "azure/gpt-4o-mini@swedencentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "azure/gpt-4o-mini@swedencentral"
    }
   ],
   "released_at": "2025-07-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4o-mini@swedencentral"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4o-mini@swedencentral"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-realtime",
   "model_name": "gpt-4o-realtime",
   "display_name": "GPT-4o Realtime",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "17.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "68.43"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "8.55"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "released_at": "2026-07-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "realtime_omni",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "cache_read",
     "old": "5.82",
     "new": "8.55"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "completion",
     "old": "46.68",
     "new": "68.43"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "prompt",
     "old": "11.67",
     "new": "17.1"
    },
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4o Realtime"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-realtime-preview",
   "model_name": "gpt-4o-realtime-preview",
   "display_name": "gpt-4o-realtime-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "80"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-realtime-preview-2024-12-17"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "110"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "220"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-realtime-preview-2024-10-01"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "realtime_omni",
   "capabilities": {
    "function_calling": true,
    "audio_input": true,
    "audio_output": true,
    "parallel_function_calling": true
   },
   "released_at": "2024-12-17",
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4o-realtime-preview-2024-10-01",
    "gpt-4o-realtime-preview-2024-12-17",
    "gpt-4o-realtime-preview-2025-06-03"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4o 实时变体，支持音频与文本的实时输入输出。",
    "zh-TW": "GPT-4o 即時變體，支援音訊與文字的即時輸入/輸出。",
    "ja-JP": "GPT-4o リアルタイムバリアントは、音声とテキストのリアルタイム入出力に対応しています。",
    "ru-RU": "Вариант GPT-4o с поддержкой аудио и текста в режиме реального времени."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "audio_input",
     "old": "40",
     "new": "110"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "audio_output",
     "old": "80",
     "new": "220"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "cache_read",
     "old": "2.5",
     "new": "2.75"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "completion",
     "old": "20",
     "new": "22"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "prompt",
     "old": "5",
     "new": "5.5"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-search",
   "model_name": "gpt-4o-search",
   "display_name": "GPT-4o-Search",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.52"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "22.08"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "openai/gpt-4o-search"
    }
   ],
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2025-03-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-4o-search"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4o-Search"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-search-preview",
   "model_name": "gpt-4o-search-preview",
   "display_name": "gpt-4o-search-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-search-preview-2025-03-11"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-4o-search-preview-2025-03-11"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o-search-preview"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o-search-preview"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.88"
      }
     },
     "provider_model_id": "openai/gpt-4o-search-preview"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "35"
      }
     },
     "provider_model_id": "openai/gpt-4o-search-preview"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o-search-preview"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "intro": "GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.",
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-03-11",
   "knowledge_cutoff": "2023-10",
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4o-search-preview-2025-03-11",
    "openai/gpt-4o-search-preview",
    "openai/gpt-4o-search-preview-2025-03-11"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4o 搜索预览版，训练用于理解并执行网页搜索请求，通过 Chat Completions API 实现。网页搜索按工具调用计费，另加 token 成本。",
    "zh-TW": "GPT-4o 搜尋預覽模型，透過 Chat Completions API 訓練以理解並執行網頁搜尋查詢。網頁搜尋按工具呼叫次數額外計費。",
    "ja-JP": "GPT-4o Search Preview は、Chat Completions API を通じてウェブ検索クエリの理解と実行に特化して訓練されたモデルです。ウェブ検索はツール呼び出しごとに課金され、トークンコストとは別に請求されます。",
    "ru-RU": "Предварительная версия GPT-4o Search обучена понимать и выполнять веб-поисковые запросы через API Chat Completions. Поиск в интернете тарифицируется отдельно за каждый вызов инструмента, помимо стоимости токенов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-transcribe",
   "model_name": "gpt-4o-transcribe",
   "display_name": "gpt-4o-transcribe",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.13"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-4o-transcribe-2025-03-20"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-4o-transcribe"
    }
   ],
   "max_input_tokens": 16000,
   "max_output_tokens": 2000,
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "audio",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-03-15",
   "knowledge_cutoff": "2024-06",
   "intro": "Speech transcription model for accurate audio-to-text and captioning workflows",
   "family": "gpt",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4o-transcribe-2025-03-20",
    "openai/gpt-4o-transcribe"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-4o 转录模型是一款语音转文本模型，使用 GPT-4o 进行音频转录，在词错误率、语言识别与准确性方面优于原始 Whisper 模型。",
    "zh-TW": "GPT-4o Transcribe 是一款語音轉文字模型，使用 GPT-4o 進行音訊轉錄，提升詞錯率、語言識別與準確性，優於原始 Whisper 模型。",
    "ja-JP": "GPT-4o Transcribe は音声をテキストに変換するモデルで、元の Whisper モデルよりも単語誤認率、言語識別、精度が向上しています。",
    "ru-RU": "GPT-4o Transcribe — это модель преобразования речи в текст, которая транскрибирует аудио с помощью GPT-4o, улучшая точность распознавания слов, определение языка и общую точность по сравнению с оригинальной моделью Whisper."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-transcribe-diarize",
   "model_name": "gpt-4o-transcribe-diarize",
   "display_name": "gpt-4o-transcribe-diarize",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "26.43"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-4o-transcribe-diarize-2025-10-15"
    }
   ],
   "max_input_tokens": 16000,
   "max_output_tokens": 2000,
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "audio",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-06-24",
   "knowledge_cutoff": "2024-06",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-4o-transcribe-diarize-2025-10-15"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o-zh",
   "model_name": "gpt-4o-zh",
   "display_name": "gpt-4o-zh",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-zh"
    }
   ]
  },
  {
   "slug": "openai/gpt-4o.ft",
   "model_name": "gpt-4o.ft",
   "display_name": "gpt-4o.ft",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.875"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o.ft"
    }
   ]
  },
  {
   "slug": "openai/gpt-5",
   "model_name": "gpt-5",
   "display_name": "GPT-5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5-2025-08-07",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.13"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5-2025-08-07"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1375"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     },
     "provider_model_id": "gpt-5-2025-08-07",
     "region": "datazone_eu"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1375"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     },
     "provider_model_id": "gpt-5-2025-08-07",
     "region": "datazone_us"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.234"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.838"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12500000000000003"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.5"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5-2025-08-07"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5"
    }
   ],
   "intro": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 34.7,
    "coding_index": 37.8,
    "agentic_index": 25.7
   },
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "azure/gpt-5",
    "gpt-5-2025-08-07",
    "openai-responses/gpt-5",
    "openai/gpt-5",
    "openai/gpt-5-2025-08-07",
    "pa/gpt-5",
    "pa/gpt-5-2025-08-07"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5 —— 旗舰模型，具备先进推理与多模态能力。",
    "zh-TW": "OpenAI GPT-5 —— 旗艦模型，具備先進推理與多模態輸入能力。",
    "ja-JP": "GPT-5 by OpenAI — 高度な推論とマルチモーダル入力を備えたフラッグシップモデル。",
    "ru-RU": "GPT-5 от OpenAI — флагманская модель с продвинутыми возможностями рассуждения и мультимодальным вводом."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-chat",
   "model_name": "gpt-5-chat",
   "display_name": "gpt-5-chat",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "26.43"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "gpt-5-chat-2025-08-07"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5-chat"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+truefoundry+openrouter+helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-chat"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "openai/gpt-5-chat"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5-chat"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-chat"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-chat"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "image_output": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-09",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "docs_url": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/",
   "deprecated": true,
   "aliases": [
    "gpt-5-chat-2025-08-07",
    "gpt-5-chat-2025-08-15",
    "gpt-5-chat-2025-10-03",
    "openai/gpt-5-chat"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5 Chat 是一款预览模型，专为对话场景优化。支持文本与图像输入，仅输出文本，适用于聊天机器人与对话式 AI 应用。",
    "zh-TW": "GPT-5 Chat 是一款預覽模型，針對對話場景進行最佳化。支援文字與圖片輸入，僅輸出文字，適用於聊天機器人與對話式 AI 應用。",
    "ja-JP": "GPT-5 Chat は会話シナリオに最適化されたプレビューモデルで、テキストと画像の入力に対応し、テキスト出力を行います。チャットボットや会話型 AI アプリケーションに適しています。",
    "ru-RU": "GPT-5 Chat — предварительная модель, оптимизированная для разговорных сценариев. Поддерживает ввод текста и изображений, выводит только текст и подходит для чат-ботов и разговорного ИИ."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "cache_read",
     "old": "0.12",
     "new": "0.33"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "completion",
     "old": "8.88",
     "new": "26.43"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "prompt",
     "old": "1.11",
     "new": "3.3"
    },
    {
     "date": "2026-07-03",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-chat-latest",
   "model_name": "gpt-5-chat-latest",
   "display_name": "GPT-5 Chat",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12500000000000003"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5-chat-latest"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5-chat-latest"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5-chat-latest"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "deprecated": true,
   "parameters": {
    "supported": [
     "max_completion_tokens",
     "response_format",
     "seed",
     "stop",
     "tool_choice",
     "tools",
     "verbosity"
    ],
    "unsupported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "n",
     "presence_penalty",
     "temperature",
     "top_logprobs",
     "top_p"
    ]
   },
   "aliases": [
    "openai/gpt-5-chat-latest",
    "pa/gpt-5-chat-latest"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5 模型用于 ChatGPT，结合强大的理解与生成能力，适用于对话类应用。",
    "zh-TW": "GPT-5 模型應用於 ChatGPT，結合強大的理解與生成能力，適用於對話應用。",
    "ja-JP": "ChatGPT に使用される GPT-5 モデルで、会話アプリケーション向けに高い理解力と生成力を兼ね備えています。",
    "ru-RU": "Модель GPT-5, используемая в ChatGPT, сочетает в себе мощное понимание и генерацию для разговорных приложений."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-codex",
   "model_name": "gpt-5-codex",
   "display_name": "GPT-5-Codex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.13"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5-codex-2025-09-15"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12500000000000003"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5-codex"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5-codex"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.992"
      }
     },
     "provider_model_id": "openai/gpt-5-codex"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-codex"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5-codex"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "openai/gpt-5-codex"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5-codex"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-codex",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-codex"
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2025-09-15",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "gpt-5-codex-2025-09-15",
    "openai-responses/gpt-5-codex",
    "openai/gpt-5-codex",
    "pa/gpt-5-codex"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5 Codex —— 具备工具调用支持的代码专项模型。",
    "zh-TW": "OpenAI GPT-5 Codex —— 專為程式設計優化，並支援工具使用。",
    "ja-JP": "GPT-5 Codex by OpenAI — ツール使用をサポートするコーディング特化型バリアント。",
    "ru-RU": "GPT-5 Codex от OpenAI — специализированная модель для программирования с поддержкой инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-image",
   "model_name": "gpt-5-image",
   "display_name": "GPT-5 Image",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-5-image"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-image"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-5-image"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-image"
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-10-14",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "gpt",
   "model_type": "image_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5-image"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5 Image"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-image-mini",
   "model_name": "gpt-5-image-mini",
   "display_name": "OpenAI: GPT-5 Image Mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5-image-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-image-mini"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "openai/gpt-5-image-mini"
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-10-16",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "pdf",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "family": "gpt",
   "model_type": "image_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5-image-mini"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI: GPT-5 Image Mini"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-mini",
   "model_name": "gpt-5-mini",
   "display_name": "GPT-5 Mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5-mini-2025-08-07",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5-mini-2025-08-07"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0275"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "gpt-5-mini-2025-08-07",
     "region": "datazone_eu"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0275"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "gpt-5-mini-2025-08-07",
     "region": "datazone_us"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "gpt-5-mini-2025-08-07",
     "region": "global"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.968"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.024999999999999998"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5-mini"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.225"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5-mini-2025-08-07"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "qihang-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-mini",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.8",
        "completion": "1.8",
        "cache_read": "1.8"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-mini"
    }
   ],
   "intro": "Small GPT-5 for responsive agents, coding help, and everyday automation",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 25.3,
    "coding_index": 15.6,
    "agentic_index": 19.4
   },
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "azure/gpt-5-mini",
    "gpt-5-mini-2025-08-07",
    "openai-responses/gpt-5-mini",
    "openai/gpt-5-mini",
    "openai/gpt-5-mini-2025-08-07",
    "pa/gpt-5-mini",
    "pa/gpt-5-mini-2025-08-07"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5 的快速、低成本变体，适用于定义明确的任务，在保持质量的同时提供更快响应。",
    "zh-TW": "GPT-5 的快速且具成本效益的變體，適用於明確任務，回應更快且維持品質。",
    "ja-JP": "明確に定義されたタスク向けに高速かつコスト効率の高い GPT-5 バリアントで、品質を維持しながら迅速な応答を提供します。",
    "ru-RU": "Быстрый и экономичный вариант GPT-5 для четко определенных задач, обеспечивающий быстрые ответы при сохранении качества."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-mini-2025-08-07-lite",
   "model_name": "gpt-5-mini-2025-08-07-lite",
   "display_name": "gpt-5-mini-2025-08-07-lite",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0275"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "region": "datazone_eu"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0275"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "region": "datazone_us"
    }
   ],
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5-mini-2025-08-07-lite"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-mini:flex",
   "model_name": "gpt-5-mini:flex",
   "display_name": "openai/gpt-5-mini:flex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0125"
      }
     },
     "provider_model_id": "openai/gpt-5-mini:flex"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5-mini:flex"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/gpt-5-mini:flex"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-mini:priority",
   "model_name": "gpt-5-mini:priority",
   "display_name": "openai/gpt-5-mini:priority",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.045"
      }
     },
     "provider_model_id": "openai/gpt-5-mini:priority"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5-mini:priority"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/gpt-5-mini:priority"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-mini@eastus2",
   "model_name": "gpt-5-mini@eastus2",
   "display_name": "azure/gpt-5-mini@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "azure/gpt-5-mini@eastus2"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5-mini@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5-mini@eastus2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-mini@francecentral",
   "model_name": "gpt-5-mini@francecentral",
   "display_name": "azure/gpt-5-mini@francecentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "azure/gpt-5-mini@francecentral"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5-mini@francecentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5-mini@francecentral"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-mini@swedencentral",
   "model_name": "gpt-5-mini@swedencentral",
   "display_name": "azure/gpt-5-mini@swedencentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "azure/gpt-5-mini@swedencentral"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5-mini@swedencentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5-mini@swedencentral"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-mini@uksouth",
   "model_name": "gpt-5-mini@uksouth",
   "display_name": "azure/gpt-5-mini@uksouth",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "azure/gpt-5-mini@uksouth"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5-mini@uksouth"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5-mini@uksouth"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-nano",
   "model_name": "gpt-5-nano",
   "display_name": "GPT-5 Nano",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5-nano-2025-08-07",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5-nano-2025-08-07"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0055"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.055"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     },
     "provider_model_id": "gpt-5-nano-2025-08-07",
     "region": "datazone_eu"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0055"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.055"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     },
     "provider_model_id": "gpt-5-nano-2025-08-07",
     "region": "datazone_us"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "global"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.054"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.394"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.017"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.049999999999999996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39999999999999997"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5-nano"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.045"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5-nano-2025-08-07"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.045"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0045"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-nano",
     "tracks": [
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-nano"
    }
   ],
   "intro": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-nano",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "azure/gpt-5-nano",
    "gpt-5-nano-2025-08-07",
    "openai-responses/gpt-5-nano",
    "openai/gpt-5-nano",
    "openai/gpt-5-nano-2025-08-07",
    "pa/gpt-5-nano",
    "pa/gpt-5-nano-2025-08-07"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5 Nano —— 轻量级高性价比模型。",
    "zh-TW": "OpenAI GPT-5 Nano —— 輕量、省成本模型。",
    "ja-JP": "GPT-5 Nano by OpenAI — 軽量でコスト効率の良いモデル。",
    "ru-RU": "GPT-5 Nano от OpenAI — лёгкая и экономичная модель."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-nano:flex",
   "model_name": "gpt-5-nano:flex",
   "display_name": "openai/gpt-5-nano:flex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "openai/gpt-5-nano:flex"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5-nano:flex"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/gpt-5-nano:flex"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-nano@eastus2",
   "model_name": "gpt-5-nano@eastus2",
   "display_name": "azure/gpt-5-nano@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "azure/gpt-5-nano@eastus2"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5-nano@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5-nano@eastus2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-nano@francecentral",
   "model_name": "gpt-5-nano@francecentral",
   "display_name": "azure/gpt-5-nano@francecentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "azure/gpt-5-nano@francecentral"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5-nano@francecentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5-nano@francecentral"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-nano@swedencentral",
   "model_name": "gpt-5-nano@swedencentral",
   "display_name": "azure/gpt-5-nano@swedencentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "azure/gpt-5-nano@swedencentral"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5-nano@swedencentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5-nano@swedencentral"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-pro",
   "model_name": "gpt-5-pro",
   "display_name": "GPT-5 Pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5-pro-2025-10-06",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5-pro-2025-10-06"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5-pro"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "108"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     },
     "provider_model_id": "openai/gpt-5-pro"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     },
     "provider_model_id": "openai/gpt-5-pro"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5-pro-2025-10-01"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-pro"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     },
     "provider_model_id": "openai/gpt-5-pro"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "110"
      }
     },
     "provider_model_id": "openai/gpt-5-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     },
     "provider_model_id": "openai/gpt-5-pro"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-pro"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-pro"
    }
   ],
   "intro": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning",
   "released_at": "2025-10-06",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 272000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-pro",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "deprecated": true,
   "docs_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5",
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "gpt-5-pro-2025-10-01",
    "gpt-5-pro-2025-10-06",
    "openai-responses/gpt-5-pro",
    "openai/gpt-5-pro",
    "openai/gpt-5-pro-2025-10-01",
    "openai/gpt-5-pro-2025-10-06",
    "pa/gpt-5-pro",
    "pa/gpt-5-pro-2025-10-01"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5 Pro 使用更多计算资源以实现更深入的思考，持续提供更优质的答案。",
    "zh-TW": "GPT-5 Pro 使用更多運算資源以進行更深入思考，穩定提供更優質的答案。",
    "ja-JP": "GPT-5 Pro はより多くの計算資源を使用して深く思考し、常に優れた回答を提供するモデルです。",
    "ru-RU": "GPT-5 Pro использует больше вычислительных ресурсов для более глубокого анализа и стабильно выдает более качественные ответы."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-search-api",
   "model_name": "gpt-5-search-api",
   "display_name": "gpt-5-search-api",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5-search-api-2025-10-14",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5-search-api-2025-10-14"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5-search-api"
    }
   ],
   "max_input_tokens": 272000,
   "max_output_tokens": 128000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-5-search-api-2025-10-14",
    "openai/gpt-5-search-api",
    "openai/gpt-5-search-api-2025-10-14"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-5-thinking",
   "model_name": "gpt-5-thinking",
   "display_name": "gpt-5-thinking",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2025-08-08",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5-thinking"
    }
   ]
  },
  {
   "slug": "openai/gpt-5:flex",
   "model_name": "gpt-5:flex",
   "display_name": "openai/gpt-5:flex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0625"
      }
     },
     "provider_model_id": "openai/gpt-5:flex"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5:flex"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/gpt-5:flex"
    }
   ]
  },
  {
   "slug": "openai/gpt-5:priority",
   "model_name": "gpt-5:priority",
   "display_name": "openai/gpt-5:priority",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5:priority"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5:priority"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/gpt-5:priority"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1-2025-11-13",
   "model_name": "gpt-5.1-2025-11-13",
   "display_name": "gpt-5.1-2025-11-13",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5.1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.13"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     },
     "provider_model_id": "gpt-5.1",
     "region": "datazone_eu"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     },
     "provider_model_id": "gpt-5.1",
     "region": "datazone_us"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-5.1",
     "region": "global"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.234"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.838"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12500000000000003"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gpt-5-1"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5.1-2025-11-13"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gpt-5.1"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1"
    }
   ],
   "intro": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
   "released_at": "2025-11-13",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "benchmarks": {
    "intelligence_index": 36.9,
    "coding_index": 49.4,
    "agentic_index": 21
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "azure/gpt-5.1",
    "gpt-5-1",
    "gpt-5.1",
    "openai-responses/gpt-5.1",
    "openai/gpt-5.1",
    "openai/gpt-5.1-2025-11-13",
    "pa/gpt-5.1-2025-11-13"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.1 —— 推理准确度进一步提升的改进版 GPT-5。",
    "zh-TW": "OpenAI GPT-5.1 —— 在推理準確性上進一步提升。",
    "ja-JP": "GPT-5.1 by OpenAI — 推論精度が向上した改良版GPT-5。",
    "ru-RU": "GPT-5.1 от OpenAI — улучшенная версия GPT-5 с повышенной точностью рассуждений."
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "fastrouter",
     "charge": "cache_read",
     "old": "0.125",
     "new": "0.13"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "fastrouter",
     "charge": "cache_read",
     "old": "0.13",
     "new": "0.125"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "fastrouter",
     "charge": "cache_read",
     "old": "0.125",
     "new": "0.13"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "audio_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "limit",
     "old": "272000",
     "new": "400000",
     "note": "max_input_tokens"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "helicone",
     "charge": "cache_read",
     "old": "0.125",
     "new": "0.12500000000000003"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "openrouter",
     "charge": "completion",
     "old": "10.55",
     "new": "10"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "1.32",
     "new": "1.25"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1-chat-2025-11-13",
   "model_name": "gpt-5.1-chat-2025-11-13",
   "display_name": "GPT-5.1 Chat",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.13"
      }
     },
     "provider_model_id": "gpt-5.1-chat"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gpt-5.1-chat"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     },
     "provider_model_id": "gpt-5.1-chat",
     "region": "datazone_eu"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     },
     "provider_model_id": "gpt-5.1-chat",
     "region": "datazone_us"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-5.1-chat",
     "region": "global"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gpt-5.1-chat"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1-chat"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-chat"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1-chat"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-chat"
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2025-11-13",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-5.1-chat",
    "openai/gpt-5.1-chat"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5.1 Chat 是 GPT-5.1 系列中轻量级成员，优化用于低延迟对话，同时保持强大的推理和指令执行能力。",
    "zh-TW": "GPT-5.1 Chat 是 GPT-5.1 系列中輕量級成員，針對低延遲對話優化，同時保有強大的推理與指令執行能力。",
    "ja-JP": "GPT-5.1 ChatはGPT-5.1ファミリーの軽量版で、低遅延な会話に最適化されつつ、強力な推論力と指示実行能力を保持しています。",
    "ru-RU": "GPT-5.1 Chat — легковесный представитель семейства GPT-5.1, оптимизированный для диалогов с низкой задержкой при сохранении сильных навыков рассуждения и выполнения инструкций."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.1 Chat"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1-chat-latest",
   "model_name": "gpt-5.1-chat-latest",
   "display_name": "GPT-5.1 Chat",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-5-1-chat-latest"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12500000000000003"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.5"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1-chat-latest"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1-chat-latest"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations",
   "released_at": "2025-11-13",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "deprecated": true,
   "aliases": [
    "gpt-5-1-chat-latest",
    "openai/gpt-5.1-chat-latest"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5.1 Chat：GPT-5.1 的 ChatGPT 变体，专为对话场景打造。",
    "zh-TW": "GPT-5.1 Chat：GPT-5.1 的 ChatGPT 變體，專為對話場景打造。",
    "ja-JP": "GPT-5.1 Chat：GPT-5.1 のチャット向けバリアントで、会話シナリオに最適化されています。",
    "ru-RU": "GPT-5.1 Chat: вариант GPT-5.1, предназначенный для сценариев общения."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1-codex",
   "model_name": "gpt-5.1-codex",
   "display_name": "GPT-5.1 Codex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.1-codex-2025-11-13"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     },
     "provider_model_id": "gpt-5.1-codex-2025-11-13",
     "region": "datazone_eu"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     },
     "provider_model_id": "gpt-5.1-codex-2025-11-13",
     "region": "datazone_us"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-5.1-codex-2025-11-13",
     "region": "global"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12500000000000003"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.107"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex"
    }
   ],
   "intro": "Codex GPT for repository edits, code review, and practical software agents",
   "released_at": "2025-11-13",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "gpt-5.1-codex-2025-11-13",
    "openai-responses/gpt-5.1-codex",
    "openai/gpt-5.1-codex"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.1 Codex —— 加强工具调用的代码专项模型。",
    "zh-TW": "OpenAI GPT-5.1 Codex —— 以程式能力為重點並增強工具使用。",
    "ja-JP": "GPT-5.1 Codex by OpenAI — ツール使用が強化されたコーディング特化型バリアント。",
    "ru-RU": "GPT-5.1 Codex от OpenAI — модель, ориентированная на программирование, с расширенной поддержкой инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1-codex-max",
   "model_name": "gpt-5.1-codex-max",
   "display_name": "GPT-5.1 Codex Max",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gpt-5.1-codex-max-2025-12-04"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-max"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-max"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gpt-5-1-codex-max"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-max"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-max"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-max"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-max"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-max"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-max",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2025-11-13",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "deprecated": true,
   "docs_url": "https://openrouter.ai/openai/gpt-5.1-codex-max",
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "gpt-5-1-codex-max",
    "gpt-5.1-codex-max-2025-12-04",
    "openai/gpt-5.1-codex-max"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.1 Codex Max —— 最高性能的 Codex 变体。",
    "zh-TW": "OpenAI GPT-5.1 Codex Max —— Codex 系列最高能力版本。",
    "ja-JP": "GPT-5.1 Codex Max by OpenAI — 最大能力のCodexバリアント。",
    "ru-RU": "GPT-5.1 Codex Max от OpenAI — максимально мощная версия Codex."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1-codex-mini",
   "model_name": "gpt-5.1-codex-mini",
   "display_name": "GPT-5.1 Codex mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.42"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.1-codex-mini-2025-11-13"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "gpt-5.1-codex-mini-2025-11-13",
     "region": "datazone_eu"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "gpt-5.1-codex-mini-2025-11-13",
     "region": "datazone_us"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "gpt-5.1-codex-mini-2025-11-13",
     "region": "global"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.024999999999999998"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.225"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-mini"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-mini"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "gpt-5-1-codex-mini"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-mini"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-mini"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-mini"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-mini"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-mini"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-mini"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-codex-mini"
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2025-11-13",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "gpt-5-1-codex-mini",
    "gpt-5.1-codex-mini-2025-11-13",
    "openai/gpt-5.1-codex-mini"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.1 Codex Mini —— 小型但强大的编码模型。",
    "zh-TW": "OpenAI GPT-5.1 Codex Mini —— 輕量型程式模型，能力依然強大。",
    "ja-JP": "GPT-5.1 Codex Mini by OpenAI — コンパクトなコーディングモデルで強力な能力を備えています。",
    "ru-RU": "GPT-5.1 Codex Mini от OpenAI — компактная, но производительная модель для программирования."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1-instant",
   "model_name": "gpt-5.1-instant",
   "display_name": "GPT-5.1 Instant",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "openai/gpt-5.1-instant"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-instant"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-11-12",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "stream": true
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5.1-instant"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.1 Instant"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1-thinking",
   "model_name": "gpt-5.1-thinking",
   "display_name": "GPT 5.1 Thinking",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.1-thinking",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-11-12",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5.1-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT 5.1 Thinking"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1@eastus2",
   "model_name": "gpt-5.1@eastus2",
   "display_name": "azure/gpt-5.1@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "azure/gpt-5.1@eastus2"
    }
   ],
   "released_at": "2025-11-26",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.1@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.1@eastus2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1@francecentral",
   "model_name": "gpt-5.1@francecentral",
   "display_name": "azure/gpt-5.1@francecentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "azure/gpt-5.1@francecentral"
    }
   ],
   "released_at": "2025-11-26",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.1@francecentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.1@francecentral"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.1@swedencentral",
   "model_name": "gpt-5.1@swedencentral",
   "display_name": "azure/gpt-5.1@swedencentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "azure/gpt-5.1@swedencentral"
    }
   ],
   "released_at": "2025-11-26",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.1@swedencentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.1@swedencentral"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.2-2025-12-11",
   "model_name": "gpt-5.2-2025-12-11",
   "display_name": "gpt-5.2-2025-12-11",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5.2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5.2"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.575"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.6"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5-2"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "qihang-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5.2"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.75"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2"
    }
   ],
   "intro": "Reliable GPT generation for broad coding, writing, and tool-assisted product work",
   "released_at": "2025-12-11",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "gpt-5-2",
    "gpt-5.2",
    "openai-responses/gpt-5.2",
    "openai/gpt-5.2",
    "openai/gpt-5.2-2025-12-11",
    "pa/gpt-5.2"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.2 —— 推理与多模态处理能力全面升级。",
    "zh-TW": "OpenAI GPT-5.2 —— 升級版推理與多模態處理能力。",
    "ja-JP": "GPT-5.2 by OpenAI — 推論とマルチモーダル処理がアップグレードされたモデル。",
    "ru-RU": "GPT-5.2 от OpenAI — улучшенная модель с расширенными возможностями рассуждения и мультимодальной обработки."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "limit",
     "old": "272000",
     "new": "400000",
     "note": "max_input_tokens"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "cache_read",
     "old": "0.175",
     "new": "0.125"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.2-chat-2026-02-10",
   "model_name": "gpt-5.2-chat-2026-02-10",
   "display_name": "GPT-5.2 Chat",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.2-chat-2025-12-11",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "gpt-5.2-chat"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.2-chat"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5.2-chat"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2-chat"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2-chat"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+truefoundry+openrouter+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2-chat"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2-chat"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2-chat"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2-chat"
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2025-12-11",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-5.2-chat",
    "gpt-5.2-chat-2025-12-11",
    "openai/gpt-5.2-chat"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5.2 Chat 是 ChatGPT 的变体，用于体验最新的对话改进。",
    "zh-TW": "GPT-5.2 Chat 是 ChatGPT 的變體，用於體驗最新的對話改進。",
    "ja-JP": "GPT-5.2 Chatは、最新の会話機能を体験できるChatGPTバリアントです。",
    "ru-RU": "GPT-5.2 Chat — вариант ChatGPT для знакомства с последними улучшениями в диалогах."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.2 Chat"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.2-chat-latest",
   "model_name": "gpt-5.2-chat-latest",
   "display_name": "GPT-5.2 Chat",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5.2-chat-latest"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.3"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2-chat-latest"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2-chat-latest"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2025-12-11",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "deprecated": true,
   "aliases": [
    "openai/gpt-5.2-chat-latest",
    "pa/gpt-5.2-chat-latest"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5.2 Chat 是 ChatGPT 的最新对话版本，带来最新的对话体验改进。",
    "zh-TW": "GPT-5.2 Chat 是 ChatGPT 的最新對話版本，帶來最新的對話體驗改進。",
    "ja-JP": "GPT-5.2 Chatは、最新の会話機能を備えたChatGPTバリアント（chat-latest）です。",
    "ru-RU": "GPT-5.2 Chat — это вариант ChatGPT (chat-latest) с последними улучшениями в области диалогов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.2-codex",
   "model_name": "gpt-5.2-codex",
   "display_name": "GPT-5.2 Codex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.2-codex-2026-01-14"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5-2-codex"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex"
    },
    {
     "provider": "qihang-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.75"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2-codex"
    }
   ],
   "intro": "Code-specialist GPT for repository edits, reviews, and long-running software agents",
   "released_at": "2025-12-11",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "gpt-5-2-codex",
    "gpt-5.2-codex-2026-01-14",
    "openai-responses/gpt-5.2-codex",
    "openai/gpt-5.2-codex"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.2 Codex —— 工具调用准确度更高的代码专项模型。",
    "zh-TW": "OpenAI GPT-5.2 Codex —— 專注程式能力並提升工具調用準確度。",
    "ja-JP": "GPT-5.2 Codex by OpenAI — ツール呼び出し精度が向上したコーディング特化型モデル。",
    "ru-RU": "GPT-5.2 Codex от OpenAI — специализированная модель программирования с повышенной точностью вызовов инструментов."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.2-codex@eastus2",
   "model_name": "gpt-5.2-codex@eastus2",
   "display_name": "azure/gpt-5.2-codex@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "azure/gpt-5.2-codex@eastus2"
    }
   ],
   "released_at": "2026-01-22",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.2-codex@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.2-codex@eastus2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.2-high",
   "model_name": "gpt-5.2-high",
   "display_name": "gpt-5.2-high",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    }
   ],
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.2-high"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.2-instant",
   "model_name": "gpt-5.2-instant",
   "display_name": "GPT-5.2-Instant",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "openai/gpt-5.2-instant"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-12-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5.2-instant"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.2-Instant"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.2-low",
   "model_name": "gpt-5.2-low",
   "display_name": "gpt-5.2-low",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    }
   ],
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.2-low"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.2-pro-2025-12-11",
   "model_name": "gpt-5.2-pro-2025-12-11",
   "display_name": "gpt-5.2-pro-2025-12-11",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5.2-pro",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      }
     },
     "provider_model_id": "gpt-5.2-pro"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.2-pro"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      }
     },
     "provider_model_id": "openai/gpt-5.2-pro"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5.2-pro"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "18.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "151.2"
      }
     },
     "provider_model_id": "gpt-5.2-pro"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      }
     },
     "provider_model_id": "openai/gpt-5.2-pro"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      }
     },
     "provider_model_id": "gpt-5.2-pro"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      }
     },
     "provider_model_id": "openai/gpt-5.2-pro"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2-pro"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      }
     },
     "provider_model_id": "openai/gpt-5.2-pro"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      }
     },
     "provider_model_id": "openai/gpt-5.2-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      }
     },
     "provider_model_id": "openai/gpt-5.2-pro"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      }
     },
     "provider_model_id": "gpt-5.2-pro"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2-pro"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.2-pro"
    }
   ],
   "intro": "Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows",
   "released_at": "2025-12-11",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-pro",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "gpt-5-2-pro",
    "gpt-5.2-pro",
    "openai/gpt-5.2-pro",
    "openai/gpt-5.2-pro-2025-12-11",
    "pa/gpt-5.2-pro"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5.2 Pro：更智能、更精准的 GPT-5.2 变体（仅限 Responses API），适用于复杂问题和多轮推理。",
    "zh-TW": "GPT-5.2 Pro：更智慧、更精確的 GPT-5.2 變體（僅限 Responses API），適用於高難度問題與多輪長推理。",
    "ja-JP": "GPT-5.2 Proは、より賢く精密なGPT-5.2バリアント（Responses API専用）であり、難解な問題や長い多段階推論に適しています。",
    "ru-RU": "GPT-5.2 pro: более умный и точный вариант GPT-5.2 (только через Responses API), подходит для сложных задач и многошагового рассуждения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "limit",
     "old": "272000",
     "new": "400000",
     "note": "max_input_tokens"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.2@eastus2",
   "model_name": "gpt-5.2@eastus2",
   "display_name": "azure/gpt-5.2@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "azure/gpt-5.2@eastus2"
    }
   ],
   "released_at": "2026-01-26",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.2@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.2@eastus2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.3",
   "model_name": "gpt-5.3",
   "display_name": "gpt-5.3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    }
   ],
   "intro": "GPT-5.3 Instant model used in ChatGPT",
   "max_input_tokens": 128000,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.3"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.3-chat-2026-03-03",
   "model_name": "gpt-5.3-chat-2026-03-03",
   "display_name": "GPT-5.3 Chat",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.36"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "gpt-5.3-chat"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.3-chat"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.3-chat"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.3-chat"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.3-chat"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai-responses/gpt-5.3-chat"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.3-chat"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.3-chat"
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2026-03-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-08",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-5.3-chat",
    "openai-responses/gpt-5.3-chat",
    "openai/gpt-5.3-chat"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.3 Chat"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.3-chat-latest",
   "model_name": "gpt-5.3-chat-latest",
   "display_name": "GPT-5.3 Chat",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+portkey+lobehub-modelbank+pricetoken+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.3"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.3-chat-latest"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.3-chat-latest"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    }
   ],
   "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
   "released_at": "2026-03-03",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "deprecated": true,
   "aliases": [
    "openai/gpt-5.3-chat-latest"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5.3 Chat 是最新的 ChatGPT 模型，改进了对话体验。",
    "zh-TW": "GPT-5.3 Chat 是最新的 ChatGPT 模型，提供改進的對話體驗。",
    "ja-JP": "GPT-5.3 ChatはChatGPTで使用される最新のChatGPTモデルで、会話体験が向上しています。",
    "ru-RU": "GPT-5.3 Chat — это последняя модель ChatGPT, используемая в ChatGPT, с улучшенным опытом общения."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.3-codex",
   "model_name": "gpt-5.3-codex",
   "display_name": "GPT-5.3 Codex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+pricetoken+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.3-codex-2026-02-20"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5-3-codex"
    },
    {
     "provider": "freemodel",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.75"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5-3-codex"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.3"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "gpt-5-3-codex"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.75"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex"
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "gpt-5-3-codex",
    "gpt-5.3-codex-2026-02-20",
    "gpt-5.3-codex-2026-02-24",
    "openai-responses/gpt-5.3-codex",
    "openai/gpt-5.3-codex"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.3 Codex —— 新一代 Codex，具备更强代码理解能力。",
    "zh-TW": "OpenAI GPT-5.3 Codex —— 最新 Codex，具備更強的程式理解能力。",
    "ja-JP": "GPT-5.3 Codex by OpenAI — コード理解が強化された最新のCodexモデル。",
    "ru-RU": "GPT-5.3 Codex от OpenAI — последняя версия Codex с улучшенным пониманием кода."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.3-codex-spark",
   "model_name": "gpt-5.3-codex-spark",
   "display_name": "GPT-5.3 Codex Spark",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/gpt-5.3-codex-spark"
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex-spark",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5.3-codex-spark"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.3 Codex Spark —— 速度优化的小型编码模型。",
    "zh-TW": "OpenAI GPT-5.3 Codex Spark —— 高速優化的輕量型程式模型。",
    "ja-JP": "GPT-5.3 Codex Spark by OpenAI — スピードに最適化されたコンパクトなコーディングモデル。",
    "ru-RU": "GPT-5.3 Codex Spark от OpenAI — компактная модель программирования, оптимизированная для скорости."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.3-codex-xhigh",
   "model_name": "gpt-5.3-codex-xhigh",
   "display_name": "GPT-5.3 Codex XHigh",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.3 Codex XHigh"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.3-codex@eastus2",
   "model_name": "gpt-5.3-codex@eastus2",
   "display_name": "azure/gpt-5.3-codex@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "azure/gpt-5.3-codex@eastus2"
    }
   ],
   "released_at": "2026-02-24",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.3-codex@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.3-codex@eastus2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.3-instant",
   "model_name": "gpt-5.3-instant",
   "display_name": "GPT-5.3-Instant",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "openai/gpt-5.3-instant"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-03-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5.3-instant"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.3-Instant"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4-2026-03-05",
   "model_name": "gpt-5.4-2026-03-05",
   "display_name": "gpt-5.4-2026-03-05",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt_0_0_272": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "prompt_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read_0_0_272": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion_0_0_272": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "22.5"
      }
     },
     "provider_model_id": "gpt-5.4",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "gpt-5.4",
     "region": "ae",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "gpt-5.4",
     "region": "au",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "gpt-5.4",
     "region": "ca",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "gpt-5.4",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "gpt-5.4",
     "region": "gb",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "gpt-5.4",
     "region": "in",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "gpt-5.4",
     "region": "jp",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "gpt-5.4",
     "region": "kr",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "gpt-5.4",
     "region": "sg",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "gpt-5.4",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "prompt_0_0_272": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "prompt_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read_0_0_272": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_read_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion_0_0_272": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "22.5"
      }
     },
     "provider_model_id": "gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai.gpt-5.4"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "openai.gpt-5.4",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "openai.gpt-5.4",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.8"
      }
     },
     "provider_model_id": "openai.gpt-5.4",
     "region": "us-gov-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      }
     },
     "provider_model_id": "openai.gpt-5.4",
     "region": "us-west-2"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      }
     },
     "provider_model_id": "gpt-5.4",
     "tracks": [
      {
       "label": ">272000000K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "cache_read": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5.4"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5.4"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5-4"
    },
    {
     "provider": "freemodel",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.25"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5.4"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "openai/gpt-5.4"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5.4"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5-4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "22.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5-4"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5.4"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "openai/gpt-5.4"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "ex/gpt-5.4"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.52"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5.4"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.2",
        "cache_read": "2",
        "prompt": "1.333333"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
   "released_at": "2026-03-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "parallel_function_calling": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "docs_url": "https://ai.azure.com/catalog/models/gpt-5.4",
   "benchmarks": {
    "intelligence_index": 51.4,
    "coding_index": 71.1,
    "agentic_index": 41.1
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "azure/gpt-5.4",
    "ex/gpt-5.4",
    "gpt-5-4",
    "gpt-5.4",
    "openai-responses/gpt-5.4",
    "openai.gpt-5.4",
    "openai.gpt-5.4-2026-03-05",
    "openai/gpt-5.4",
    "openai/gpt-5.4-2026-03-05",
    "pa/gpt-5.4",
    "pa/gpt-5.4-2026-03-05",
    "codex-auto-review",
    "openai/codex-auto-review"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.4 —— 新一代模型，支持百万级上下文与多模态输入。",
    "zh-TW": "OpenAI GPT-5.4 —— 次世代模型，具備百萬級上下文與多模態輸入能力。",
    "ja-JP": "GPT-5.4 by OpenAI — 1M+コンテキストウィンドウとマルチモーダル入力を備えた次世代モデル。",
    "ru-RU": "GPT-5.4 от OpenAI — модель следующего поколения с контекстом более 1M и мультимодальным вводом."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "openrouter",
     "charge": "completion",
     "old": "15.825",
     "new": "15"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "2.6375",
     "new": "2.5"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4-272k",
   "model_name": "gpt-5.4-272k",
   "display_name": "GPT-5.4",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "22.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4-high",
   "model_name": "gpt-5.4-high",
   "display_name": "gpt-5.4-high",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    }
   ],
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.4-high"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4-image-2",
   "model_name": "gpt-5.4-image-2",
   "display_name": "OpenAI: GPT-5.4 Image 2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-5.4-image-2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4-image-2"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "openai/gpt-5.4-image-2"
    }
   ],
   "intro": "GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows across reasoning, coding, and image generation.",
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "released_at": "2026-04-21",
   "max_input_tokens": 272000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text",
     "pdf"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "family": "gpt",
   "model_type": "image_generation",
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5.4-image-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI: GPT-5.4 Image 2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4-low",
   "model_name": "gpt-5.4-low",
   "display_name": "gpt-5.4-low",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    }
   ],
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.4-low"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4-mini-2026-03-17",
   "model_name": "gpt-5.4-mini-2026-03-17",
   "display_name": "gpt-5.4-mini-2026-03-17",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.825"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "region": "ae",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.825"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "region": "au",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.825"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "region": "ca",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.825"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.825"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "region": "gb",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.825"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "region": "in",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.825"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "region": "jp",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.825"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "region": "kr",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.825"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "region": "sg",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.825"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0825"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      }
     },
     "provider_model_id": "gpt-5.4-mini",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "freemodel",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5-4-mini"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.275"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5-4-mini"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5-4-mini"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.68"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "azure/gpt-5.4-mini"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "gpt-5.4-mini"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4-mini"
    }
   ],
   "intro": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
   "released_at": "2026-03-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "docs_url": "https://ai.azure.com/catalog/models/gpt-5.4-mini",
   "benchmarks": {
    "intelligence_index": 40,
    "coding_index": 56.1,
    "agentic_index": 30.2
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "azure/gpt-5.4-mini",
    "gpt-5-4-mini",
    "gpt-5.4-mini",
    "openai-responses/gpt-5.4-mini",
    "openai/gpt-5.4-mini",
    "openai/gpt-5.4-mini-2026-03-17"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.4 Mini —— 性能与成本的高效平衡。",
    "zh-TW": "OpenAI GPT-5.4 Mini —— 在成本與效能間取得高效平衡。",
    "ja-JP": "GPT-5.4 Mini by OpenAI — コストと性能のバランスが取れた効率的なモデル。",
    "ru-RU": "GPT-5.4 Mini от OpenAI — эффективная модель, сочетающая стоимость и производительность."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "limit",
     "old": "1050000",
     "new": "400000",
     "note": "max_input_tokens"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4-mini@eastus2",
   "model_name": "gpt-5.4-mini@eastus2",
   "display_name": "azure/gpt-5.4-mini@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "azure/gpt-5.4-mini@eastus2"
    }
   ],
   "released_at": "2026-03-17",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.4-mini@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.4-mini@eastus2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4-nano-2026-03-17",
   "model_name": "gpt-5.4-nano-2026-03-17",
   "display_name": "gpt-5.4-nano-2026-03-17",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "region": "ae",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "region": "au",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "region": "ca",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "region": "gb",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "region": "in",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "region": "jp",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "region": "kr",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "region": "sg",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.375"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.022"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+computeprices+portkey+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      }
     },
     "provider_model_id": "gpt-5.4-nano",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5-4-nano"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1875"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5-4-nano"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.018"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai-responses/gpt-5.4-nano"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.019999999999999997"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano",
     "tracks": [
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "gpt-5.4-nano"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4-nano"
    }
   ],
   "intro": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
   "released_at": "2026-03-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-nano",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "docs_url": "https://ai.azure.com/catalog/models/gpt-5.4-nano",
   "benchmarks": {
    "intelligence_index": 38.2,
    "coding_index": 56.1,
    "agentic_index": 27.5
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "gpt-5-4-nano",
    "gpt-5.4-nano",
    "openai-responses/gpt-5.4-nano",
    "openai/gpt-5.4-nano",
    "openai/gpt-5.4-nano-2026-03-17"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.4 Nano —— 超轻量模型，适用于高吞吐任务。",
    "zh-TW": "OpenAI GPT-5.4 Nano —— 超輕量模型，適合高吞吐量任務。",
    "ja-JP": "GPT-5.4 Nano by OpenAI — 高スループットタスク向けの超軽量モデル。",
    "ru-RU": "GPT-5.4 Nano от OpenAI — сверхлёгкая модель для высокоскоростных задач."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "limit",
     "old": "1050000",
     "new": "400000",
     "note": "max_input_tokens"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4-pro-2026-03-05",
   "model_name": "gpt-5.4-pro-2026-03-05",
   "display_name": "gpt-5.4-pro-2026-03-05",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt_0_0_272": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "prompt_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion_0_0_272": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "completion_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "270"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "region": "ae",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "region": "au",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "region": "ca",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "region": "gb",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "region": "in",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "region": "jp",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "region": "kr",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "region": "sg",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt_0_0_272": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "prompt_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion_0_0_272": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "completion_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "270"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "gpt-5.4-pro"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "79.49"
      }
     },
     "provider_model_id": "gpt-5.4-pro"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "tracks": [
      {
       "label": ">272000000K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "gpt-5.4-pro",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "openai/gpt-5.4-pro"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "28.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "171"
      }
     },
     "provider_model_id": "gpt-5.4-pro"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "openai/gpt-5.4-pro"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "gpt-5.4-pro"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "openai/gpt-5.4-pro"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "gpt-5.4-pro"
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "gpt-5.4-pro"
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "gpt-5.4-pro"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-5.4-pro",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "270"
      }
     },
     "provider_model_id": "openai/gpt-5.4-pro",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "160"
      }
     },
     "provider_model_id": "openai/gpt-5.4-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-5.4-pro"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "gpt-5.4-pro"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-5.4-pro"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4-pro",
     "tracks": [
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "225"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.4-pro",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.2",
        "prompt": "1.333333"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks",
   "released_at": "2026-03-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-pro",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "docs_url": "https://ai.azure.com/catalog/models/gpt-5.4-pro",
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "gpt-5-4-pro",
    "gpt-5.4-pro",
    "openai-responses/gpt-5.4-pro",
    "openai/gpt-5.4-pro",
    "openai/gpt-5.4-pro-2026-03-05"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的 GPT-5.4 Pro —— 具备最大上下文与推理能力的高端模型。",
    "zh-TW": "OpenAI GPT-5.4 Pro —— 最強模型，提供最大上下文與推理能力。",
    "ja-JP": "GPT-5.4 Pro by OpenAI — 最大コンテキストと推論能力を備えた最も能力の高いモデル。",
    "ru-RU": "GPT-5.4 Pro от OpenAI — самая мощная модель с максимальным контекстом и рассуждениями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4-pro-272k",
   "model_name": "gpt-5.4-pro-272k",
   "display_name": "GPT-5.4 Pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "270"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4 Pro"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4@us-east-1",
   "model_name": "gpt-5.4@us-east-1",
   "display_name": "bedrock/gpt-5.4@us-east-1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "bedrock/gpt-5.4@us-east-1"
    }
   ],
   "released_at": "2026-06-16",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "bedrock/gpt-5.4@us-east-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/gpt-5.4@us-east-1"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4@us-east-2",
   "model_name": "gpt-5.4@us-east-2",
   "display_name": "bedrock/gpt-5.4@us-east-2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "bedrock/gpt-5.4@us-east-2"
    }
   ],
   "released_at": "2026-06-16",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "bedrock/gpt-5.4@us-east-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/gpt-5.4@us-east-2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.4@us-west-2",
   "model_name": "gpt-5.4@us-west-2",
   "display_name": "bedrock/gpt-5.4@us-west-2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "bedrock/gpt-5.4@us-west-2"
    }
   ],
   "released_at": "2026-06-16",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "bedrock/gpt-5.4@us-west-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/gpt-5.4@us-west-2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.5-2026-04-23",
   "model_name": "gpt-5.5-2026-04-23",
   "display_name": "gpt-5.5-2026-04-23",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "prompt_0_0_272": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "prompt_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read_0_0_272": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion_0_0_272": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "45"
      }
     },
     "provider_model_id": "gpt-5.5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "gpt-5.5",
     "region": "ae",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "gpt-5.5",
     "region": "au",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "gpt-5.5",
     "region": "ca",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "gpt-5.5",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "gpt-5.5",
     "region": "gb",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "gpt-5.5",
     "region": "in",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "gpt-5.5",
     "region": "jp",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "gpt-5.5",
     "region": "kr",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "gpt-5.5",
     "region": "sg",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "gpt-5.5",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-5.5"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt_0_0_272": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "prompt_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read_0_0_272": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion_0_0_272": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion_0_272_infinity": {
       "unit": "per_M_tokens",
       "price": "45"
      }
     },
     "provider_model_id": "gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai.gpt-5.5"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "gpt-5.5"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      }
     },
     "provider_model_id": "openai.gpt-5.5"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5"
    },
    {
     "provider": "freemodel",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "gpt-5.5"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "gpt-5-5"
    },
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "28.5"
      }
     },
     "provider_model_id": "gpt-5.5"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5-5"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-5.5"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "perplexity",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.5455"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.2727"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4545"
      }
     },
     "provider_model_id": "openai/gpt-5.5"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai-responses/gpt-5.5"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-5.5"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-5.5"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "openai/gpt-5.5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.5",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "2.5",
        "completion": "2.5",
        "cache_read": "2.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Default frontier GPT for coding, computer use, research, and knowledge work",
   "released_at": "2026-04-23",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "docs_url": "https://ai.azure.com/catalog/models/gpt-5.5",
   "benchmarks": {
    "intelligence_index": 54.8,
    "coding_index": 74.9,
    "agentic_index": 44.9
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "gpt-5-5",
    "gpt-5.5",
    "gpt-5.5-2026-04-24",
    "openai-responses/gpt-5.5",
    "openai.gpt-5.5",
    "openai.gpt-5.5-2026-04-23",
    "openai/gpt-5.5",
    "openai/gpt-5.5-2026-04-23"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5.5 是我们最新的前沿模型，适用于最复杂的专业工作。",
    "zh-TW": "GPT-5.5 是我們最新的前沿模型，適用於最複雜的專業工作。",
    "ja-JP": "GPT-5.5は、最も複雑なプロフェッショナルな作業向けの最新のフロンティアモデルです。",
    "ru-RU": "GPT-5.5 — наша новейшая передовая модель для самых сложных профессиональных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "orcarouter",
     "charge": "completion",
     "old": "45",
     "new": "30"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "orcarouter",
     "charge": "prompt",
     "old": "10",
     "new": "5"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.5-272k",
   "model_name": "gpt-5.5-272k",
   "display_name": "GPT-5.5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "45"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.5"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.5-instant",
   "model_name": "gpt-5.5-instant",
   "display_name": "GPT-5.5 Instant",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-5.5-instant"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-05",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-5.5-instant"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.5 Instant"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.5-light",
   "model_name": "gpt-5.5-light",
   "display_name": "gpt-5.5-light",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "released_at": "2026-05-12",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.5-light"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.5-pro-2026-04-23",
   "model_name": "gpt-5.5-pro-2026-04-23",
   "display_name": "gpt-5.5-pro-2026-04-23",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "region": "ae",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "region": "au",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "region": "ca",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "region": "eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "region": "gb",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "region": "in",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "region": "jp",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "region": "kr",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "region": "sg",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "198"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "region": "us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "gpt-5.5-pro"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "openai/gpt-5.5-pro"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "gpt-5.5-pro"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "openai/gpt-5.5-pro"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "gpt-5.5-pro",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "gpt-5.5-pro"
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "gpt-5.5-pro"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.5-pro"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "openai/gpt-5.5-pro",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "27.2727"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "163.6364"
      }
     },
     "provider_model_id": "openai/gpt-5.5-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "openai-responses/gpt-5.5-pro"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "gpt-5.5-pro"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-5.5-pro"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "14"
      }
     },
     "provider_model_id": "openai/gpt-5.5-pro",
     "tracks": [
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-5.5-pro",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding",
   "released_at": "2026-04-23",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-pro",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "aliases": [
    "gpt-5.5-pro",
    "openai-responses/gpt-5.5-pro",
    "openai/gpt-5.5-pro",
    "openai/gpt-5.5-pro-2026-04-23"
   ],
   "intro_i18n": {
    "zh-CN": "GPT-5.5 Pro 通过更高计算投入实现更深入思考，并持续输出更可靠的答案。",
    "zh-TW": "GPT-5.5 Pro 使用更多算力進行更深入的思考，提供始終如一的高品質回答。",
    "ja-JP": "GPT-5.5 Proは、より多くの計算を使用して、より深く考え、一貫して優れた回答を提供します。",
    "ru-RU": "GPT-5.5 Pro использует больше вычислительных ресурсов для более глубоких рассуждений и consistently better answers."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "orcarouter",
     "charge": "completion",
     "old": "270",
     "new": "180"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "orcarouter",
     "charge": "prompt",
     "old": "60",
     "new": "30"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.5-r",
   "model_name": "gpt-5.5-r",
   "display_name": "gpt-5.5-r",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "released_at": "2026-06-03",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.5-r"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.5@us-east-1",
   "model_name": "gpt-5.5@us-east-1",
   "display_name": "bedrock/gpt-5.5@us-east-1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "bedrock/gpt-5.5@us-east-1"
    }
   ],
   "released_at": "2026-06-16",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "bedrock/gpt-5.5@us-east-1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/gpt-5.5@us-east-1"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.5@us-east-2",
   "model_name": "gpt-5.5@us-east-2",
   "display_name": "bedrock/gpt-5.5@us-east-2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "bedrock/gpt-5.5@us-east-2"
    }
   ],
   "released_at": "2026-06-16",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "bedrock/gpt-5.5@us-east-2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bedrock/gpt-5.5@us-east-2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.6-luna",
   "model_name": "gpt-5.6-luna",
   "display_name": "GPT-5.6 Luna",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.6 Luna"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.6-sol",
   "model_name": "gpt-5.6-sol",
   "display_name": "GPT-5.6 Sol",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.6 Sol"
    }
   ]
  },
  {
   "slug": "openai/gpt-5.6-terra",
   "model_name": "gpt-5.6-terra",
   "display_name": "GPT-5.6 Terra",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.6 Terra"
    }
   ]
  },
  {
   "slug": "openai/gpt-5@eastus2",
   "model_name": "gpt-5@eastus2",
   "display_name": "azure/gpt-5@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "azure/gpt-5@eastus2"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5@eastus2"
    }
   ]
  },
  {
   "slug": "openai/gpt-5@francecentral",
   "model_name": "gpt-5@francecentral",
   "display_name": "azure/gpt-5@francecentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "azure/gpt-5@francecentral"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5@francecentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5@francecentral"
    }
   ]
  },
  {
   "slug": "openai/gpt-5@swedencentral",
   "model_name": "gpt-5@swedencentral",
   "display_name": "azure/gpt-5@swedencentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "azure/gpt-5@swedencentral"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5@swedencentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5@swedencentral"
    }
   ]
  },
  {
   "slug": "openai/gpt-5@uksouth",
   "model_name": "gpt-5@uksouth",
   "display_name": "azure/gpt-5@uksouth",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "azure/gpt-5@uksouth"
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5@uksouth"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5@uksouth"
    }
   ]
  },
  {
   "slug": "openai/gpt-audio",
   "model_name": "gpt-audio",
   "display_name": "gpt-audio",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-audio-2025-08-28"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "26.43"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     },
     "provider_model_id": "gpt-audio-2025-08-28"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-audio"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      }
     },
     "provider_model_id": "openai/gpt-audio"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "openai/gpt-audio"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "omni",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "intro": "The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural-sounding voices and maintains better voice consistency.",
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "released_at": "2025-08-28",
   "knowledge_cutoff": "2023-10",
   "family": "gpt",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "aliases": [
    "gpt-audio-2025-08-28",
    "openai/gpt-audio"
   ],
   "intro_i18n": {
    "zh-CN": "GPT Audio 是支持音频输入/输出的通用对话模型，可通过 Chat Completions API 使用。",
    "zh-TW": "GPT Audio 是一款通用聊天模型，支援音訊輸入/輸出，並整合於 Chat Completions API 中。",
    "ja-JP": "GPT Audio は、音声の入出力に対応した汎用チャットモデルで、Chat Completions API に対応しています。",
    "ru-RU": "GPT Audio — универсальная модель общения с поддержкой ввода и вывода аудио, доступная через API завершения чата."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "audio_input",
     "old": "32",
     "new": "40"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "audio_output",
     "old": "64",
     "new": "80"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-audio-1.5",
   "model_name": "gpt-audio-1.5",
   "display_name": "gpt-audio-1.5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.88"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     },
     "provider_model_id": "gpt-audio-1.5-2026-02-23"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "omni",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "released_at": "2026-02-20",
   "knowledge_cutoff": "2024-09",
   "aliases": [
    "gpt-audio-1.5-2026-02-23"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "completion",
     "old": "23.34",
     "new": "8.88"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "prompt",
     "old": "5.82",
     "new": "2.22"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-audio-mini",
   "model_name": "gpt-audio-mini",
   "display_name": "gpt-audio-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-audio-mini-2025-10-06"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "gpt-audio-mini-2025-10-06"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "openai/gpt-audio-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     },
     "provider_model_id": "openai/gpt-audio-mini"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "75"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "openai/gpt-audio-mini"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "model_type": "omni",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "intro": "A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.",
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "deprecated": true,
   "released_at": "2025-10-03",
   "knowledge_cutoff": "2023-10",
   "family": "o-mini",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "aliases": [
    "gpt-audio-mini-2025-10-06",
    "gpt-audio-mini-2025-12-15",
    "openai/gpt-audio-mini"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-chat-latest",
   "model_name": "gpt-chat-latest",
   "display_name": "OpenAI: GPT Chat Latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-chat-latest-2026-05-05"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-chat-latest"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-chat-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-chat-latest"
    }
   ],
   "intro": "GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "released_at": "2026-05-05",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "pdf",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "family": "gpt",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-chat-latest-2026-05-05",
    "gpt-chat-latest-2026-05-28",
    "openai/gpt-chat-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI: GPT Chat Latest"
    }
   ]
  },
  {
   "slug": "openai/gpt-image-1",
   "model_name": "gpt-image-1",
   "display_name": "gpt-image-1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.167"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.167"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.167"
      },
      "image_output_1024x1536": {
       "unit": "per_image",
       "price": "0.25"
      },
      "image_output_1536x1024": {
       "unit": "per_image",
       "price": "0.25"
      },
      "image_output_hd": {
       "unit": "per_image",
       "price": "0.167"
      },
      "image_output_1024px_hd": {
       "unit": "per_image",
       "price": "0.167"
      },
      "image_output_1024x1536_hd": {
       "unit": "per_image",
       "price": "0.25"
      },
      "image_output_1536x1024_hd": {
       "unit": "per_image",
       "price": "0.25"
      },
      "image_output_medium": {
       "unit": "per_image",
       "price": "0.042"
      },
      "image_output_1024px_medium": {
       "unit": "per_image",
       "price": "0.042"
      },
      "image_output_1024x1536_medium": {
       "unit": "per_image",
       "price": "0.063"
      },
      "image_output_1536x1024_medium": {
       "unit": "per_image",
       "price": "0.063"
      },
      "image_output_low": {
       "unit": "per_image",
       "price": "0.011"
      },
      "image_output_1024px_low": {
       "unit": "per_image",
       "price": "0.011"
      },
      "image_output_1024x1536_low": {
       "unit": "per_image",
       "price": "0.016"
      },
      "image_output_1536x1024_low": {
       "unit": "per_image",
       "price": "0.016"
      },
      "image_output_tokens": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.167"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.167"
      },
      "image_output_1024x1536": {
       "unit": "per_image",
       "price": "0.25"
      },
      "image_output_1536x1024": {
       "unit": "per_image",
       "price": "0.25"
      },
      "image_output_hd": {
       "unit": "per_image",
       "price": "0.167"
      },
      "image_output_1024px_hd": {
       "unit": "per_image",
       "price": "0.167"
      },
      "image_output_1024x1536_hd": {
       "unit": "per_image",
       "price": "0.25"
      },
      "image_output_1536x1024_hd": {
       "unit": "per_image",
       "price": "0.25"
      },
      "image_output_medium": {
       "unit": "per_image",
       "price": "0.042"
      },
      "image_output_1024px_medium": {
       "unit": "per_image",
       "price": "0.042"
      },
      "image_output_1024x1536_medium": {
       "unit": "per_image",
       "price": "0.063"
      },
      "image_output_1536x1024_medium": {
       "unit": "per_image",
       "price": "0.063"
      },
      "image_output_low": {
       "unit": "per_image",
       "price": "0.011"
      },
      "image_output_1024px_low": {
       "unit": "per_image",
       "price": "0.011"
      },
      "image_output_1024x1536_low": {
       "unit": "per_image",
       "price": "0.016"
      },
      "image_output_1536x1024_low": {
       "unit": "per_image",
       "price": "0.016"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "image_output_tokens": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-image-1-2025-04-15"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "openai/gpt-image-1"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     },
     "provider_model_id": "openai/gpt-image-1"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-image-1"
    }
   ],
   "intro": "OpenAI image model for production generation, edits, and brand-safe visual workflows",
   "released_at": "2025-04-24",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "gpt-image",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "image_generation",
   "deprecated": true,
   "knowledge_cutoff": "2025-04",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-image-1-2025-04-15",
    "openai/gpt-image-1"
   ],
   "intro_i18n": {
    "zh-CN": "ChatGPT 原生多模态图像生成模型。",
    "zh-TW": "ChatGPT 原生多模態圖像生成模型。",
    "ja-JP": "ChatGPT にネイティブ対応したマルチモーダル画像生成モデルです。",
    "ru-RU": "Нативная мультимодальная модель генерации изображений ChatGPT."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-image-1-mini",
   "model_name": "gpt-image-1-mini",
   "display_name": "gpt-image-1-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "gpt-image-1-mini-2025-10-06"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-image-1-mini"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "openai/gpt-image-1-mini"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai/gpt-image-1-mini"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-09-26",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "gpt-image",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "image_generation",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-image-1-mini-2025-10-06",
    "openai/gpt-image-1-mini"
   ],
   "intro_i18n": {
    "zh-CN": "GPT Image 1 的低成本变体，原生支持文本与图像输入，以及图像输出。",
    "zh-TW": "GPT Image 1 的低成本變體，原生支援文字與圖片輸入，並輸出圖片。",
    "ja-JP": "低コストな GPT Image 1 バリアントで、テキストと画像の入力および画像出力に対応しています。",
    "ru-RU": "Бюджетный вариант GPT Image 1 с нативной поддержкой ввода текста и изображений и генерацией изображений."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-image-1.5-2025-12-16",
   "model_name": "gpt-image-1.5-2025-12-16",
   "display_name": "gpt-image-1.5-2025-12-16",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.009"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.009"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.133"
      },
      "image_output_1024x1536": {
       "unit": "per_image",
       "price": "0.2"
      },
      "image_output_1536x1024": {
       "unit": "per_image",
       "price": "0.2"
      },
      "image_output_hd": {
       "unit": "per_image",
       "price": "0.133"
      },
      "image_output_1024px_hd": {
       "unit": "per_image",
       "price": "0.133"
      },
      "image_output_1024x1536_hd": {
       "unit": "per_image",
       "price": "0.2"
      },
      "image_output_1536x1024_hd": {
       "unit": "per_image",
       "price": "0.2"
      },
      "image_output_medium": {
       "unit": "per_image",
       "price": "0.034"
      },
      "image_output_1024px_medium": {
       "unit": "per_image",
       "price": "0.034"
      },
      "image_output_1024x1536_medium": {
       "unit": "per_image",
       "price": "0.05"
      },
      "image_output_1536x1024_medium": {
       "unit": "per_image",
       "price": "0.05"
      },
      "image_output_low": {
       "unit": "per_image",
       "price": "0.009"
      },
      "image_output_1024px_low": {
       "unit": "per_image",
       "price": "0.009"
      },
      "image_output_1024x1536_low": {
       "unit": "per_image",
       "price": "0.013"
      },
      "image_output_1536x1024_low": {
       "unit": "per_image",
       "price": "0.013"
      },
      "image_output_tokens": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-image-1.5",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.133"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.133"
      },
      "image_output_1024x1536": {
       "unit": "per_image",
       "price": "0.2"
      },
      "image_output_1536x1024": {
       "unit": "per_image",
       "price": "0.2"
      },
      "image_output_hd": {
       "unit": "per_image",
       "price": "0.133"
      },
      "image_output_1024px_hd": {
       "unit": "per_image",
       "price": "0.133"
      },
      "image_output_1024x1536_hd": {
       "unit": "per_image",
       "price": "0.2"
      },
      "image_output_1536x1024_hd": {
       "unit": "per_image",
       "price": "0.2"
      },
      "image_output_medium": {
       "unit": "per_image",
       "price": "0.034"
      },
      "image_output_1024px_medium": {
       "unit": "per_image",
       "price": "0.034"
      },
      "image_output_1024x1536_medium": {
       "unit": "per_image",
       "price": "0.05"
      },
      "image_output_1536x1024_medium": {
       "unit": "per_image",
       "price": "0.05"
      },
      "image_output_low": {
       "unit": "per_image",
       "price": "0.009"
      },
      "image_output_1024px_low": {
       "unit": "per_image",
       "price": "0.009"
      },
      "image_output_1024x1536_low": {
       "unit": "per_image",
       "price": "0.013"
      },
      "image_output_1536x1024_low": {
       "unit": "per_image",
       "price": "0.013"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "image_output_tokens": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "gpt-image-1.5"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "openai/gpt-image-1.5"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-image-1.5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "32"
      }
     },
     "provider_model_id": "openai/gpt-image-1.5"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "gpt-image-1.5"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.034"
      }
     },
     "provider_model_id": "openai/gpt-image-1.5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-image-1.5"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "openai/gpt-image-1.5"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-11-25",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text",
     "image"
    ]
   },
   "family": "gpt-image",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "image_generation",
   "deprecated": true,
   "knowledge_cutoff": "2025-12",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-image-1.5",
    "openai/gpt-image-1.5"
   ],
   "intro_i18n": {
    "zh-CN": "GPT Image 1 的增强版本，生成速度提升 4 倍，编辑更精准，文本渲染效果更佳。",
    "zh-TW": "GPT Image 1 的增強版，生成速度提升 4 倍，編輯更精準，文字渲染效果更佳。",
    "ja-JP": "GPT Image 1 の強化版で、4倍の生成速度、より正確な編集、テキスト描画の改善を実現しています。",
    "ru-RU": "Улучшенная модель GPT Image 1 с генерацией в 4 раза быстрее, более точным редактированием и улучшенной визуализацией текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "limit",
     "new": "0",
     "note": "max_input_tokens"
    },
    {
     "date": "2026-07-03",
     "kind": "limit",
     "new": "0",
     "note": "max_output_tokens"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "completion",
     "old": "10",
     "new": "32"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/gpt-image-2",
   "model_name": "gpt-image-2",
   "display_name": "gpt-image-2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.211"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.211"
      },
      "image_output_1024x1536": {
       "unit": "per_image",
       "price": "0.165"
      },
      "image_output_1536x1024": {
       "unit": "per_image",
       "price": "0.165"
      },
      "image_output_hd": {
       "unit": "per_image",
       "price": "0.211"
      },
      "image_output_1024px_hd": {
       "unit": "per_image",
       "price": "0.211"
      },
      "image_output_1024x1536_hd": {
       "unit": "per_image",
       "price": "0.165"
      },
      "image_output_1536x1024_hd": {
       "unit": "per_image",
       "price": "0.165"
      },
      "image_output_medium": {
       "unit": "per_image",
       "price": "0.053"
      },
      "image_output_1024px_medium": {
       "unit": "per_image",
       "price": "0.053"
      },
      "image_output_1024x1536_medium": {
       "unit": "per_image",
       "price": "0.041"
      },
      "image_output_1536x1024_medium": {
       "unit": "per_image",
       "price": "0.041"
      },
      "image_output_low": {
       "unit": "per_image",
       "price": "0.006"
      },
      "image_output_1024px_low": {
       "unit": "per_image",
       "price": "0.006"
      },
      "image_output_1024x1536_low": {
       "unit": "per_image",
       "price": "0.005"
      },
      "image_output_1536x1024_low": {
       "unit": "per_image",
       "price": "0.005"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "image_output_tokens": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "gpt-image-2-2026-04-21",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "image_output": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.211"
      },
      "image_output_1024px": {
       "unit": "per_image",
       "price": "0.211"
      },
      "image_output_1024x1536": {
       "unit": "per_image",
       "price": "0.165"
      },
      "image_output_1536x1024": {
       "unit": "per_image",
       "price": "0.165"
      },
      "image_output_hd": {
       "unit": "per_image",
       "price": "0.211"
      },
      "image_output_1024px_hd": {
       "unit": "per_image",
       "price": "0.211"
      },
      "image_output_1024x1536_hd": {
       "unit": "per_image",
       "price": "0.165"
      },
      "image_output_1536x1024_hd": {
       "unit": "per_image",
       "price": "0.165"
      },
      "image_output_medium": {
       "unit": "per_image",
       "price": "0.053"
      },
      "image_output_1024px_medium": {
       "unit": "per_image",
       "price": "0.053"
      },
      "image_output_1024x1536_medium": {
       "unit": "per_image",
       "price": "0.041"
      },
      "image_output_1536x1024_medium": {
       "unit": "per_image",
       "price": "0.041"
      },
      "image_output_low": {
       "unit": "per_image",
       "price": "0.006"
      },
      "image_output_1024px_low": {
       "unit": "per_image",
       "price": "0.006"
      },
      "image_output_1024x1536_low": {
       "unit": "per_image",
       "price": "0.005"
      },
      "image_output_1536x1024_low": {
       "unit": "per_image",
       "price": "0.005"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "image_output_tokens": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "gpt-image-2-2026-04-21"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai/gpt-image-2"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/gpt-image-2"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.0505"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "32.3232"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.2626"
      }
     },
     "provider_model_id": "openai/gpt-image-2"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.053"
      }
     },
     "provider_model_id": "openai/gpt-image-2"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai/gpt-image-2"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "openai/gpt-image-2"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-04-21",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "gpt-image",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-image-2-2026-04-21",
    "openai/gpt-image-2"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的下一代多模态图像模型，具备原生推理能力，支持最高 4K 分辨率、近乎完美的文字渲染及高保真多语言能力。",
    "zh-TW": "OpenAI 新一代多模態影像模型，具備原生推理能力、最高 4K 解析度、幾乎完美的文字呈現與高保真多語支援。",
    "ja-JP": "OpenAIの次世代マルチモーダル画像モデルで、ネイティブ推論、最大4K解像度、ほぼ完璧なテキストレンダリング、高忠実度の多言語サポートを提供します。",
    "ru-RU": "Следующее поколение мультимодальной модели генерации изображений от OpenAI с нативными возможностями рассуждения, разрешением до 4K, почти идеальным рендерингом текста и высококачественной многоязычной поддержкой."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "audio_input: true→false"
    },
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "video_input: true→false"
    },
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-image-2-image",
   "model_name": "gpt-image-2-image",
   "display_name": "gpt-image-2 (image gen) image tokens",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-image-2 (image gen) image tokens"
    }
   ]
  },
  {
   "slug": "openai/gpt-image-2-text",
   "model_name": "gpt-image-2-text",
   "display_name": "gpt-image-2 (image gen) text tokens",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-image-2 (image gen) text tokens"
    }
   ]
  },
  {
   "slug": "openai/gpt-image-test",
   "model_name": "gpt-image-test",
   "display_name": "gpt-image-test",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-image-test"
    }
   ]
  },
  {
   "slug": "openai/GPT-JT-Moderation-6B",
   "model_name": "GPT-JT-Moderation-6B",
   "display_name": "GPT-JT-Moderation-6B",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "togethercomputer/GPT-JT-Moderation-6B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "togethercomputer/GPT-JT-Moderation-6B"
   ],
   "model_type": "safety_detection",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-JT-Moderation-6B"
    }
   ]
  },
  {
   "slug": "openai/gpt-latest",
   "model_name": "gpt-latest",
   "display_name": "OpenAI: GPT Latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "~openai/gpt-latest"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "~openai/gpt-latest"
    }
   ],
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2026-04-27",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2025-12",
   "family": "gpt",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-latest",
    "~openai/gpt-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI: GPT Latest"
    }
   ]
  },
  {
   "slug": "openai/gpt-mini-latest",
   "model_name": "gpt-mini-latest",
   "display_name": "OpenAI: GPT Mini Latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "~openai/gpt-mini-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "~openai/gpt-mini-latest"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-04-27",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2025-08",
   "family": "gpt-mini",
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "~openai/gpt-mini-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI: GPT Mini Latest"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss",
   "model_name": "gpt-oss",
   "display_name": "gpt-oss",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2283279"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.856229625"
      }
     },
     "provider_model_id": "openai/gpt-oss"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "openai/gpt-oss",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "open_weights": true
   },
   "released_at": "2025-08-05",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-oss"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.85778061",
     "new": "0.856229625"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.228741496",
     "new": "0.2283279"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.8574494775",
     "new": "0.85778061"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.228653194",
     "new": "0.228741496"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.8581060725",
     "new": "0.8574494775"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.228828286",
     "new": "0.228653194"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.85776063",
     "new": "0.8581060725"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.228736168",
     "new": "0.228828286"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.8579984025",
     "new": "0.85776063"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.228799574",
     "new": "0.228736168"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.85357275",
     "new": "0.8579984025"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.2276194",
     "new": "0.228799574"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss-120b",
   "model_name": "gpt-oss-120b",
   "display_name": "gpt-oss-120b",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.039"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai.gpt-oss-120b",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.466667",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     }
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.618"
      }
     },
     "provider_model_id": "openai.gpt-oss-120b",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.500324",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.83"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "cerebras",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     }
    },
    {
     "provider": "cloudferro-sherlock",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.92"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.92"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "workers-ai/@cf/openai/gpt-oss-120b"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "@cf/openai/gpt-oss-120b"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.009"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+litellm+truefoundry+helicone-registry+deepinfra+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.037"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "dinference",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0675"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     }
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.92"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gpt-oss-120b"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.69"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "hyperstack",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.61"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.039"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.117705056"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.470820224"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.072"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.47"
      }
     }
    },
    {
     "provider": "privatemode-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.2"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "fireworks/gpt-oss-120b"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+computeprices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "stackit",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.53"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.76"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "submodel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "hf:openai/gpt-oss-120b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.039"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "deepinfra/openai/gpt-oss-120b"
    },
    {
     "provider": "tinfoil",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+litellm+truefoundry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.039"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.039"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.039"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.039"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.039"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b"
    }
   ],
   "intro": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "released_at": "2025-08-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "knowledge_cutoff": "2024-10",
   "reasoning_config": {
    "mandatory": true,
    "budget_min": 128
   },
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "deep_thinking",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 23.8,
    "coding_index": 30.4,
    "agentic_index": 13.2
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_a",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "@cf/openai/gpt-oss-120b",
    "TEE/gpt-oss-120b",
    "accounts/fireworks/models/gpt-oss-120b",
    "deepinfra/openai/gpt-oss-120b",
    "fireworks/gpt-oss-120b",
    "groq/openai/gpt-oss-120b",
    "hf:openai/gpt-oss-120b",
    "nebius/openai/gpt-oss-120b",
    "openai.gpt-oss-120b",
    "openai/gpt-oss-120b",
    "openai/gpt-oss-120b:exacto",
    "openai/gpt-oss-120b:free",
    "workers-ai/@cf/openai/gpt-oss-120b"
   ],
   "intro_i18n": {
    "zh-CN": "需申请访问。GPT-OSS-120B 是 OpenAI 开源的大型语言模型，具备强大的文本生成能力。",
    "zh-TW": "需申請使用。GPT-OSS-120B 是 OpenAI 推出的開源大型語言模型，具備強大的文字生成能力。",
    "ja-JP": "申請が必要です。GPT-OSS-120B は、OpenAI によるオープンソースの大規模言語モデルで、強力なテキスト生成能力を備えています。",
    "ru-RU": "Требуется заявка на доступ. GPT-OSS-120B — это крупная open-source языковая модель от OpenAI с мощными возможностями генерации текста."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.089",
     "new": "0.09"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.68",
     "new": "0.61"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.178",
     "new": "0.18"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471045376",
     "new": "0.470820224"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.117761344",
     "new": "0.117705056"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "prompt",
     "old": "0.039",
     "new": "0.037"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471372608",
     "new": "0.471045376"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.117843152",
     "new": "0.117761344"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "wandb",
     "charge": "completion",
     "old": "0.6",
     "new": "0.14"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "wandb",
     "charge": "prompt",
     "old": "0.15",
     "new": "0.04"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471869504",
     "new": "0.471372608"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.117967376",
     "new": "0.117843152"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.085",
     "new": "0.089"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.64",
     "new": "0.68"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.17",
     "new": "0.178"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.471965856",
     "new": "0.471869504"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.117991464",
     "new": "0.117967376"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "stackit",
     "charge": "completion",
     "old": "0.71",
     "new": "0.76"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "stackit",
     "charge": "prompt",
     "old": "0.49",
     "new": "0.53"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.089",
     "new": "0.085"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss-120b-cs",
   "model_name": "gpt-oss-120b-cs",
   "display_name": "GPT-OSS-120B-CS",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "cerebras/gpt-oss-120b-cs"
    }
   ],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "cerebras/gpt-oss-120b-cs"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-OSS-120B-CS"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss-120b-fast",
   "model_name": "gpt-oss-120b-fast",
   "display_name": "gpt-oss-120b-fast",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b-fast"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-06-10",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 8000,
   "max_output_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-oss-120b-fast"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss-120b-fast"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss-120b-maas",
   "model_name": "gpt-oss-120b-maas",
   "display_name": "GPT OSS 120B",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b-maas",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b-maas",
     "region": "global",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b-maas",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-oss-120b-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT OSS 120B"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss-120b-TEE",
   "model_name": "gpt-oss-120b-TEE",
   "display_name": "gpt oss 120b TEE",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-oss-120b-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt oss 120b TEE"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss-120b-Turbo",
   "model_name": "gpt-oss-120b-Turbo",
   "display_name": "openai/gpt-oss-120b-Turbo",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai/gpt-oss-120b-Turbo"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "deepinfra/openai/gpt-oss-120b-Turbo"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "reasoning": true
   },
   "max_output_tokens": 131072,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "deepinfra/openai/gpt-oss-120b-Turbo",
    "openai/gpt-oss-120b-Turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/gpt-oss-120b-Turbo"
    }
   ]
  },
  {
   "slug": "openai/GPT-OSS-20B",
   "model_name": "GPT-OSS-20B",
   "display_name": "gpt-oss-20b",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.428571",
        "completion": "0.333333"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0721"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.309"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.500693",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "ap-southeast-3"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "eu-central-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "eu-north-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.47"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "openai.gpt-oss-20b",
     "region": "us-west-2"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.045"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "openai/chat-completion/models/gpt-oss-20b"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "workers-ai/@cf/openai/gpt-oss-20b"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "@cf/openai/gpt-oss-20b"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.027"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.124"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.007"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+litellm+truefoundry+deepinfra+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.007"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gpt-oss-20b"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.049999999999999996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19999999999999998"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.235294"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.043"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.184"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0215"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "lmstudio",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "neon",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "gpt-oss-20b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035"
      }
     },
     "provider_model_id": "fireworks/gpt-oss-20b"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "stackit",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.037"
      }
     },
     "provider_model_id": "deepinfra/openai/gpt-oss-20b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+litellm+truefoundry+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b"
    }
   ],
   "intro": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass.",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "released_at": "2025-08-06",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "knowledge_cutoff": "2024-10",
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "deep_thinking",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 14.9,
    "coding_index": 20.7,
    "agentic_index": 3.1
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "@cf/openai/gpt-oss-20b",
    "TEE/gpt-oss-20b",
    "accounts/fireworks/models/gpt-oss-20b",
    "deepinfra/openai/gpt-oss-20b",
    "fireworks/gpt-oss-20b",
    "gpt-oss-20b",
    "groq/openai/gpt-oss-20b",
    "openai.gpt-oss-20b",
    "openai/chat-completion/models/gpt-oss-20b",
    "openai/gpt-oss-20b",
    "openai/gpt-oss-20b:free",
    "workers-ai/@cf/openai/gpt-oss-20b"
   ],
   "intro_i18n": {
    "zh-CN": "需申请访问。GPT-OSS-20B 是 OpenAI 开源的中型语言模型，具备高效的文本生成能力。",
    "zh-TW": "需申請使用。GPT-OSS-20B 是 OpenAI 推出的中型開源語言模型，具備高效的文字生成能力。",
    "ja-JP": "申請が必要です。GPT-OSS-20B は、OpenAI による中規模のオープンソース言語モデルで、効率的なテキスト生成が可能です。",
    "ru-RU": "Требуется заявка на доступ. GPT-OSS-20B — это средняя open-source языковая модель от OpenAI с эффективной генерацией текста."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.0225",
     "new": "0.0215"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.045",
     "new": "0.043"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.194",
     "new": "0.184"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "wandb",
     "charge": "completion",
     "old": "0.2",
     "new": "0.13"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "wandb",
     "charge": "prompt",
     "old": "0.05",
     "new": "0.03"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.0265",
     "new": "0.0225"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.196",
     "new": "0.194"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.053",
     "new": "0.045"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.0245",
     "new": "0.0265"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.204",
     "new": "0.196"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.049",
     "new": "0.053"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.0235",
     "new": "0.0245"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.198",
     "new": "0.204"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.047",
     "new": "0.049"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.0255",
     "new": "0.0235"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "0.206",
     "new": "0.198"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.051",
     "new": "0.047"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss-20b"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss-20b-maas",
   "model_name": "gpt-oss-20b-maas",
   "display_name": "GPT OSS 20B",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b-maas"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.007"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/gpt-oss-20b-maas",
     "region": "us-central1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/gpt-oss-20b-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT OSS 20B"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss-safeguard-120b",
   "model_name": "gpt-oss-safeguard-120b",
   "display_name": "gpt-oss-safeguard-120b",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.618"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.93"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.618"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.93"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-120b",
     "region": "us-west-2"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.161"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.626"
      }
     }
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gpt-oss-safeguard-120b"
    },
    {
     "provider": "tinfoil",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows",
   "released_at": "2025-10-29",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 131000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "safety_detection",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/gpt-oss-safeguard-120b",
    "openai.gpt-oss-safeguard-120b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss-safeguard-120b"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss-safeguard-20b",
   "model_name": "gpt-oss-safeguard-20b",
   "display_name": "gpt-oss-safeguard-20b",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.037"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "ap-northeast-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "ap-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0721"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.206"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "eu-south-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "eu-west-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "eu-west-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "sa-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "us-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "ap-northeast-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "ap-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0721"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.206"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "ap-southeast-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "eu-south-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "eu-west-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "eu-west-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "sa-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "us-east-1"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "us-east-2"
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openai.gpt-oss-safeguard-20b",
     "region": "us-west-2"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/gpt-oss-safeguard-20b"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.037"
      }
     },
     "provider_model_id": "openai/gpt-oss-safeguard-20b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.037"
      }
     },
     "provider_model_id": "openai/gpt-oss-safeguard-20b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "openai/gpt-oss-safeguard-20b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0375"
      }
     },
     "provider_model_id": "openai/gpt-oss-safeguard-20b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.037"
      }
     },
     "provider_model_id": "groq/openai/gpt-oss-safeguard-20b"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.037"
      }
     },
     "provider_model_id": "openai/gpt-oss-safeguard-20b"
    }
   ],
   "intro": "gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks.",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "web_search": true,
    "stream": true
   },
   "released_at": "2025-10-29",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "status": "beta",
   "model_type": "safety_detection",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/gpt-oss-safeguard-20b",
    "groq/openai/gpt-oss-safeguard-20b",
    "openai.gpt-oss-safeguard-20b",
    "openai/gpt-oss-safeguard-20b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss-safeguard-20b"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss:120b",
   "model_name": "gpt-oss:120b",
   "display_name": "gpt-oss:120b",
   "vendor": "openai",
   "pricing": [],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GPT-OSS 120B 是 OpenAI 推出的大型开源语言模型，采用 MXFP4 量化技术，定位为旗舰模型。需多 GPU 或高端工作站环境支持，在复杂推理、代码生成和多语言处理方面表现出色，具备先进的函数调用与工具集成能力。",
    "zh-TW": "GPT-OSS 120B 是 OpenAI 的大型開源 LLM，採用 MXFP4 量化，定位為旗艦模型。需多 GPU 或高階工作站環境，於複雜推理、程式碼生成與多語言處理方面表現優異，支援進階函式呼叫與工具整合。",
    "ja-JP": "GPT-OSS 120B は、OpenAI による MXFP4 量子化を用いた大規模オープンソース LLM で、複雑な推論、コード生成、多言語処理に優れ、先進的な関数呼び出しやツール統合にも対応します。マルチ GPU や高性能ワークステーション環境が必要です。",
    "ru-RU": "GPT-OSS 120B — крупная open-source LLM от OpenAI с квантованием MXFP4, позиционируемая как флагманская модель. Требует многопроцессорной или высокопроизводительной рабочей станции. Обеспечивает отличные результаты в сложных рассуждениях, генерации кода и многоязычной обработке, с поддержкой вызова функций и интеграции инструментов."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss:120b"
    }
   ]
  },
  {
   "slug": "openai/gpt-oss:20b",
   "model_name": "gpt-oss:20b",
   "display_name": "gpt-oss:20b",
   "vendor": "openai",
   "pricing": [],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GPT-OSS 20B 是 OpenAI 推出的开源语言模型，采用 MXFP4 量化技术，适用于高端消费级 GPU 或 Apple Silicon Mac。擅长对话生成、编程与推理任务，支持函数调用与工具使用。",
    "zh-TW": "GPT-OSS 20B 是 OpenAI 的開源 LLM，採用 MXFP4 量化，適用於高階消費級 GPU 或 Apple Silicon Mac。於對話生成、編碼與推理任務中表現良好，支援函式呼叫與工具使用。",
    "ja-JP": "GPT-OSS 20B は、OpenAI による MXFP4 量子化を用いたオープンソース LLM で、高性能なコンシューマー GPU や Apple Silicon Mac に適しており、対話生成、コーディング、推論タスクに強く、関数呼び出しやツール使用にも対応します。",
    "ru-RU": "GPT-OSS 20B — open-source LLM от OpenAI с квантованием MXFP4, подходящая для мощных потребительских GPU или Apple Silicon. Эффективна в генерации диалогов, программировании и логических задачах, поддерживает вызов функций и использование инструментов."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss:20b"
    }
   ]
  },
  {
   "slug": "openai/gpt-realtime",
   "model_name": "gpt-realtime",
   "display_name": "gpt-realtime",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000005"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-realtime-2025-08-28"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "21.15"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+computeprices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000005"
      },
      "cache_creation_input_audio": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "64"
      }
     },
     "provider_model_id": "gpt-realtime-2025-08-28"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      }
     },
     "provider_model_id": "openai/gpt-realtime"
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "model_type": "realtime_omni",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text",
     "audio",
     "image"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "released_at": "2025-08-28",
   "knowledge_cutoff": "2023-10",
   "family": "GPT Realtime",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-realtime-2025-08-28",
    "openai/gpt-realtime"
   ],
   "intro_i18n": {
    "zh-CN": "通用实时模型，支持实时文本与音频输入/输出，并支持图像输入。",
    "zh-TW": "通用即時模型，支援即時文字與音訊輸入/輸出，並支援圖片輸入。",
    "ja-JP": "リアルタイムのテキスト・音声入出力、画像入力に対応した汎用リアルタイムモデルです。",
    "ru-RU": "Универсальная модель реального времени с поддержкой ввода/вывода текста и аудио, а также ввода изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "cache_read",
     "old": "0.4",
     "new": "4"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "completion",
     "old": "24",
     "new": "16"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-realtime-1.5",
   "model_name": "gpt-realtime-1.5",
   "display_name": "gpt-realtime-1.5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000005"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "42.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.05"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000005"
      },
      "cache_creation_input_audio": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "64"
      }
     },
     "provider_model_id": "gpt-realtime-1.5-2026-02-23"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      }
     },
     "provider_model_id": "openai/gpt-realtime-1.5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-realtime-1.5"
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "model_type": "realtime_omni",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text",
     "audio",
     "image"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "released_at": "2026-02-19",
   "knowledge_cutoff": "2024-09",
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "family": "gpt",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-realtime-1.5-2026-02-23",
    "openai/gpt-realtime-1.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "azure",
     "charge": "cache_read",
     "old": "16",
     "new": "4"
    }
   ]
  },
  {
   "slug": "openai/gpt-realtime-2",
   "model_name": "gpt-realtime-2",
   "display_name": "gpt-realtime-2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000005"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "image_input": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "gpt-realtime-2-2026-05-06"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-realtime-2"
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "model_type": "realtime_omni",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text",
     "audio",
     "image"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "released_at": "2026-05-05",
   "knowledge_cutoff": "2024-09",
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "family": "gpt",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-realtime-2-2026-05-06",
    "openai/gpt-realtime-2"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-realtime-2.1",
   "model_name": "gpt-realtime-2.1",
   "display_name": "GPT-Realtime-2.1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "32"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "24"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "audio",
     "image"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "model_type": "realtime_omni",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "audio_input": true,
    "audio_output": true,
    "pdf_input": true
   },
   "released_at": "2026-06-23",
   "knowledge_cutoff": "2024-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "GPT-Realtime-2.1"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "openai",
     "charge": "cache_read",
     "old": "0.5",
     "new": "0.4"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "openai",
     "charge": "completion",
     "old": "64",
     "new": "24"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "openai",
     "charge": "prompt",
     "old": "5",
     "new": "4"
    }
   ]
  },
  {
   "slug": "openai/gpt-realtime-2.1-mini",
   "model_name": "gpt-realtime-2.1-mini",
   "display_name": "GPT-Realtime-2.1 mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "audio",
     "image"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "model_type": "realtime_omni",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "audio_input": true,
    "audio_output": true,
    "pdf_input": true
   },
   "released_at": "2026-06-23",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "GPT-Realtime-2.1 mini"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "openai",
     "charge": "cache_read",
     "old": "0.08",
     "new": "0.06"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "openai",
     "charge": "completion",
     "old": "20",
     "new": "2.4"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "openai",
     "charge": "prompt",
     "old": "0.8",
     "new": "0.6"
    }
   ]
  },
  {
   "slug": "openai/gpt-realtime-mini",
   "model_name": "gpt-realtime-mini",
   "display_name": "gpt-realtime-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0000008"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "audio_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "image_cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "gpt-realtime-mini-2025-10-06"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0000008"
      },
      "cache_read_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_creation_input_audio": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "gpt-realtime-mini-2025-10-06"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "openai/gpt-realtime-mini"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/gpt-realtime-mini"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "model_type": "realtime_omni",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "audio_output": true,
    "pdf_input": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text",
     "audio",
     "image"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "deprecated": true,
   "released_at": "2025-10-03",
   "knowledge_cutoff": "2023-10",
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "family": "gpt",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "gpt-realtime-mini-2025-10-06",
    "gpt-realtime-mini-2025-12-15",
    "openai/gpt-realtime-mini"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "openai/gpt-realtime-translate",
   "model_name": "gpt-realtime-translate",
   "display_name": "gpt-realtime-translate",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0005666666666666667"
      }
     }
    }
   ],
   "max_input_tokens": 16000,
   "max_output_tokens": 2000,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "audio",
     "text"
    ]
   },
   "model_type": "realtime_speech_translation",
   "capabilities": {
    "audio_input": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-realtime-translate"
    }
   ]
  },
  {
   "slug": "openai/gpt-realtime-whisper",
   "model_name": "gpt-realtime-whisper",
   "display_name": "gpt-realtime-whisper",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0002833333333333333"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0002833333333333333"
      }
     }
    }
   ],
   "docs_url": "https://platform.openai.com/docs/models/gpt-realtime-whisper",
   "model_type": "realtime_speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "max_input_tokens": 16000,
   "max_output_tokens": 2000,
   "modalities": {
    "input": [
     "audio",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "limit",
     "new": "16000",
     "note": "max_input_tokens"
    },
    {
     "date": "2026-07-02",
     "kind": "limit",
     "new": "2000",
     "note": "max_output_tokens"
    }
   ]
  },
  {
   "slug": "openai/gt-4.1",
   "model_name": "gt-4.1",
   "display_name": "OpenAI GPT-4.1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gt-4.1"
    }
   ],
   "intro": "GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token context window and outperforms GPT-4o and GPT-4.5 across coding (54.6% SWE-bench Verified), instruction compliance (87.4% IFEval), and multimodal understanding benchmarks. It is tuned for precise code diffs, agent reliability, and high recall in large document contexts, making it ideal for agents, IDE tooling, and enterprise knowledge retrieval.",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "pa/gt-4.1"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI GPT-4.1"
    }
   ]
  },
  {
   "slug": "openai/gt-4.1-m",
   "model_name": "gt-4.1-m",
   "display_name": "OpenAI GPT-4.1 Mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gt-4.1-m"
    }
   ],
   "intro": "GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard instruction evals, 35.8% on MultiChallenge, and 84.1% on IFEval. Mini also shows strong coding ability (e.g., 31.6% on Aider's polyglot diff benchmark) and vision understanding, making it suitable for interactive applications with tight performance constraints.",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "pa/gt-4.1-m"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI GPT-4.1 Mini"
    }
   ]
  },
  {
   "slug": "openai/gt-4.1-n",
   "model_name": "gt-4.1-n",
   "display_name": "OpenAI GPT-4.1 Nano",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gt-4.1-n"
    }
   ],
   "intro": "For tasks that demand low latency, GPT-4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT-4o mini. It's ideal for tasks like classification or autocompletion.",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "pa/gt-4.1-n"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI GPT-4.1 Nano"
    }
   ]
  },
  {
   "slug": "openai/gt-4p",
   "model_name": "gt-4p",
   "display_name": "OpenAI GPT-4o",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gt-4p"
    }
   ],
   "intro": "GPT-4o (\"o\" for \"omni\") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of GPT-4 Turbo while being twice as fast and 50% more cost-effective. GPT-4o also offers improved performance in processing non-English languages and enhanced visual capabilities.\n\nFor benchmarking against other models, it was briefly called [\"im-also-a-good-gpt2-chatbot\"](https://twitter.com/LiamFedus/status/1790064963966370209)\n\n#multimodal",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "pa/gt-4p"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI GPT-4o"
    }
   ]
  },
  {
   "slug": "openai/gt-4p-m",
   "model_name": "gt-4p-m",
   "display_name": "OpenAI GPT-4o-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/gt-4p-m"
    }
   ],
   "intro": "GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.\n\nAs their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.\n\nGPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences common leaderboards.\n\nCheck out the launch announcement to learn more.\n\n#multimodal",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "presence_penalty",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "pa/gt-4p-m"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI GPT-4o-mini"
    }
   ]
  },
  {
   "slug": "openai/kb-whisper-large",
   "model_name": "kb-whisper-large",
   "display_name": "KB Whisper",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "KBLab/kb-whisper-large"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0023"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0023"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "KBLab/kb-whisper-large"
    }
   ],
   "intro": "Speech transcription model for accurate audio-to-text and captioning workflows",
   "released_at": "2024-10-01",
   "max_input_tokens": 448,
   "max_output_tokens": 448,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "whisper",
   "capabilities": {
    "audio_input": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2025-04",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "KBLab/kb-whisper-large"
   ],
   "model_type": "speech_recognition",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "KB Whisper"
    }
   ]
  },
  {
   "slug": "openai/o1",
   "model_name": "o1",
   "display_name": "o1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "o1-2024-12-17",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "o1-2024-12-17"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.14"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "o1-2024-12-17"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "github",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "57"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.993999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "59.993"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "54"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "openai/o1"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "openai/o1"
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2024-12-05",
   "knowledge_cutoff": "2023-09",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": null,
    "coding_index": 39.7,
    "agentic_index": null
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "o1-2024-12-17",
    "openai/o1"
   ],
   "intro_i18n": {
    "zh-CN": "o1 是 OpenAI 推出的新型推理模型，支持文本+图像输入和文本输出，适用于需要广泛知识的复杂任务。具备 200K 上下文窗口，知识截止于 2023 年 10 月。",
    "zh-TW": "o1 是 OpenAI 的新一代推理模型，支援文字與圖像輸入、文字輸出，適用於需要廣泛知識的複雜任務。具備 200K 上下文視窗，知識截止於 2023 年 10 月。",
    "ja-JP": "o1はOpenAIの新しい推論モデルで、テキスト＋画像入力とテキスト出力に対応し、幅広い知識を必要とする複雑なタスクに適しています。200Kのコンテキストウィンドウと2023年10月の知識カットオフを持ちます。",
    "ru-RU": "o1 — новая модель рассуждения от OpenAI с вводом текст+изображение и текстовым выводом, подходящая для сложных задач, требующих обширных знаний. Имеет контекстное окно 200K и отсечку знаний на октябрь 2023 года."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/o1-mini",
   "model_name": "o1-mini",
   "display_name": "o1-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices+truefoundry+portkey+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "o1-mini-2024-09-12",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "o1-mini-2024-09-12"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "o1-mini-2024-09-12"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.605"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      }
     },
     "provider_model_id": "o1-mini-2024-09-12",
     "region": "datazone_eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.605"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      }
     },
     "provider_model_id": "o1-mini-2024-09-12",
     "region": "datazone_us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     }
    },
    {
     "provider": "github",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "openai/o1-mini"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/o1-mini"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.045"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.18"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o1-mini"
    }
   ],
   "intro": "O1 Mini is a model that offers a balance between cost and performance.",
   "max_input_tokens": 128000,
   "capabilities": {
    "prompt_caching": true,
    "vision": true,
    "pdf_input": true,
    "function_calling": true,
    "reasoning": true,
    "parallel_function_calling": true,
    "stream": true,
    "structured_output": true
   },
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "image",
     "pdf"
    ],
    "output": []
   },
   "model_type": "deep_thinking",
   "released_at": "2024-09-12",
   "knowledge_cutoff": "2023-10",
   "family": "o-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "o1-mini-2024-09-12",
    "openai/o1-mini",
    "openai/o1-mini-2024-09-12"
   ],
   "intro_i18n": {
    "zh-CN": "o1-mini 是一款快速、经济高效的推理模型，专为编码、数学和科学设计。支持 128K 上下文，知识截止日期为 2023 年 10 月。",
    "zh-TW": "o1-mini 是一款快速且具成本效益的推理模型，專為編程、數學和科學設計。擁有 128K 上下文及 2023 年 10 月的知識截止。",
    "ja-JP": "o1-miniは、コーディング、数学、科学向けに設計された高速でコスト効率の高い推論モデルです。128Kのコンテキストと2023年10月の知識カットオフを持ちます。",
    "ru-RU": "o1-mini — это быстрая, экономичная модель рассуждений, разработанная для программирования, математики и науки. Она имеет контекст 128K и отсечку знаний на октябрь 2023 года."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o1-mini"
    }
   ]
  },
  {
   "slug": "openai/o1-preview",
   "model_name": "o1-preview",
   "display_name": "o1 and o1-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey+llm-prices-www",
     "charges": {
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "o1-preview-2024-09-12",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "o1-preview-2024-09-12"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "o1-preview-2024-09-12"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "66"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "8.25"
      }
     }
    },
    {
     "provider": "github",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai/o1-preview"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/o1-preview"
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.993999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "59.993"
      }
     },
     "provider_model_id": "openai/o1-preview"
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2024-09-12",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "o1-preview-2024-09-12",
    "openai/o1-preview"
   ],
   "intro_i18n": {
    "zh-CN": "o1 是 OpenAI 推出的新推理模型，适用于需要广泛知识的复杂任务。支持 128K 上下文，知识截止日期为 2023 年 10 月。",
    "zh-TW": "o1 是 OpenAI 的新推理模型，適用於需要廣泛知識的複雜任務。擁有 128K 上下文及 2023 年 10 月的知識截止。",
    "ja-JP": "o1は、広範な知識を必要とする複雑なタスク向けのOpenAIの新しい推論モデルです。128Kのコンテキストと2023年10月の知識カットオフを持ちます。",
    "ru-RU": "o1 — это новая модель рассуждений от OpenAI для сложных задач, требующих обширных знаний. Она имеет контекст 128K и отсечку знаний на октябрь 2023 года."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o1 and o1-preview"
    }
   ]
  },
  {
   "slug": "openai/o1-pro",
   "model_name": "o1-pro",
   "display_name": "o1-pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "600"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "o1-pro-2025-03-19",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "170"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "680"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "600"
      }
     },
     "provider_model_id": "o1-pro-2025-03-19"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "600"
      }
     },
     "provider_model_id": "openai/o1-pro"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "600"
      }
     },
     "provider_model_id": "openai/o1-pro"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "600"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o1-pro"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "140"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "540"
      }
     },
     "provider_model_id": "openai/o1-pro"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "150"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "600"
      }
     }
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2025-03-19",
   "knowledge_cutoff": "2023-09",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o-pro",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "o1-pro-2025-03-19",
    "openai/o1-pro"
   ],
   "intro_i18n": {
    "zh-CN": "o1 系列通过强化学习训练，具备先思考后作答的能力，能处理复杂推理任务。o1-pro 使用更多计算资源，提供更深入的思考和更高质量的回答。",
    "zh-TW": "o1 系列透過強化學習訓練，具備先思考再作答的能力，能處理複雜推理任務。o1-pro 使用更多運算資源以進行更深入思考，並穩定提供更高品質的回答。",
    "ja-JP": "o1シリーズは、回答前に思考するよう強化学習で訓練され、複雑な推論を処理できます。o1-proはより多くの計算資源を使用し、より深い思考と一貫して高品質な回答を提供します。",
    "ru-RU": "Серия o1 обучена с использованием обучения с подкреплением для предварительного обдумывания ответов и решения сложных задач. o1-pro использует больше вычислений для более глубокого мышления и стабильно высокого качества ответов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/o1:high",
   "model_name": "o1:high",
   "display_name": "openai/o1:high",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "openai/o1:high"
    }
   ],
   "released_at": "2024-12-17",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o1:high"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o1:high"
    }
   ]
  },
  {
   "slug": "openai/o1:low",
   "model_name": "o1:low",
   "display_name": "openai/o1:low",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "openai/o1:low"
    }
   ],
   "released_at": "2024-12-17",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o1:low"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o1:low"
    }
   ]
  },
  {
   "slug": "openai/o1:medium",
   "model_name": "o1:medium",
   "display_name": "openai/o1:medium",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     },
     "provider_model_id": "openai/o1:medium"
    }
   ],
   "released_at": "2024-12-17",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o1:medium"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o1:medium"
    }
   ]
  },
  {
   "slug": "openai/o3",
   "model_name": "o3",
   "display_name": "o3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "o3-2025-04-16",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "1.75",
        "completion": "1.75",
        "cache_read": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "o3-2025-04-16"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.8"
      }
     },
     "provider_model_id": "o3-2025-04-16",
     "region": "datazone_us"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "github",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/o3"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o3",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75",
        "cache_read": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/o3"
    }
   ],
   "intro": "Deliberate o-series reasoner for hard math, coding, and multi-step analysis",
   "released_at": "2025-04-16",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses",
     "openai-compatible"
    ]
   },
   "deprecated": true,
   "deprecation_date": "2026-04-16",
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "o3-2025-04-16",
    "openai/o3"
   ],
   "intro_i18n": {
    "zh-CN": "o3 是 OpenAI 推出的新型推理模型，支持文本+图像输入和文本输出，适用于需要广泛知识的复杂任务。",
    "zh-TW": "o3 是 OpenAI 的新一代推理模型，支援文字與圖像輸入、文字輸出，適用於需要廣泛知識的複雜任務。",
    "ja-JP": "o3はOpenAIの新しい推論モデルで、テキスト＋画像入力とテキスト出力に対応し、幅広い知識を必要とする複雑なタスクに適しています。",
    "ru-RU": "o3 — новая модель рассуждения от OpenAI с вводом текст+изображение и текстовым выводом для сложных задач, требующих обширных знаний."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/o3-deep-research",
   "model_name": "o3-deep-research",
   "display_name": "o3-deep-research",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "o3-deep-research-2025-06-26",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "34.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "136.89"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+computeprices+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "o3-deep-research-2025-06-26"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "openai/o3-deep-research"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.992"
      }
     },
     "provider_model_id": "openai/o3-deep-research"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o3-deep-research"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "36"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "openai/o3-deep-research"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o3-deep-research"
    }
   ],
   "intro": "Research model for long-horizon investigation, synthesis, and analytical reports",
   "released_at": "2024-06-26",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "o3-deep-research-2025-06-26",
    "openai/o3-deep-research"
   ],
   "intro_i18n": {
    "zh-CN": "o3-deep-research 是我们最先进的深度研究模型，适用于复杂的多步骤任务。它可以通过 MCP 连接器访问您的数据并进行网页搜索。",
    "zh-TW": "o3-deep-research 是我們最先進的深度研究模型，適用於複雜的多步任務。可透過 MCP 連接器搜尋網路並存取您的資料。",
    "ja-JP": "o3-deep-researchは、複雑な多段階タスク向けの最先端リサーチモデルで、ウェブ検索やMCPコネクタを通じたデータアクセスが可能です。",
    "ru-RU": "o3-deep-research — наша самая продвинутая модель для глубоких исследований и многошаговых задач. Может искать в интернете и получать доступ к вашим данным через MCP-коннекторы."
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "completion",
     "old": "93.33",
     "new": "136.89"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "prompt",
     "old": "23.34",
     "new": "34.23"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/o3-deep-research-2025-06-26-ev3",
   "model_name": "o3-deep-research-2025-06-26-ev3",
   "display_name": "o3-deep-research-2025-06-26-ev3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     }
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o3-deep-research-2025-06-26-ev3"
    }
   ]
  },
  {
   "slug": "openai/o3-global",
   "model_name": "o3-global",
   "display_name": "o3-global",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o3-global"
    }
   ]
  },
  {
   "slug": "openai/o3-mini",
   "model_name": "o3-mini",
   "display_name": "o3-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "o3-mini-2025-01-31",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.91"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.64"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.44"
      }
     },
     "provider_model_id": "o3-mini-2025-01-31"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "o3-mini-2025-01-31"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.605"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      }
     },
     "provider_model_id": "o3-mini-2025-01-31",
     "region": "datazone_eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.605"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      }
     },
     "provider_model_id": "o3-mini-2025-01-31",
     "region": "datazone_us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "github",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai-responses/o3-mini"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini"
    }
   ],
   "intro": "Smaller o-series reasoner for economical coding, math, and planning tasks",
   "released_at": "2024-12-20",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "o3-mini-2025-01-31",
    "openai-responses/o3-mini",
    "openai/o3-mini"
   ],
   "intro_i18n": {
    "zh-CN": "o3-mini 是我们最新的小型推理模型，在保持与 o1-mini 相同成本和延迟的前提下，提供更高的智能表现。",
    "zh-TW": "o3-mini 是我們最新的小型推理模型，在維持與 o1-mini 相同成本與延遲的前提下，提供更高智慧表現。",
    "ja-JP": "o3-miniは、o1-miniと同等のコストとレイテンシで、より高い知能を提供する最新の小型推論モデルです。",
    "ru-RU": "o3-mini — наша последняя компактная модель рассуждения, обеспечивающая более высокий интеллект при тех же затратах и задержке, что и o1-mini."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/o3-mini-alpha-2024-12-17",
   "model_name": "o3-mini-alpha-2024-12-17",
   "display_name": "o3-mini-alpha-2024-12-17",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.605"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      }
     },
     "region": "datazone_eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.605"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      }
     },
     "region": "datazone_us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o3-mini-alpha-2024-12-17"
    }
   ]
  },
  {
   "slug": "openai/o3-mini-global",
   "model_name": "o3-mini-global",
   "display_name": "o3-mini-global",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o3-mini-global"
    }
   ]
  },
  {
   "slug": "openai/o3-mini-high",
   "model_name": "o3-mini-high",
   "display_name": "o3-mini-high",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini-high"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini-high"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.588"
      }
     },
     "provider_model_id": "openai/o3-mini-high"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+truefoundry+openrouter+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o3-mini-high"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "openai/o3-mini-high"
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2025-01-31",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "knowledge_cutoff": "2023-10",
   "model_type": "deep_thinking",
   "deprecated": true,
   "benchmarks": {
    "intelligence_index": 15.6,
    "coding_index": 16.3,
    "agentic_index": 1.7
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o3-mini-high"
   ],
   "intro_i18n": {
    "zh-CN": "o3-mini（高推理）在保持与 o1-mini 相同成本和延迟的前提下，提供更高的智能表现。",
    "zh-TW": "o3-mini（高推理）在維持與 o1-mini 相同成本與延遲的前提下，提供更高智慧表現。",
    "ja-JP": "o3-mini（高推論）は、o1-miniと同等のコストと遅延でより高い知性を提供します。",
    "ru-RU": "o3-mini (высокий уровень рассуждения) обеспечивает более высокий интеллект при тех же затратах и задержке, что и o1-mini."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o3-mini-high"
    }
   ]
  },
  {
   "slug": "openai/o3-mini-low",
   "model_name": "o3-mini-low",
   "display_name": "OpenAI o3-mini (Low)",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.992"
      }
     },
     "provider_model_id": "openai/o3-mini-low"
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2025-01-31",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o-mini",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o3-mini-low"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI o3-mini (Low)"
    }
   ]
  },
  {
   "slug": "openai/o3-mini:high",
   "model_name": "o3-mini:high",
   "display_name": "openai/o3-mini:high",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini:high"
    }
   ],
   "released_at": "2025-01-31",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o3-mini:high"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o3-mini:high"
    }
   ]
  },
  {
   "slug": "openai/o3-mini:low",
   "model_name": "o3-mini:low",
   "display_name": "openai/o3-mini:low",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini:low"
    }
   ],
   "released_at": "2025-01-31",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o3-mini:low"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o3-mini:low"
    }
   ]
  },
  {
   "slug": "openai/o3-mini:medium",
   "model_name": "o3-mini:medium",
   "display_name": "openai/o3-mini:medium",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     },
     "provider_model_id": "openai/o3-mini:medium"
    }
   ],
   "released_at": "2025-01-31",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o3-mini:medium"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o3-mini:medium"
    }
   ]
  },
  {
   "slug": "openai/o3-pro",
   "model_name": "o3-pro",
   "display_name": "o3-pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "o3-pro-2025-06-10",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "o3-pro-2025-06-10",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     },
     "provider_model_id": "openai/o3-pro"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     },
     "provider_model_id": "openai/o3-pro"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.992"
      }
     },
     "provider_model_id": "openai/o3-pro-2025-06-10"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o3-pro"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "72"
      }
     },
     "provider_model_id": "openai/o3-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     },
     "provider_model_id": "openai-responses/o3-pro"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o3-pro"
    }
   ],
   "intro": "High-effort o3 tier for difficult technical reasoning and careful answers",
   "released_at": "2025-06-10",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o-pro",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-responses"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "o3-pro-2025-06-10",
    "openai-responses/o3-pro",
    "openai/o3-pro",
    "openai/o3-pro-2025-06-10"
   ],
   "intro_i18n": {
    "zh-CN": "o3 Pro 是 OpenAI 推出的新一代推理模型，支持文本+图像输入和文本输出，适用于需要广泛知识的复杂任务。",
    "zh-TW": "o3 Pro 是 OpenAI 的新一代推理模型，支援文字與圖像輸入、文字輸出，適用於需要廣泛知識的複雜任務。",
    "ja-JP": "o3 Proは、OpenAIの新しい推論モデルで、テキスト＋画像入力とテキスト出力に対応し、幅広い知識を必要とする複雑なタスクに適しています。",
    "ru-RU": "o3 Pro — новая модель рассуждения от OpenAI с вводом текст+изображение и текстовым выводом для сложных задач, требующих обширных знаний."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/o3-pro-global",
   "model_name": "o3-pro-global",
   "display_name": "o3-pro-global",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o3-pro-global"
    }
   ]
  },
  {
   "slug": "openai/o3:flex",
   "model_name": "o3:flex",
   "display_name": "openai/o3:flex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/o3:flex"
    }
   ],
   "released_at": "2025-04-16",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o3:flex"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o3:flex"
    }
   ]
  },
  {
   "slug": "openai/o4-mini",
   "model_name": "o4-mini",
   "display_name": "o4-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "o4-mini-2025-04-16",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "1.818182",
        "completion": "1.818182",
        "cache_read": "1.818182"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "web_search": "1",
        "file_search_call": "1",
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.501818"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "routing_units": {
       "unit": "per_request",
       "price": "0.00000014"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "o4-mini-2025-04-16",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.303"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      }
     },
     "region": "datazone_eu",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      }
     },
     "provider_model_id": "o4-mini-2025-04-16",
     "region": "datazone_us",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     }
    },
    {
     "provider": "azureai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "github",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/o4-mini"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.99"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o4-mini",
     "tracks": [
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.818182",
        "completion": "1.818182",
        "cache_read": "1.818182"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "cache_read": "0.501818"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai/o4-mini"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+lobehub-modelbank+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "openai/o4-mini"
    }
   ],
   "intro": "Fast o-series model for compact reasoning, coding, and tool use",
   "released_at": "2025-04-16",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "o4-mini-2025-04-16",
    "openai-responses/o4-mini",
    "openai/o4-mini",
    "pa/o4-mini"
   ],
   "intro_i18n": {
    "zh-CN": "o4-mini 是 OpenAI 的推理模型，支持文本+图像输入和文本输出，适用于需要广泛知识的复杂任务，具备 200K 上下文窗口。",
    "zh-TW": "o4-mini 是 OpenAI 的推理模型，支援文字與圖像輸入、文字輸出，適用於需要廣泛知識的複雜任務，具備 200K 上下文視窗。",
    "ja-JP": "o4-miniは、OpenAIの推論モデルで、テキスト＋画像入力とテキスト出力に対応し、幅広い知識を必要とする複雑なタスクに適しており、200Kのコンテキストウィンドウを備えています。",
    "ru-RU": "o4-mini — модель рассуждения от OpenAI с вводом текст+изображение и текстовым выводом, подходящая для сложных задач, требующих обширных знаний, с контекстным окном 200K."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/o4-mini-deep-research",
   "model_name": "o4-mini-deep-research",
   "display_name": "o4-mini-deep-research",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "o4-mini-deep-research-2025-06-26",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5",
        "web_search": "1",
        "file_search_call": "1"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6.84"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.39"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "o4-mini-deep-research-2025-06-26"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai/o4-mini-deep-research"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.992"
      }
     },
     "provider_model_id": "openai/o4-mini-deep-research"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o4-mini-deep-research"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "openai/o4-mini-deep-research"
    }
   ],
   "intro": "Research model for long-horizon investigation, synthesis, and analytical reports",
   "released_at": "2024-06-26",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": false
   },
   "aliases": [
    "o4-mini-deep-research-2025-06-26",
    "openai/o4-mini-deep-research"
   ],
   "intro_i18n": {
    "zh-CN": "o4-mini-deep-research 是一款更快速、更经济的深度研究模型，适用于复杂的多步骤研究任务。它可以进行网页搜索，并通过 MCP 连接器访问您的数据。",
    "zh-TW": "o4-mini-deep-research 是一款更快速、更經濟的深度研究模型，適用於複雜的多步研究任務。可搜尋網路並透過 MCP 連接器存取您的資料。",
    "ja-JP": "o4-mini-deep-researchは、複雑な多段階リサーチ向けの高速かつ低コストなモデルで、ウェブ検索やMCPコネクタを通じたデータアクセスが可能です。",
    "ru-RU": "o4-mini-deep-research — более быстрая и доступная модель для глубоких исследований и многошаговых задач. Может искать в интернете и получать доступ к вашим данным через MCP-коннекторы."
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "completion",
     "old": "18.66",
     "new": "27.39"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "api-airforce",
     "charge": "prompt",
     "old": "4.68",
     "new": "6.84"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "openai/o4-mini-high",
   "model_name": "o4-mini-high",
   "display_name": "OpenAI: o4 Mini High",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai/o4-mini-high"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai/o4-mini-high"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "openai/o4-mini-high"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "openai/o4-mini-high"
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2025-04-17",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "image",
     "pdf",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-06",
   "family": "o",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "deprecated": true,
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o4-mini-high"
   ],
   "intro_i18n": {
    "zh-CN": "o4-mini 高推理版本，优化用于快速、高效的推理任务，具备强大的编程和视觉能力。",
    "zh-TW": "o4-mini 高推理等級，針對快速、高效推理進行優化，具備強大程式與視覺表現。",
    "ja-JP": "o4-mini高推論ティアは、高速かつ効率的な推論に最適化され、コーディングと視覚性能に優れています。",
    "ru-RU": "o4-mini — модель высокого уровня рассуждения, оптимизированная для быстрого и эффективного мышления с сильными результатами в программировании и зрении."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI: o4 Mini High"
    }
   ]
  },
  {
   "slug": "openai/o4-mini:flex",
   "model_name": "o4-mini:flex",
   "display_name": "openai/o4-mini:flex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.138"
      }
     },
     "provider_model_id": "openai/o4-mini:flex"
    }
   ],
   "released_at": "2025-04-16",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o4-mini:flex"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o4-mini:flex"
    }
   ]
  },
  {
   "slug": "openai/o4-mini:high",
   "model_name": "o4-mini:high",
   "display_name": "openai/o4-mini:high",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai/o4-mini:high"
    }
   ],
   "released_at": "2025-04-16",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o4-mini:high"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o4-mini:high"
    }
   ]
  },
  {
   "slug": "openai/o4-mini:low",
   "model_name": "o4-mini:low",
   "display_name": "openai/o4-mini:low",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai/o4-mini:low"
    }
   ],
   "released_at": "2025-04-16",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o4-mini:low"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o4-mini:low"
    }
   ]
  },
  {
   "slug": "openai/o4-mini:medium",
   "model_name": "o4-mini:medium",
   "display_name": "openai/o4-mini:medium",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "openai/o4-mini:medium"
    }
   ],
   "released_at": "2025-04-16",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/o4-mini:medium"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openai/o4-mini:medium"
    }
   ]
  },
  {
   "slug": "openai/o4-mini@eastus2",
   "model_name": "o4-mini@eastus2",
   "display_name": "azure/o4-mini@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "azure/o4-mini@eastus2"
    }
   ],
   "released_at": "2025-04-24",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/o4-mini@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/o4-mini@eastus2"
    }
   ]
  },
  {
   "slug": "openai/o4-mini@francecentral",
   "model_name": "o4-mini@francecentral",
   "display_name": "azure/o4-mini@francecentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "azure/o4-mini@francecentral"
    }
   ],
   "released_at": "2025-04-24",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/o4-mini@francecentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/o4-mini@francecentral"
    }
   ]
  },
  {
   "slug": "openai/o4-mini@swedencentral",
   "model_name": "o4-mini@swedencentral",
   "display_name": "azure/o4-mini@swedencentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "azure/o4-mini@swedencentral"
    }
   ],
   "released_at": "2025-04-24",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/o4-mini@swedencentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/o4-mini@swedencentral"
    }
   ]
  },
  {
   "slug": "openai/o4-mini@westus3",
   "model_name": "o4-mini@westus3",
   "display_name": "azure/o4-mini@westus3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "azure/o4-mini@westus3"
    }
   ],
   "released_at": "2025-04-24",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/o4-mini@westus3"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/o4-mini@westus3"
    }
   ]
  },
  {
   "slug": "openai/omni-moderation-2024-09-26",
   "model_name": "omni-moderation-2024-09-26",
   "display_name": "omni-moderation-2024-09-26",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "safety_detection",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "omni-moderation-2024-09-26"
    }
   ]
  },
  {
   "slug": "openai/omni-moderation-latest",
   "model_name": "omni-moderation-latest",
   "display_name": "omni-moderation-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "safety_detection",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "omni-moderation-latest"
    }
   ]
  },
  {
   "slug": "openai/omni-moderation-latest-intents",
   "model_name": "omni-moderation-latest-intents",
   "display_name": "omni-moderation-latest-intents",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "safety_detection",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "omni-moderation-latest-intents"
    }
   ]
  },
  {
   "slug": "openai/openai-chat-latest",
   "model_name": "openai-chat-latest",
   "display_name": "chat-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    }
   ],
   "released_at": "2026-05-06",
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chat-latest"
    }
   ]
  },
  {
   "slug": "openai/openai-chatgpt-4o-latest",
   "model_name": "openai-chatgpt-4o-latest",
   "display_name": "chatgpt-4o-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2024-08-08",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chatgpt-4o-latest"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-3-5-turbo-0125",
   "model_name": "openai-gpt-3-5-turbo-0125",
   "display_name": "gpt-3.5-turbo-0125",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "released_at": "2024-02-01",
   "max_input_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-3.5-turbo-0125"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4",
   "model_name": "openai-gpt-4",
   "display_name": "gpt-4",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    }
   ],
   "released_at": "2024-02-01",
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4-1",
   "model_name": "openai-gpt-4-1",
   "display_name": "GPT-4.1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "openai-gpt-4-1-2025-04-14"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai-gpt-4.1"
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai-gpt-4.1"
    }
   ],
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2025-04-14",
   "knowledge_cutoff": "2024-04",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-4-1-2025-04-14",
    "openai-gpt-4.1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4.1"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4-1-mini",
   "model_name": "openai-gpt-4-1-mini",
   "display_name": "gpt-4.1-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "openai-gpt-4-1-mini-2025-04-14"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-4-1-mini-2025-04-14"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4.1-mini"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4-1-nano",
   "model_name": "openai-gpt-4-1-nano",
   "display_name": "gpt-4.1-nano",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "openai-gpt-4-1-nano-2025-04-14"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-4-1-nano-2025-04-14"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4.1-nano"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4-plus",
   "model_name": "openai-gpt-4-plus",
   "display_name": "gpt-4-plus",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     }
    }
   ],
   "released_at": "2024-05-14",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "audio",
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "audio",
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4-plus"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4-turbo",
   "model_name": "openai-gpt-4-turbo",
   "display_name": "gpt-4-turbo",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai-gpt-4-turbo-2024-04-09"
    }
   ],
   "released_at": "2024-06-28",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-4-turbo-2024-04-09"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4-turbo"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4o",
   "model_name": "openai-gpt-4o",
   "display_name": "GPT-4o",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai-gpt-4o-2024-05-13"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "12.5"
      }
     },
     "provider_model_id": "openai-gpt-4o-2024-11-20"
    }
   ],
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2024-05-13",
   "knowledge_cutoff": "2023-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-4o-2024-05-13",
    "openai-gpt-4o-2024-08-06",
    "openai-gpt-4o-2024-11-20"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4o"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4o-image-generation",
   "model_name": "openai-gpt-4o-image-generation",
   "display_name": "gpt-4o-image-generation",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    }
   ],
   "released_at": "2025-04-03",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-image-generation"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4o-mini",
   "model_name": "openai-gpt-4o-mini",
   "display_name": "GPT-4o mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "openai-gpt-4o-mini-2024-07-18"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09375"
      }
     },
     "provider_model_id": "openai-gpt-4o-mini-2024-07-18"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-07-18",
   "knowledge_cutoff": "2023-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-4o-mini-2024-07-18"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-4o mini"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4o-mini-search-preview",
   "model_name": "openai-gpt-4o-mini-search-preview",
   "display_name": "gpt-4o-mini-search-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2025-05-06",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-mini-search-preview"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4o-plus",
   "model_name": "openai-gpt-4o-plus",
   "display_name": "gpt-4o-plus",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2024-11-20",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "audio",
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "audio",
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-plus"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-4o-search-preview",
   "model_name": "openai-gpt-4o-search-preview",
   "display_name": "gpt-4o-search-preview",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2025-05-06",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-4o-search-preview"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5",
   "model_name": "openai-gpt-5",
   "display_name": "GPT-5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai-gpt-5-2025-08-07"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "status": "beta",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5-2025-08-07"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-1",
   "model_name": "openai-gpt-5-1",
   "display_name": "GPT-5.1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "openai-gpt-5-1-2025-11-13"
    }
   ],
   "intro": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
   "released_at": "2025-11-13",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5-1-2025-11-13",
    "openai-gpt-5.1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.1"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-1-codex",
   "model_name": "openai-gpt-5-1-codex",
   "display_name": "gpt-5.1-codex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2025-11-14",
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.1-codex"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-1-codex-mini",
   "model_name": "openai-gpt-5-1-codex-mini",
   "display_name": "gpt-5.1-codex-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "released_at": "2025-11-14",
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.1-codex-mini"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-1-plus",
   "model_name": "openai-gpt-5-1-plus",
   "display_name": "gpt-5.1-plus",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2025-11-13",
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.1-plus"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-1-thinking-plus",
   "model_name": "openai-gpt-5-1-thinking-plus",
   "display_name": "gpt-5.1-thinking-plus",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2025-11-13",
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.1-thinking-plus"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-2",
   "model_name": "openai-gpt-5-2",
   "display_name": "GPT-5.2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     },
     "provider_model_id": "openai-gpt-5-2-2025-12-11"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai-gpt-5.2"
    }
   ],
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2025-12-11",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5-2-2025-12-11",
    "openai-gpt-5.2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.2"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-2-chat-latest",
   "model_name": "openai-gpt-5-2-chat-latest",
   "display_name": "gpt-5.2-chat-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    }
   ],
   "released_at": "2025-12-12",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.2-chat-latest"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-2-codex",
   "model_name": "openai-gpt-5-2-codex",
   "display_name": "gpt-5.2-codex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    }
   ],
   "released_at": "2025-12-19",
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.2-codex"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-2-pro",
   "model_name": "openai-gpt-5-2-pro",
   "display_name": "GPT-5.2 pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      }
     }
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "168"
      }
     },
     "provider_model_id": "openai-gpt-5.2-pro"
    }
   ],
   "intro": "Frontier GPT model for professional reasoning, coding, and multimodal work",
   "released_at": "2025-12-11",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-pro",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5.2-pro"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.2 pro"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-3",
   "model_name": "openai-gpt-5-3",
   "display_name": "gpt-5.3-chat-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    }
   ],
   "released_at": "2026-03-04",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5.3-chat-latest"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-3-codex",
   "model_name": "openai-gpt-5-3-codex",
   "display_name": "GPT-5.3 Codex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "openai-gpt-5.3-codex"
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5.3-codex"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.3 Codex"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-4",
   "model_name": "openai-gpt-5-4",
   "display_name": "GPT-5.4",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "openai-gpt-5.4"
    }
   ],
   "intro": "Frontier GPT model for professional reasoning, coding, and multimodal work",
   "released_at": "2026-03-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "status": "beta",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5.4"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-4-pro",
   "model_name": "openai-gpt-5-4-pro",
   "display_name": "GPT-5.4 pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     }
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      }
     },
     "provider_model_id": "openai-gpt-5.4-pro"
    }
   ],
   "intro": "Frontier GPT model for professional reasoning, coding, and multimodal work",
   "released_at": "2026-03-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-pro",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5.4-pro"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4 pro"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-5",
   "model_name": "openai-gpt-5-5",
   "display_name": "GPT-5.5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "openai-gpt-5.5",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Frontier GPT model for professional reasoning, coding, and multimodal work",
   "released_at": "2026-04-23",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "status": "beta",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5.5"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.5"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-chat-latest",
   "model_name": "openai-gpt-5-chat-latest",
   "display_name": "gpt-5-chat-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2025-08-07",
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5-chat-latest"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-codex",
   "model_name": "openai-gpt-5-codex",
   "display_name": "gpt-5-codex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2025-09-19",
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5-codex"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-mini",
   "model_name": "openai-gpt-5-mini",
   "display_name": "GPT-5 mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "openai-gpt-5-mini-2025-08-07"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "status": "beta",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5-mini-2025-08-07"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5 mini"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-nano",
   "model_name": "openai-gpt-5-nano",
   "display_name": "GPT-5 nano",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "openai-gpt-5-nano-2025-08-07"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     }
    },
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-08-07",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-nano",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "status": "beta",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5-nano-2025-08-07"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5 nano"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5-pro",
   "model_name": "openai-gpt-5-pro",
   "display_name": "gpt-5-pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     },
     "provider_model_id": "openai-gpt-5-pro-2025-10-06"
    }
   ],
   "released_at": "2025-10-09",
   "max_input_tokens": 400000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5-pro-2025-10-06"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-5-pro"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5.1-codex-max",
   "model_name": "openai-gpt-5.1-codex-max",
   "display_name": "GPT-5.1 Codex Max",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2025-11-13",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-codex",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.1 Codex Max"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5.4-mini-2026-03-17",
   "model_name": "openai-gpt-5.4-mini-2026-03-17",
   "display_name": "GPT-5.4 mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "openai-gpt-5.4-mini"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "openai-gpt-5.4-mini"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-03-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5.4-mini"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4 mini"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-5.4-nano-2026-03-17",
   "model_name": "openai-gpt-5.4-nano-2026-03-17",
   "display_name": "GPT-5.4 nano",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "openai-gpt-5.4-nano"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai-gpt-5.4-nano"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-03-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-nano",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-gpt-5.4-nano"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4 nano"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-52",
   "model_name": "openai-gpt-52",
   "display_name": "GPT-5.2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.219"
      }
     }
    }
   ],
   "intro": "Reliable GPT generation for broad coding, writing, and tool-assisted product work",
   "released_at": "2025-12-13",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 256000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.2"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-52-codex",
   "model_name": "openai-gpt-52-codex",
   "display_name": "GPT-5.2 Codex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.219"
      }
     }
    }
   ],
   "intro": "Code-specialist GPT for repository edits, reviews, and long-running software agents",
   "released_at": "2025-01-15",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 256000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.2 Codex"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-53-codex",
   "model_name": "openai-gpt-53-codex",
   "display_name": "GPT-5.3 Codex",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.19"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.219"
      }
     }
    }
   ],
   "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
   "released_at": "2026-02-24",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.3 Codex"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-54",
   "model_name": "openai-gpt-54",
   "display_name": "GPT-5.4",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.313"
      }
     }
    }
   ],
   "intro": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
   "released_at": "2026-03-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-54-mini",
   "model_name": "openai-gpt-54-mini",
   "display_name": "GPT-5.4 Mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9375"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.625"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09375"
      }
     }
    }
   ],
   "intro": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
   "released_at": "2026-03-27",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4 Mini"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-54-pro",
   "model_name": "openai-gpt-54-pro",
   "display_name": "GPT-5.4 Pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "37.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "225"
      }
     },
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks",
   "released_at": "2026-03-05",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.4 Pro"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-55",
   "model_name": "openai-gpt-55",
   "display_name": "GPT-5.5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "37.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.625"
      }
     },
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Default frontier GPT for coding, computer use, research, and knowledge work",
   "released_at": "2026-04-23",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.5"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-55-pro",
   "model_name": "openai-gpt-55-pro",
   "display_name": "GPT-5.5 Pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "37.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "225"
      }
     }
    }
   ],
   "intro": "Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding",
   "released_at": "2026-04-24",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.5 Pro"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-image-1",
   "model_name": "openai-gpt-image-1",
   "display_name": "GPT Image 1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-04-24",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "gpt-image",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT Image 1"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-image-1.5",
   "model_name": "openai-gpt-image-1.5",
   "display_name": "GPT Image 1.5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-11-25",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "gpt-image",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT Image 1.5"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-image-2",
   "model_name": "openai-gpt-image-2",
   "display_name": "GPT Image 2",
   "vendor": "openai",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-04-24",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "gpt-image",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT Image 2"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-oss-120b",
   "model_name": "openai-gpt-oss-120b",
   "display_name": "gpt-oss-120b",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss-120b"
    }
   ]
  },
  {
   "slug": "openai/openai-gpt-oss-20b",
   "model_name": "openai-gpt-oss-20b",
   "display_name": "gpt-oss-20b",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     }
    }
   ],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss-20b"
    }
   ]
  },
  {
   "slug": "openai/openai-o1",
   "model_name": "openai-o1",
   "display_name": "o1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      }
     },
     "provider_model_id": "openai-o1-2024-12-17"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2024-12-05",
   "knowledge_cutoff": "2023-09",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-o1-2024-12-17"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o1"
    }
   ]
  },
  {
   "slug": "openai/openai-o1-plus",
   "model_name": "openai-o1-plus",
   "display_name": "o1-plus",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "released_at": "2024-12-05",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "audio",
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "audio",
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o1-plus"
    }
   ]
  },
  {
   "slug": "openai/openai-o3",
   "model_name": "openai-o3",
   "display_name": "o3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "openai-o3-2025-04-16"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2025-04-16",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-o3-2025-04-16"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o3"
    }
   ]
  },
  {
   "slug": "openai/openai-o3-deep-research",
   "model_name": "openai-o3-deep-research",
   "display_name": "o3-deep-research",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     },
     "provider_model_id": "openai-o3-deep-research-2025-06-26"
    }
   ],
   "released_at": "2025-06-30",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-o3-deep-research-2025-06-26"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o3-deep-research"
    }
   ]
  },
  {
   "slug": "openai/openai-o3-mini",
   "model_name": "openai-o3-mini",
   "display_name": "o3-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "openai-o3-mini-2025-01-31"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      }
     }
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2024-12-20",
   "knowledge_cutoff": "2024-05",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "o-mini",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-o3-mini-2025-01-31"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o3-mini"
    }
   ]
  },
  {
   "slug": "openai/openai-o3-pro",
   "model_name": "openai-o3-pro",
   "display_name": "o3-pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      }
     },
     "provider_model_id": "openai-o3-pro-2025-06-10"
    }
   ],
   "released_at": "2025-06-11",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-o3-pro-2025-06-10"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o3-pro"
    }
   ]
  },
  {
   "slug": "openai/openai-o4-mini",
   "model_name": "openai-o4-mini",
   "display_name": "o4-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "openai-o4-mini-2025-04-16"
    }
   ],
   "released_at": "2025-04-16",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-o4-mini-2025-04-16"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o4-mini"
    }
   ]
  },
  {
   "slug": "openai/openai-o4-mini-deep-research",
   "model_name": "openai-o4-mini-deep-research",
   "display_name": "o4-mini-deep-research",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "openai-o4-mini-deep-research-2025-06-26"
    }
   ],
   "released_at": "2025-06-30",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai-o4-mini-deep-research-2025-06-26"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o4-mini-deep-research"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1-mini@eastus2",
   "model_name": "openai-responses/gpt-4.1-mini@eastus2",
   "display_name": "azure/gpt-4.1-mini@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "azure/gpt-4.1-mini@eastus2"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1-mini@eastus2",
    "azure/openai-responses/gpt-4.1-mini@eastus2"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1-mini@eastus2"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1-mini@francecentral",
   "model_name": "openai-responses/gpt-4.1-mini@francecentral",
   "display_name": "azure/gpt-4.1-mini@francecentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "azure/gpt-4.1-mini@francecentral"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1-mini@francecentral",
    "azure/openai-responses/gpt-4.1-mini@francecentral"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1-mini@francecentral"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1-mini@westus3",
   "model_name": "openai-responses/gpt-4.1-mini@westus3",
   "display_name": "azure/gpt-4.1-mini@westus3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "azure/gpt-4.1-mini@westus3"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1-mini@westus3",
    "azure/openai-responses/gpt-4.1-mini@westus3"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1-mini@westus3"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1-nano@eastus2",
   "model_name": "openai-responses/gpt-4.1-nano@eastus2",
   "display_name": "azure/gpt-4.1-nano@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "azure/gpt-4.1-nano@eastus2"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1-nano@eastus2",
    "azure/openai-responses/gpt-4.1-nano@eastus2"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1-nano@eastus2"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1-nano@francecentral",
   "model_name": "openai-responses/gpt-4.1-nano@francecentral",
   "display_name": "azure/gpt-4.1-nano@francecentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "azure/gpt-4.1-nano@francecentral"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1-nano@francecentral",
    "azure/openai-responses/gpt-4.1-nano@francecentral"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1-nano@francecentral"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1-nano@swedencentral",
   "model_name": "openai-responses/gpt-4.1-nano@swedencentral",
   "display_name": "azure/gpt-4.1-nano@swedencentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "azure/gpt-4.1-nano@swedencentral"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1-nano@swedencentral",
    "azure/openai-responses/gpt-4.1-nano@swedencentral"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1-nano@swedencentral"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1-nano@westus3",
   "model_name": "openai-responses/gpt-4.1-nano@westus3",
   "display_name": "azure/gpt-4.1-nano@westus3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "azure/gpt-4.1-nano@westus3"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1-nano@westus3",
    "azure/openai-responses/gpt-4.1-nano@westus3"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1-nano@westus3"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1@eastus2",
   "model_name": "openai-responses/gpt-4.1@eastus2",
   "display_name": "azure/gpt-4.1@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "azure/gpt-4.1@eastus2"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1@eastus2",
    "azure/openai-responses/gpt-4.1@eastus2"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1@eastus2"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1@francecentral",
   "model_name": "openai-responses/gpt-4.1@francecentral",
   "display_name": "azure/gpt-4.1@francecentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "azure/gpt-4.1@francecentral"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1@francecentral",
    "azure/openai-responses/gpt-4.1@francecentral"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1@francecentral"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1@swedencentral",
   "model_name": "openai-responses/gpt-4.1@swedencentral",
   "display_name": "azure/gpt-4.1@swedencentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "azure/gpt-4.1@swedencentral"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1@swedencentral",
    "azure/openai-responses/gpt-4.1@swedencentral"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1@swedencentral"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-4.1@westus3",
   "model_name": "openai-responses/gpt-4.1@westus3",
   "display_name": "azure/gpt-4.1@westus3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "azure/gpt-4.1@westus3"
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 1047576,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-4.1@westus3",
    "azure/openai-responses/gpt-4.1@westus3"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-4.1@westus3"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-5.4-pro@eastus2",
   "model_name": "openai-responses/gpt-5.4-pro@eastus2",
   "display_name": "azure/openai-responses/gpt-5.4-pro@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "180"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "azure/openai-responses/gpt-5.4-pro@eastus2"
    }
   ],
   "released_at": "2025-12-11",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/openai-responses/gpt-5.4-pro@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/openai-responses/gpt-5.4-pro@eastus2"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-5.4@eastus2",
   "model_name": "openai-responses/gpt-5.4@eastus2",
   "display_name": "azure/gpt-5.4@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "azure/gpt-5.4@eastus2"
    }
   ],
   "released_at": "2026-03-05",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.4@eastus2",
    "azure/openai-responses/gpt-5.4@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.4@eastus2"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-5.4@francecentral",
   "model_name": "openai-responses/gpt-5.4@francecentral",
   "display_name": "azure/gpt-5.4@francecentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "azure/gpt-5.4@francecentral"
    }
   ],
   "released_at": "2026-03-05",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.4@francecentral",
    "azure/openai-responses/gpt-5.4@francecentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.4@francecentral"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-5.4@swedencentral",
   "model_name": "openai-responses/gpt-5.4@swedencentral",
   "display_name": "azure/gpt-5.4@swedencentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "azure/gpt-5.4@swedencentral"
    }
   ],
   "released_at": "2026-03-05",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.4@swedencentral",
    "azure/openai-responses/gpt-5.4@swedencentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.4@swedencentral"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-5.5@eastus2",
   "model_name": "openai-responses/gpt-5.5@eastus2",
   "display_name": "azure/gpt-5.5@eastus2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "azure/gpt-5.5@eastus2"
    }
   ],
   "released_at": "2026-04-24",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.5@eastus2",
    "azure/openai-responses/gpt-5.5@eastus2"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.5@eastus2"
    }
   ]
  },
  {
   "slug": "openai/openai-responses/gpt-5.5@swedencentral",
   "model_name": "openai-responses/gpt-5.5@swedencentral",
   "display_name": "azure/gpt-5.5@swedencentral",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "azure/gpt-5.5@swedencentral"
    }
   ],
   "released_at": "2026-04-24",
   "max_input_tokens": 1050000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "azure/gpt-5.5@swedencentral",
    "azure/openai-responses/gpt-5.5@swedencentral"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure/gpt-5.5@swedencentral"
    }
   ]
  },
  {
   "slug": "openai/openai.gpt-oss-120b-1:0",
   "model_name": "openai.gpt-oss-120b-1:0",
   "display_name": "gpt-oss-120b",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.73"
      }
     },
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.493151"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     },
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.492958"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1545"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.618"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.62"
      }
     },
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.506329"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.79"
      }
     },
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.506329"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.23"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.93"
      }
     },
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.521739",
        "completion": "0.505376"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.73"
      }
     },
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.493151"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "region": "us-gov-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     },
     "region": "us-gov-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss-120b"
    }
   ]
  },
  {
   "slug": "openai/openai.gpt-oss-20b-1:0",
   "model_name": "openai.gpt-oss-20b-1:0",
   "display_name": "gpt-oss-20b",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "region": "ap-northeast-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.514286"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0721"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.309"
      }
     },
     "region": "ap-southeast-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "region": "ap-southeast-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.571429",
        "completion": "0.516129"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "eu-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.555556",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "eu-north-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "region": "eu-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.555556",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.514286"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.47"
      }
     },
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.454545",
        "completion": "0.489362"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "us-east-2"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.084"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "region": "us-gov-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.084"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.36"
      }
     },
     "region": "us-gov-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "region": "us-west-2"
    }
   ],
   "intro": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
   "released_at": "2025-08-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt-oss",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gpt-oss-20b"
    }
   ]
  },
  {
   "slug": "openai/p1",
   "model_name": "p1",
   "display_name": "o1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "60"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/p1"
    }
   ],
   "intro": "Reasoning model with extended thinking capabilities",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "pa/p1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o1"
    }
   ]
  },
  {
   "slug": "openai/p1-m",
   "model_name": "p1-m",
   "display_name": "o1-mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/p1-m"
    }
   ],
   "intro": "Efficient reasoning model",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "pa/p1-m"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "o1-mini"
    }
   ]
  },
  {
   "slug": "openai/p3",
   "model_name": "p3",
   "display_name": "OpenAI o3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/p3"
    }
   ],
   "intro": "o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images. o3 is succeeded by GPT-5.",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens"
    ],
    "unsupported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "n",
     "presence_penalty",
     "temperature",
     "top_logprobs",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "pa/p3"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI o3"
    }
   ]
  },
  {
   "slug": "openai/p3-m",
   "model_name": "p3-m",
   "display_name": "OpenAI o3 Mini",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/p3-m"
    }
   ],
   "intro": "o3-mini is our newest small reasoning model, providing high intelligence at the same cost and latency targets of o1-mini. o3-mini supports key developer features, like Structured Outputs, function calling, and Batch API. This model supports the `reasoning_effort` parameter, which can be set to 'high', 'medium', or 'low' to control the thinking time of the model.",
   "knowledge_cutoff": "2023-10",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens"
    ],
    "unsupported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "n",
     "presence_penalty",
     "temperature",
     "top_logprobs",
     "top_p"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "pa/p3-m"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI o3 Mini"
    }
   ]
  },
  {
   "slug": "openai/p3-pro",
   "model_name": "p3-pro",
   "display_name": "OpenAI o3 Pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "80"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "pa/p3-pro"
    }
   ],
   "intro": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers. o3-pro is available in the Responses API only to enable support for multi-turn model interactions before responding to API requests. Since o3-pro is designed to tackle tough problems, some requests may take several minutes to finish.",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "max_tokens"
    ],
    "unsupported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "n",
     "presence_penalty",
     "temperature",
     "top_logprobs",
     "top_p"
    ]
   },
   "capabilities": {
    "vision": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "pa/p3-pro"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenAI o3 Pro"
    }
   ]
  },
  {
   "slug": "openai/privacy-filter",
   "model_name": "privacy-filter",
   "display_name": "Privacy Filter",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "nearai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "openai/privacy-filter"
    }
   ],
   "released_at": "2026-05-18",
   "max_input_tokens": 512,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/privacy-filter"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Privacy Filter"
    }
   ]
  },
  {
   "slug": "openai/sora-2",
   "model_name": "sora-2",
   "display_name": "Sora 2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_720x1280": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "video_output": {
       "unit": "per_second",
       "price": "0.1"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "video_output_720x1280": "0.5",
        "video_output_720p": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_720x1280": {
       "unit": "per_second",
       "price": "0.1"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "sora-2-2025-10-06"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.8"
      }
     },
     "provider_model_id": "openai/sora-2"
    }
   ],
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video",
     "audio"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "audio_output": true,
    "function_calling": true,
    "pdf_input": true,
    "video_input": true
   },
   "released_at": "2025-12-08",
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "family": "sora",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/sora-2",
    "sora-2-2025-10-06",
    "sora-2-2025-12-08"
   ],
   "intro_i18n": {
    "zh-CN": "Sora 2是我们新推出的强大媒体生成模型，生成与音频同步的视频。可从自然语言或图像创建细节丰富、动态的视频片段。",
    "zh-TW": "Sora 2是我們的新型強大媒體生成模型，生成與音頻同步的影像。能從自然語言或影像創建細緻且動態的片段。",
    "ja-JP": "Sora 2は、新しい強力なメディア生成モデルで、音声と同期したビデオを生成します。自然言語または画像からリッチで詳細な動的クリップを作成できます。",
    "ru-RU": "Sora 2 — наша новая мощная модель генерации медиа, создающая видео с синхронизированным звуком. Она может создавать детализированные, динамичные клипы из естественного языка или изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sora 2"
    }
   ]
  },
  {
   "slug": "openai/sora-2-pro",
   "model_name": "sora-2-pro",
   "display_name": "Sora 2 Pro",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey+llmdb+lobehub-modelbank",
     "charges": {
      "video_output_720x1280": {
       "unit": "per_second",
       "price": "0.3"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.3"
      },
      "video_output_1024x1792": {
       "unit": "per_second",
       "price": "0.5"
      },
      "video_output_1792x1024": {
       "unit": "per_second",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "video_output_1080x1920": {
       "unit": "per_second",
       "price": "0.7"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.7"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "video_output": {
       "unit": "per_second",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "video_output_720x1280": "0.5",
        "video_output_720p": "0.5",
        "video_output_1024x1792": "0.5",
        "video_output_1792x1024": "0.5",
        "video_output_1080x1920": "0.5",
        "video_output_1080p": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "video_output_720x1280": {
       "unit": "per_second",
       "price": "0.3"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.3"
      },
      "video_output_1024x1792": {
       "unit": "per_second",
       "price": "0.5"
      },
      "video_output_1792x1024": {
       "unit": "per_second",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "3"
      }
     },
     "provider_model_id": "openai/sora-2-pro"
    }
   ],
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "released_at": "2025-10-06",
   "model_type": "video_generation",
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "sora",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/sora-2-pro"
   ],
   "intro_i18n": {
    "zh-CN": "Sora 2 Pro是我们最先进的媒体生成模型，生成与音频同步的视频。可从自然语言或图像创建细节丰富、动态的视频片段。",
    "zh-TW": "Sora 2 Pro是我們最先進的媒體生成模型，生成與音頻同步的影像。能從自然語言或影像創建細緻且動態的片段。",
    "ja-JP": "Sora 2 Proは、最先端の最も高度なメディア生成モデルで、音声と同期したビデオを生成します。自然言語または画像からリッチで詳細な動的クリップを作成できます。",
    "ru-RU": "Sora 2 Pro — наша передовая модель генерации медиа, создающая видео с синхронизированным звуком. Она может создавать детализированные, динамичные клипы из естественного языка или изображений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sora 2 Pro"
    }
   ]
  },
  {
   "slug": "openai/text-davinci-001",
   "model_name": "text-davinci-001",
   "display_name": "text-davinci-001",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-davinci-001"
    }
   ]
  },
  {
   "slug": "openai/text-davinci-002",
   "model_name": "text-davinci-002",
   "display_name": "text-davinci-002",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-davinci-002"
    }
   ]
  },
  {
   "slug": "openai/text-davinci-003",
   "model_name": "text-davinci-003",
   "display_name": "GPT-3 Text Davinci 003",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "pydantic-prices+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-3 Text Davinci 003"
    }
   ]
  },
  {
   "slug": "openai/text-davinci-edit-001",
   "model_name": "text-davinci-edit-001",
   "display_name": "text-davinci-edit-001",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-davinci-edit-001"
    }
   ]
  },
  {
   "slug": "openai/text-embedding-3-large",
   "model_name": "text-embedding-3-large",
   "display_name": "text-embedding-3-large",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "openai/text-embedding-3-large"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "openai/text-embedding-3-large"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "openai/text-embedding-3-large"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "openai/text-embedding-3-large"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "openai/text-embedding-3-large"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "openai/text-embedding-3-large"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2024-01-25",
   "knowledge_cutoff": "2024-01",
   "max_input_tokens": 8191,
   "max_output_tokens": 3072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "text-embedding",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/text-embedding-3-large"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 最强大的嵌入模型，适用于英文和非英文任务。",
    "zh-TW": "OpenAI 最強大的嵌入模型，適用於英文與非英文任務。",
    "ja-JP": "OpenAIの英語および非英語タスク向けで最も高性能な埋め込みモデルです。",
    "ru-RU": "Самая мощная модель встраивания от OpenAI для задач на английском и других языках."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/text-embedding-3-small",
   "model_name": "text-embedding-3-small",
   "display_name": "text-embedding-3-small",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.022"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "datazone_eu"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/text-embedding-3-small"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/text-embedding-3-small"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/text-embedding-3-small"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/text-embedding-3-small"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/text-embedding-3-small"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "openai/text-embedding-3-small"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2024-01-25",
   "knowledge_cutoff": "2024-01",
   "max_input_tokens": 8191,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "text-embedding",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_embedding",
   "deprecated": true,
   "deprecation_date": "2026-04-30",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/text-embedding-3-small"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 提升性能的 ada 嵌入模型变体。",
    "zh-TW": "OpenAI 改良版、高效能的 ada 嵌入模型變體。",
    "ja-JP": "OpenAIの改良された高性能なada埋め込みモデルのバリアントです。",
    "ru-RU": "Улучшенный и более производительный вариант модели встраивания ada от OpenAI."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/text-embedding-ada-002",
   "model_name": "text-embedding-ada-002",
   "display_name": "text-embedding-ada-002",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+truefoundry+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/text-embedding-ada-002"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/text-embedding-ada-002"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/text-embedding-ada-002"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/text-embedding-ada-002"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "openai/text-embedding-ada-002"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2022-12-15",
   "knowledge_cutoff": "2022-12",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "text-embedding",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/text-embedding-ada-002"
   ],
   "intro_i18n": {
    "zh-CN": "OpenAI 的旧版文本嵌入模型。",
    "zh-TW": "OpenAI 的舊版文字嵌入模型。",
    "ja-JP": "OpenAIの旧世代テキスト埋め込みモデルです。",
    "ru-RU": "Устаревшая модель встраивания текста от OpenAI."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "openai/text-embedding-ada-002-2",
   "model_name": "text-embedding-ada-002-2",
   "display_name": "text-embedding-ada-002-2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-embedding-ada-002-2"
    }
   ]
  },
  {
   "slug": "openai/text-embedding-ada-002-v2",
   "model_name": "text-embedding-ada-002-v2",
   "display_name": "text-embedding-ada-002-v2",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    }
   ],
   "max_input_tokens": 8191,
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   }
  },
  {
   "slug": "openai/text-moderation-004",
   "model_name": "text-moderation-004",
   "display_name": "text-moderation-004",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "safety_detection",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-moderation-004"
    }
   ]
  },
  {
   "slug": "openai/text-moderation-007",
   "model_name": "text-moderation-007",
   "display_name": "text-moderation-007",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_output_tokens": 0,
   "model_type": "safety_detection",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-moderation-007"
    }
   ]
  },
  {
   "slug": "openai/text-moderation-latest",
   "model_name": "text-moderation-latest",
   "display_name": "text-moderation-latest",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_output_tokens": 0,
   "model_type": "safety_detection",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-moderation-latest"
    }
   ]
  },
  {
   "slug": "openai/text-moderation-stable",
   "model_name": "text-moderation-stable",
   "display_name": "text-moderation-stable",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search_call": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_output_tokens": 0,
   "model_type": "safety_detection",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-moderation-stable"
    }
   ]
  },
  {
   "slug": "openai/tts-1",
   "model_name": "tts-1",
   "display_name": "TTS-1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.21"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "openai/tts-1"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "speech_input": {
       "unit": "per_M_characters",
       "price": "15"
      }
     },
     "provider_model_id": "openai/tts-1"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true,
    "pdf_input": true,
    "audio_input": true
   },
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2023-11-06",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "family": "o",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/tts-1"
   ],
   "intro_i18n": {
    "zh-CN": "最新文本转语音模型，优化实时速度。",
    "zh-TW": "最新的文字轉語音模型，優化即時速度。",
    "ja-JP": "リアルタイム速度に最適化された最新の音声合成モデルです。",
    "ru-RU": "Последняя модель синтеза речи, оптимизированная для скорости в реальном времени."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TTS-1"
    }
   ]
  },
  {
   "slug": "openai/tts-1-1106",
   "model_name": "tts-1-1106",
   "display_name": "tts-1-1106",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey+llmdb",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "openai/tts-1-1106"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true,
    "pdf_input": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/tts-1-1106"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "tts-1-1106"
    }
   ]
  },
  {
   "slug": "openai/tts-1-hd",
   "model_name": "tts-1-hd",
   "display_name": "TTS-1 HD",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "30"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.42"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "30"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/tts-1-hd"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "speech_input": {
       "unit": "per_M_characters",
       "price": "30"
      }
     },
     "provider_model_id": "openai/tts-1-hd"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true,
    "pdf_input": true,
    "audio_input": true
   },
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2023-11-06",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "family": "o",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/tts-1-hd"
   ],
   "intro_i18n": {
    "zh-CN": "最新文本转语音模型，优化音质表现。",
    "zh-TW": "最新的文字轉語音模型，優化音質表現。",
    "ja-JP": "高品質に最適化された最新の音声合成モデルです。",
    "ru-RU": "Последняя модель синтеза речи, оптимизированная для качества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TTS-1 HD"
    }
   ]
  },
  {
   "slug": "openai/tts-1-hd-1106",
   "model_name": "tts-1-hd-1106",
   "display_name": "tts-1-hd-1106",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "truefoundry+portkey+llmdb",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "30"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     },
     "provider_model_id": "openai/tts-1-hd-1106"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true,
    "pdf_input": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/tts-1-hd-1106"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "tts-1-hd-1106"
    }
   ]
  },
  {
   "slug": "openai/whisper",
   "model_name": "whisper",
   "display_name": "whisper",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0001"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0.0001"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "whisper"
    }
   ]
  },
  {
   "slug": "openai/whisper-001",
   "model_name": "whisper-001",
   "display_name": "whisper-001",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0001"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0.0001"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "whisper-001"
    }
   ]
  },
  {
   "slug": "openai/whisper-1",
   "model_name": "whisper-1",
   "display_name": "whisper-1",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "openai",
     "official": true,
     "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0001"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6000"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "web_search_preview": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "file_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.42"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0001"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0.0001"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "100"
      }
     },
     "provider_model_id": "openai/whisper-1"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0001"
      },
      "audio_input": {
       "unit": "per_second",
       "price": "0.0001"
      }
     },
     "provider_model_id": "openai/whisper-1"
    }
   ],
   "model_type": "speech_recognition",
   "capabilities": {
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Speech transcription model for accurate audio-to-text and captioning workflows",
   "released_at": "2022-09-21",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "family": "whisper",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/whisper-1"
   ],
   "intro_i18n": {
    "zh-CN": "通用语音识别模型，支持多语言 ASR、语音翻译和语言识别。",
    "zh-TW": "通用語音識別模型，支援多語言 ASR、語音翻譯與語言識別。",
    "ja-JP": "多言語ASR、音声翻訳、言語識別に対応した汎用音声認識モデルです。",
    "ru-RU": "Универсальная модель распознавания речи с поддержкой многоязычного ASR, перевода речи и определения языка."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "openai/Whisper-Large-v3",
   "model_name": "Whisper-Large-v3",
   "display_name": "Whisper large-v3",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0000075"
      }
     },
     "provider_model_id": "openai/whisper-large-v3"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0023"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0023"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "openai/whisper-large-v3"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00003083"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0"
      }
     },
     "provider_model_id": "whisper-large-v3"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/whisper-large-v3"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openai/whisper-large-v3"
    },
    {
     "provider": "privatemode-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "whisper-large-v3"
    },
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00002778"
      }
     }
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "whisper-large-v3"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.000025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "openai/whisper-large-v3"
    }
   ],
   "intro": "Speech transcription model for accurate audio-to-text and captioning workflows",
   "released_at": "2023-09-01",
   "knowledge_cutoff": "2023-09",
   "max_input_tokens": 0,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "whisper",
   "capabilities": {
    "prompt_caching": true,
    "audio_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "speech_recognition",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/whisper-large-v3",
    "whisper-large-v3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Whisper large-v3"
    }
   ]
  },
  {
   "slug": "openai/whisper-large-v3-turbo",
   "model_name": "whisper-large-v3-turbo",
   "display_name": "Whisper Large V3 Turbo",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0000033333333333"
      }
     },
     "provider_model_id": "openai/whisper-large-v3-turbo"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0023"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0023"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     },
     "provider_model_id": "openai/whisper-large-v3-turbo"
    },
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00001111"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0"
      }
     }
    },
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0001"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0.0001"
      }
     }
    }
   ],
   "intro": "Speech transcription model for accurate audio-to-text and captioning workflows",
   "released_at": "2024-10-01",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "whisper",
   "capabilities": {
    "audio_input": true,
    "open_weights": true
   },
   "model_type": "speech_recognition",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "aliases": [
    "openai/whisper-large-v3-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Whisper Large V3 Turbo"
    }
   ]
  },
  {
   "slug": "openai/whisper-v3-large",
   "model_name": "whisper-v3-large",
   "display_name": "Whisper V3 Large",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "speech_recognition",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Whisper V3 Large"
    }
   ]
  },
  {
   "slug": "openai/xpersona-gpt-5.5",
   "model_name": "xpersona-gpt-5.5",
   "display_name": "GPT-5.5",
   "vendor": "openai",
   "pricing": [
    {
     "provider": "xpersona",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "18"
      }
     }
    }
   ],
   "intro": "Default frontier GPT for coding, computer use, research, and knowledge work",
   "released_at": "2026-05-29",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "openai-responses",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible",
     "openai-responses"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GPT-5.5"
    }
   ]
  },
  {
   "slug": "openchat/openchat-3.5-1210",
   "model_name": "openchat-3.5-1210",
   "display_name": "openchat-3.5-1210",
   "vendor": "openchat",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "openchat/openchat-3.5-1210"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "openchat/openchat-3.5-1210"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openchat-3.5-1210"
    }
   ]
  },
  {
   "slug": "openchat/openchat-3p5-0106-7b",
   "model_name": "openchat-3p5-0106-7b",
   "display_name": "OpenChat 3.5 0106",
   "vendor": "openchat",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/openchat-3p5-0106-7b"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/openchat-3p5-0106-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenChat 3.5 0106"
    }
   ]
  },
  {
   "slug": "openchat/openchat-7b",
   "model_name": "openchat-7b",
   "display_name": "OpenChat 7B",
   "vendor": "openchat",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "openchat/openchat-7b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     },
     "provider_model_id": "openchat/openchat-7b"
    }
   ],
   "capabilities": {
    "structured_output": true
   },
   "released_at": "2024-07-26",
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "openchat/openchat-7b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OpenChat 7B"
    }
   ]
  },
  {
   "slug": "other/@cf/pipecat-ai/smart-turn-v2",
   "model_name": "@cf/pipecat-ai/smart-turn-v2",
   "display_name": "Pipecat Smart Turn v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/pipecat-ai/smart-turn-v2"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-11-14",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "smart-turn",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "workers-ai/@cf/pipecat-ai/smart-turn-v2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pipecat Smart Turn v2"
    }
   ]
  },
  {
   "slug": "other/abliterated-model",
   "model_name": "abliterated-model",
   "display_name": "Abliterated Model",
   "vendor": "other",
   "pricing": [
    {
     "provider": "abliteration-ai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2026-01-06",
   "max_input_tokens": 150000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "open_weights": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2026-05",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Abliterated Model"
    }
   ]
  },
  {
   "slug": "other/agent-max",
   "model_name": "agent-max",
   "display_name": "Agent Max",
   "vendor": "other",
   "pricing": [],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-05-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "status": "beta",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agent Max"
    }
   ]
  },
  {
   "slug": "other/agent-prime",
   "model_name": "agent-prime",
   "display_name": "Agent Prime",
   "vendor": "other",
   "pricing": [],
   "intro": "Preview model for early access evaluation, prototyping, and compatibility testing",
   "released_at": "2026-05-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "beta",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agent Prime"
    }
   ]
  },
  {
   "slug": "other/agent-standard",
   "model_name": "agent-standard",
   "display_name": "Agent Standard",
   "vendor": "other",
   "pricing": [],
   "intro": "Preview model for early access evaluation, prototyping, and compatibility testing",
   "released_at": "2026-05-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "beta",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agent Standard"
    }
   ]
  },
  {
   "slug": "other/agnes-1.5-lite",
   "model_name": "agnes-1.5-lite",
   "display_name": "Agnes 1.5 Lite",
   "vendor": "other",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "sapiens-ai/agnes-1.5-lite"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2026-03-26",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sapiens-ai/agnes-1.5-lite"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agnes 1.5 Lite"
    }
   ]
  },
  {
   "slug": "other/agnes-1.5-pro",
   "model_name": "agnes-1.5-pro",
   "display_name": "Agnes 1.5 Pro",
   "vendor": "other",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "sapiens-ai/agnes-1.5-pro"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2026-03-21",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sapiens-ai/agnes-1.5-pro"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agnes 1.5 Pro"
    }
   ]
  },
  {
   "slug": "other/agnes-2.0-flash",
   "model_name": "agnes-2.0-flash",
   "display_name": "Agnes-2.0-Flash",
   "vendor": "other",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "sapiens-ai/agnes-2.0-flash"
    }
   ],
   "released_at": "2026-05-21",
   "max_input_tokens": 256000,
   "capabilities": {
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sapiens-ai/agnes-2.0-flash"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agnes-2.0-Flash"
    }
   ]
  },
  {
   "slug": "other/ai4bharat/indictrans2-en-indic-1B",
   "model_name": "ai4bharat/indictrans2-en-indic-1B",
   "display_name": "IndicTrans2 EN-Indic 1B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.34"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "@cf/ai4bharat/indictrans2-en-indic-1B"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-09-25",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "indictrans",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/ai4bharat/indictrans2-en-indic-1B",
    "workers-ai/@cf/ai4bharat/indictrans2-en-indic-1B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "IndicTrans2 EN-Indic 1B"
    }
   ]
  },
  {
   "slug": "other/aihubmix-router",
   "model_name": "aihubmix-router",
   "display_name": "aihubmix-router",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aihubmix-router"
    }
   ]
  },
  {
   "slug": "other/aion-1.0",
   "model_name": "aion-1.0",
   "display_name": "AionLabs: Aion-1.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "aion-labs/aion-1.0"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.995"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.99"
      }
     },
     "provider_model_id": "aion-labs/aion-1.0"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "aion-labs/aion-1.0"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-02-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "family": "llama",
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "aion-labs/aion-1.0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AionLabs: Aion-1.0"
    }
   ]
  },
  {
   "slug": "other/aion-1.0-mini",
   "model_name": "aion-1.0-mini",
   "display_name": "AionLabs: Aion-1.0-Mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "aion-labs/aion-1.0-mini"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7989999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.394"
      }
     },
     "provider_model_id": "aion-labs/aion-1.0-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "aion-labs/aion-1.0-mini"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-02-05",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "family": "deepseek",
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "aion-labs/aion-1.0-mini"
   ],
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "open_weights: true→false"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AionLabs: Aion-1.0-Mini"
    }
   ]
  },
  {
   "slug": "other/aion-2.0",
   "model_name": "aion-2.0",
   "display_name": "AionLabs: Aion-2.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "aion-labs/aion-2.0"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "aion-labs/aion-2.0"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "aion-labs/aion-2.0"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-02-24",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "aion-labs/aion-2.0"
   ],
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AionLabs: Aion-2.0"
    }
   ]
  },
  {
   "slug": "other/aion-2.5",
   "model_name": "aion-2.5",
   "display_name": "AionLabs: Aion-2.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "aion-labs/aion-2.5"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2026-03-20",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "aion-labs/aion-2.5"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AionLabs: Aion-2.5"
    }
   ]
  },
  {
   "slug": "other/aion-3.0",
   "model_name": "aion-3.0",
   "display_name": "Aion-3.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "aion-labs/aion-3.0"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "aion-labs/aion-3.0"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "aion-labs/aion-3.0"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-07-07",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "aion-labs/aion-3.0"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "Aion-3.0"
    }
   ]
  },
  {
   "slug": "other/aion-3.0-mini",
   "model_name": "aion-3.0-mini",
   "display_name": "Aion-3.0-Mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "aion-labs/aion-3.0-mini"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "aion-labs/aion-3.0-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "aion-labs/aion-3.0-mini"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2026-07-07",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "aion-labs/aion-3.0-mini"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "Aion-3.0-Mini"
    }
   ]
  },
  {
   "slug": "other/aion-labs-aion-2-0",
   "model_name": "aion-labs-aion-2-0",
   "display_name": "Aion 2.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-03-24",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Aion 2.0"
    }
   ]
  },
  {
   "slug": "other/aion-labs-aion-3-0",
   "model_name": "aion-labs-aion-3-0",
   "display_name": "Aion 3.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.9375"
      }
     }
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-07-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "Aion 3.0"
    }
   ]
  },
  {
   "slug": "other/aion-labs-aion-3-0-mini",
   "model_name": "aion-labs-aion-3-0-mini",
   "display_name": "Aion 3.0 Mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.225"
      }
     }
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2026-07-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "Aion 3.0 Mini"
    }
   ]
  },
  {
   "slug": "other/airoboros-l2-70b",
   "model_name": "airoboros-l2-70b",
   "display_name": "airoboros-l2-70b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "jondurbin/airoboros-l2-70b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "jondurbin/airoboros-l2-70b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "airoboros-l2-70b"
    }
   ]
  },
  {
   "slug": "other/airoboros-l2-70b-2.1",
   "model_name": "airoboros-l2-70b-2.1",
   "display_name": "airoboros-l2-70b-2.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13.875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.875"
      }
     },
     "provider_model_id": "jondurbin/airoboros-l2-70b-2.1"
    }
   ],
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "jondurbin/airoboros-l2-70b-2.1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "airoboros-l2-70b-2.1"
    }
   ]
  },
  {
   "slug": "other/all-mini-lm-l6-v2",
   "model_name": "all-mini-lm-l6-v2",
   "display_name": "All-MiniLM-L6-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.009"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2021-08-30",
   "max_input_tokens": 256,
   "max_output_tokens": 384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "text-embedding",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "All-MiniLM-L6-v2"
    }
   ]
  },
  {
   "slug": "other/all-MiniLM-L12-v2",
   "model_name": "all-MiniLM-L12-v2",
   "display_name": "Sentence Transformers: all-MiniLM-L12-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/all-MiniLM-L12-v2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/all-minilm-l12-v2"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/sentence-transformers/all-MiniLM-L12-v2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true,
    "stream": true
   },
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/sentence-transformers/all-MiniLM-L12-v2",
    "sentence-transformers/all-MiniLM-L12-v2",
    "sentence-transformers/all-minilm-l12-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sentence Transformers: all-MiniLM-L12-v2"
    }
   ]
  },
  {
   "slug": "other/all-MiniLM-L6-v2",
   "model_name": "all-MiniLM-L6-v2",
   "display_name": "Sentence Transformers: all-MiniLM-L6-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/all-MiniLM-L6-v2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/all-minilm-l6-v2"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/sentence-transformers/all-MiniLM-L6-v2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true,
    "stream": true
   },
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/sentence-transformers/all-MiniLM-L6-v2",
    "sentence-transformers/all-MiniLM-L6-v2",
    "sentence-transformers/all-minilm-l6-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sentence Transformers: all-MiniLM-L6-v2"
    }
   ]
  },
  {
   "slug": "other/all-mpnet-base-v2",
   "model_name": "all-mpnet-base-v2",
   "display_name": "Sentence Transformers: all-mpnet-base-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/all-mpnet-base-v2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/all-mpnet-base-v2"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/sentence-transformers/all-mpnet-base-v2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true,
    "stream": true
   },
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/sentence-transformers/all-mpnet-base-v2",
    "sentence-transformers/all-mpnet-base-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sentence Transformers: all-mpnet-base-v2"
    }
   ]
  },
  {
   "slug": "other/allam-1-13b-instruct",
   "model_name": "allam-1-13b-instruct",
   "display_name": "allam-1-13b-instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "allam-1-13b-instruct"
    }
   ]
  },
  {
   "slug": "other/ALLaM-7B-Instruct-preview",
   "model_name": "ALLaM-7B-Instruct-preview",
   "display_name": "ALLaM-7B-Instruct-preview",
   "vendor": "other",
   "pricing": [
    {
     "provider": "sambanova",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.59"
      }
     }
    }
   ],
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ALLaM-7B-Instruct-preview"
    }
   ]
  },
  {
   "slug": "other/alpaca-7b",
   "model_name": "alpaca-7b",
   "display_name": "alpaca-7b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "togethercomputer/alpaca-7b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/alpaca-7b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "alpaca-7b"
    }
   ]
  },
  {
   "slug": "other/Anubis-70B-v1",
   "model_name": "Anubis-70B-v1",
   "display_name": "Anubis 70B v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "TheDrummer/Anubis-70B-v1"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2024-01-01",
   "max_input_tokens": 65536,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/Anubis-70B-v1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Anubis 70B v1"
    }
   ]
  },
  {
   "slug": "other/Anubis-70B-v1.1",
   "model_name": "Anubis-70B-v1.1",
   "display_name": "Anubis 70B v1.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.31"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.31"
      }
     },
     "provider_model_id": "TheDrummer/Anubis-70B-v1.1"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2024-01-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/Anubis-70B-v1.1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Anubis 70B v1.1"
    }
   ]
  },
  {
   "slug": "other/anubis-pro-105b-v1",
   "model_name": "anubis-pro-105b-v1",
   "display_name": "anubis-pro-105b-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "thedrummer/anubis-pro-105b-v1"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "thedrummer/anubis-pro-105b-v1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "anubis-pro-105b-v1"
    }
   ]
  },
  {
   "slug": "other/aoai-sora",
   "model_name": "aoai-sora",
   "display_name": "aoai-sora",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.1"
      }
     },
     "provider_model_id": "aoai-sora-2025-02-28"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "aoai-sora-2025-02-28"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "aoai-sora"
    }
   ]
  },
  {
   "slug": "other/apertus-70b-instruct",
   "model_name": "apertus-70b-instruct",
   "display_name": "Apertus 70B Instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.82"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.92"
      }
     },
     "provider_model_id": "publicai/apertus-70b-instruct"
    }
   ],
   "released_at": "2026-06-30",
   "max_input_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "publicai/apertus-70b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "Apertus 70B Instruct"
    }
   ]
  },
  {
   "slug": "other/Apertus-70B-Instruct-2509",
   "model_name": "Apertus-70B-Instruct-2509",
   "display_name": "swiss-ai/Apertus-70B-Instruct-2509",
   "vendor": "other",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.82"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.92"
      }
     },
     "provider_model_id": "swiss-ai/Apertus-70B-Instruct-2509"
    }
   ],
   "released_at": "2025-09-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "swiss-ai/Apertus-70B-Instruct-2509"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "swiss-ai/Apertus-70B-Instruct-2509"
    }
   ]
  },
  {
   "slug": "other/apertus-8b-instruct",
   "model_name": "apertus-8b-instruct",
   "display_name": "Apertus 8B Instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "publicai/apertus-8b-instruct"
    }
   ],
   "released_at": "2026-06-30",
   "max_input_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "publicai/apertus-8b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "Apertus 8B Instruct"
    }
   ]
  },
  {
   "slug": "other/Apertus-8B-Instruct-2509",
   "model_name": "Apertus-8B-Instruct-2509",
   "display_name": "swiss-ai/Apertus-8B-Instruct-2509",
   "vendor": "other",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "swiss-ai/Apertus-8B-Instruct-2509"
    }
   ],
   "released_at": "2025-08-13",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "swiss-ai/Apertus-8B-Instruct-2509"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "swiss-ai/Apertus-8B-Instruct-2509"
    }
   ]
  },
  {
   "slug": "other/Apriel-1.5-15b-Thinker",
   "model_name": "Apriel-1.5-15b-Thinker",
   "display_name": "Apriel-1.5-15b-Thinker",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ServiceNow-AI/Apriel-1.5-15b-Thinker"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ServiceNow-AI/Apriel-1.5-15b-Thinker"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Apriel-1.5-15b-Thinker"
    }
   ]
  },
  {
   "slug": "other/Apriel-1.6-15b-Thinker",
   "model_name": "Apriel-1.6-15b-Thinker",
   "display_name": "Apriel-1.6-15b-Thinker",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ServiceNow-AI/Apriel-1.6-15b-Thinker"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ServiceNow-AI/Apriel-1.6-15b-Thinker"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Apriel-1.6-15b-Thinker"
    }
   ]
  },
  {
   "slug": "other/arrow-1.1",
   "model_name": "arrow-1.1",
   "display_name": "Arrow 1.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.2"
      },
      "image_output_vectorize": {
       "unit": "per_image",
       "price": "0.15"
      }
     },
     "provider_model_id": "quiverai/arrow-1.1"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-04-16",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "o",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "quiverai/arrow-1.1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Arrow 1.1"
    }
   ]
  },
  {
   "slug": "other/asi1-mini",
   "model_name": "asi1-mini",
   "display_name": "ASI1 Mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-03-25",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ASI1 Mini"
    }
   ]
  },
  {
   "slug": "other/auto-model",
   "model_name": "auto-model",
   "display_name": "Auto model",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2024-06-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 1000000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Auto model"
    }
   ]
  },
  {
   "slug": "other/auto-model-basic",
   "model_name": "auto-model-basic",
   "display_name": "Auto model (Basic)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.992"
      }
     }
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2024-06-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 1000000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Auto model (Basic)"
    }
   ]
  },
  {
   "slug": "other/auto-model-premium",
   "model_name": "auto-model-premium",
   "display_name": "Auto model (Premium)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.992"
      }
     }
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2024-06-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 1000000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Auto model (Premium)"
    }
   ]
  },
  {
   "slug": "other/auto-model-standard",
   "model_name": "auto-model-standard",
   "display_name": "Auto model (Standard)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.992"
      }
     }
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2024-06-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 1000000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Auto model (Standard)"
    }
   ]
  },
  {
   "slug": "other/azure-o1",
   "model_name": "azure-o1",
   "display_name": "Azure o1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "59.993"
      }
     }
    }
   ],
   "intro": "O-series reasoning model for hard analysis, math, coding, and planning",
   "released_at": "2024-12-17",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Azure o1"
    }
   ]
  },
  {
   "slug": "other/azure-stt",
   "model_name": "azure-stt",
   "display_name": "azure-stt",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.0002777778"
      },
      "audio_output": {
       "unit": "per_second",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/speech-services/",
   "model_type": "speech_recognition",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure-stt"
    }
   ]
  },
  {
   "slug": "other/azure-tts",
   "model_name": "azure-tts",
   "display_name": "azure-tts",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "15"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure-tts"
    }
   ]
  },
  {
   "slug": "other/azure-tts-hd",
   "model_name": "azure-tts-hd",
   "display_name": "azure-tts-hd",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "30"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "azure-tts-hd"
    }
   ]
  },
  {
   "slug": "other/balanced",
   "model_name": "balanced",
   "display_name": "Kilo Auto Balanced",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0325"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.40625"
      }
     },
     "provider_model_id": "kilo-auto/balanced"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2026-03-15",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kilo-auto/balanced"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kilo Auto Balanced"
    }
   ]
  },
  {
   "slug": "other/bce-reranker-base",
   "model_name": "bce-reranker-base",
   "display_name": "bce-reranker-base",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "bce-reranker-base"
    }
   ]
  },
  {
   "slug": "other/Bielik-11B-v2.6-Instruct",
   "model_name": "Bielik-11B-v2.6-Instruct",
   "display_name": "Bielik 11B v2.6 Instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "cloudferro-sherlock",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.67"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.67"
      }
     },
     "provider_model_id": "speakleash/Bielik-11B-v2.6-Instruct"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-03-13",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "speakleash/Bielik-11B-v2.6-Instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Bielik 11B v2.6 Instruct"
    }
   ]
  },
  {
   "slug": "other/Bielik-11B-v3.0-Instruct",
   "model_name": "Bielik-11B-v3.0-Instruct",
   "display_name": "Bielik 11B v3.0 Instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "cloudferro-sherlock",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.67"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.67"
      }
     },
     "provider_model_id": "speakleash/Bielik-11B-v3.0-Instruct"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "speakleash/Bielik-11B-v3.0-Instruct"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-03-13",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "speakleash/Bielik-11B-v3.0-Instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Bielik 11B v3.0 Instruct"
    }
   ]
  },
  {
   "slug": "other/big-pickle",
   "model_name": "big-pickle",
   "display_name": "Big Pickle",
   "vendor": "other",
   "pricing": [
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-10-17",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "big-pickle",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "OpenCode 推出的 Big Pickle —— 免费开源、具备强大代码能力的模型。",
    "zh-TW": "OpenCode 推出的 Big Pickle —— 免費開放權重模型，具備強大的程式能力。",
    "ja-JP": "Big Pickle by OpenCode — 強力なコーディング能力を備えた無料のオープンウェイトモデル。",
    "ru-RU": "Big Pickle от OpenCode — бесплатная модель с открытыми весами и сильными возможностями в области программирования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Big Pickle"
    }
   ]
  },
  {
   "slug": "other/blur_background",
   "model_name": "blur_background",
   "display_name": "blur_background",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/blur_background"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/blur_background"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "blur_background"
    }
   ]
  },
  {
   "slug": "other/bodybuilder",
   "model_name": "bodybuilder",
   "display_name": "Body Builder (beta)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/bodybuilder"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/bodybuilder"
    }
   ],
   "intro": "Preview model for early access evaluation, prototyping, and compatibility testing",
   "released_at": "2026-03-15",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "beta",
   "capabilities": {},
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "openrouter/bodybuilder"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Body Builder (beta)"
    }
   ]
  },
  {
   "slug": "other/brave",
   "model_name": "brave",
   "display_name": "Brave (Answers)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-03-02",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Brave (Answers)"
    }
   ]
  },
  {
   "slug": "other/brave-pro",
   "model_name": "brave-pro",
   "display_name": "Brave (Pro)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-03-02",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Brave (Pro)"
    }
   ]
  },
  {
   "slug": "other/brave-research",
   "model_name": "brave-research",
   "display_name": "Brave (Research)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-03-02",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Brave (Research)"
    }
   ]
  },
  {
   "slug": "other/Bria-3.2",
   "model_name": "Bria-3.2",
   "display_name": "Bria-3.2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/Bria-3.2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/Bria-3.2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Bria-3.2"
    }
   ]
  },
  {
   "slug": "other/Bria-3.2-vector",
   "model_name": "Bria-3.2-vector",
   "display_name": "Bria-3.2-vector",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/Bria-3.2-vector"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/Bria-3.2-vector"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Bria-3.2-vector"
    }
   ]
  },
  {
   "slug": "other/bulbul:v2",
   "model_name": "bulbul:v2",
   "display_name": "Sarvam: Bulbul V2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "sarvam/bulbul:v2"
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 1500,
   "max_output_tokens": 1500,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sarvam/bulbul:v2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sarvam: Bulbul V2"
    }
   ]
  },
  {
   "slug": "other/caller-large",
   "model_name": "caller-large",
   "display_name": "caller-large",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "caller-large"
    }
   ]
  },
  {
   "slug": "other/cc-k2.6-code-preview",
   "model_name": "cc-k2.6-code-preview",
   "display_name": "cc-k2.6-code-preview",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-k2.6-code-preview"
    }
   ]
  },
  {
   "slug": "other/chatterbox-multilingual",
   "model_name": "chatterbox-multilingual",
   "display_name": "chatterbox-multilingual",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "1"
      }
     },
     "provider_model_id": "ResembleAI/chatterbox-multilingual"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_input": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ResembleAI/chatterbox-multilingual"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chatterbox-multilingual"
    }
   ]
  },
  {
   "slug": "other/chatterbox-turbo",
   "model_name": "chatterbox-turbo",
   "display_name": "chatterbox-turbo",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "1"
      }
     },
     "provider_model_id": "ResembleAI/chatterbox-turbo"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ResembleAI/chatterbox-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chatterbox-turbo"
    }
   ]
  },
  {
   "slug": "other/cheap",
   "model_name": "cheap",
   "display_name": "Cheap",
   "vendor": "other",
   "pricing": [],
   "intro": "TrustedRouter low-cost routing alias that prefers inexpensive healthy model endpoints.",
   "released_at": "2026-05-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cheap"
    }
   ]
  },
  {
   "slug": "other/chirp_3",
   "model_name": "chirp_3",
   "display_name": "chirp_3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.00026667"
      }
     }
    }
   ],
   "docs_url": "https://cloud.google.com/speech-to-text/pricing",
   "model_type": "speech_recognition",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "chirp_3"
    }
   ]
  },
  {
   "slug": "other/chirp-3-hd",
   "model_name": "chirp-3-hd",
   "display_name": "chirp-3-hd",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "speech_recognition",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chirp-3-hd"
    }
   ]
  },
  {
   "slug": "other/chronos-hermes-13b",
   "model_name": "chronos-hermes-13b",
   "display_name": "chronos-hermes-13b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Austism/chronos-hermes-13b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Austism/chronos-hermes-13b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chronos-hermes-13b"
    }
   ]
  },
  {
   "slug": "other/chronos-hermes-13b-v2",
   "model_name": "chronos-hermes-13b-v2",
   "display_name": "Chronos Hermes 13B v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/chronos-hermes-13b-v2"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/chronos-hermes-13b-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Chronos Hermes 13B v2"
    }
   ]
  },
  {
   "slug": "other/claudinio",
   "model_name": "claudinio",
   "display_name": "Claudinio",
   "vendor": "other",
   "pricing": [
    {
     "provider": "claudinio",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-05-12",
   "knowledge_cutoff": "2026-05",
   "max_input_tokens": 256000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claudinio"
    }
   ]
  },
  {
   "slug": "other/claudius",
   "model_name": "claudius",
   "display_name": "Claudius",
   "vendor": "other",
   "pricing": [
    {
     "provider": "claudinio",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-05-12",
   "knowledge_cutoff": "2026-05",
   "max_input_tokens": 256000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claudius"
    }
   ]
  },
  {
   "slug": "other/claw-high",
   "model_name": "claw-high",
   "display_name": "Claw High",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25.007"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-11",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claw High"
    }
   ]
  },
  {
   "slug": "other/claw-low",
   "model_name": "claw-low",
   "display_name": "Claw Low",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-11",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claw Low"
    }
   ]
  },
  {
   "slug": "other/claw-medium",
   "model_name": "claw-medium",
   "display_name": "Claw Medium",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-11",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Claw Medium"
    }
   ]
  },
  {
   "slug": "other/clip-ViT-B-32",
   "model_name": "clip-ViT-B-32",
   "display_name": "sentence-transformers/clip-ViT-B-32",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/clip-ViT-B-32"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/sentence-transformers/clip-ViT-B-32"
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "max_input_tokens": 77,
   "max_output_tokens": 77,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/sentence-transformers/clip-ViT-B-32",
    "sentence-transformers/clip-ViT-B-32"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sentence-transformers/clip-ViT-B-32"
    }
   ]
  },
  {
   "slug": "other/clip-ViT-B-32-multilingual-v1",
   "model_name": "clip-ViT-B-32-multilingual-v1",
   "display_name": "sentence-transformers/clip-ViT-B-32-multilingual-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/clip-ViT-B-32-multilingual-v1"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/sentence-transformers/clip-ViT-B-32-multilingual-v1"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/sentence-transformers/clip-ViT-B-32-multilingual-v1",
    "sentence-transformers/clip-ViT-B-32-multilingual-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sentence-transformers/clip-ViT-B-32-multilingual-v1"
    }
   ]
  },
  {
   "slug": "other/code-bison32k",
   "model_name": "code-bison32k",
   "display_name": "code-bison32k",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "code-bison32k"
    }
   ]
  },
  {
   "slug": "other/code-max",
   "model_name": "code-max",
   "display_name": "Code Max",
   "vendor": "other",
   "pricing": [],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2026-05-04",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "status": "beta",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Max"
    }
   ]
  },
  {
   "slug": "other/code-prime",
   "model_name": "code-prime",
   "display_name": "Code Prime",
   "vendor": "other",
   "pricing": [],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2026-05-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "beta",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Prime"
    }
   ]
  },
  {
   "slug": "other/code-standard",
   "model_name": "code-standard",
   "display_name": "Code Standard",
   "vendor": "other",
   "pricing": [],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2026-05-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "beta",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Code Standard"
    }
   ]
  },
  {
   "slug": "other/coding-router",
   "model_name": "coding-router",
   "display_name": "Coding Router",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "nanogpt/coding-router"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2026-05-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nanogpt/coding-router"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding Router"
    }
   ]
  },
  {
   "slug": "other/coding-router:high",
   "model_name": "coding-router:high",
   "display_name": "Coding Router High",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "nanogpt/coding-router:high"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2026-05-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nanogpt/coding-router:high"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding Router High"
    }
   ]
  },
  {
   "slug": "other/coding-router:low",
   "model_name": "coding-router:low",
   "display_name": "Coding Router Low",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "nanogpt/coding-router:low"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2026-05-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nanogpt/coding-router:low"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding Router Low"
    }
   ]
  },
  {
   "slug": "other/coding-router:max",
   "model_name": "coding-router:max",
   "display_name": "Coding Router Max",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "nanogpt/coding-router:max"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2026-05-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nanogpt/coding-router:max"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding Router Max"
    }
   ]
  },
  {
   "slug": "other/coding-router:medium",
   "model_name": "coding-router:medium",
   "display_name": "Coding Router Medium",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     },
     "provider_model_id": "nanogpt/coding-router:medium"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2026-05-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nanogpt/coding-router:medium"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding Router Medium"
    }
   ]
  },
  {
   "slug": "other/cogito-2.1:671b",
   "model_name": "cogito-2.1:671b",
   "display_name": "cogito-2.1:671b",
   "vendor": "other",
   "pricing": [],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-11-19",
   "max_input_tokens": 163840,
   "max_output_tokens": 32000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "cogito",
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cogito-2.1:671b"
    }
   ]
  },
  {
   "slug": "other/cogito-671b-v2-p1",
   "model_name": "cogito-671b-v2-p1",
   "display_name": "Cogito 671B v2.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/cogito/models/cogito-671b-v2-p1"
    }
   ],
   "max_input_tokens": 163840,
   "max_output_tokens": 163840,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/cogito/models/cogito-671b-v2-p1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cogito 671B v2.1"
    }
   ]
  },
  {
   "slug": "other/cogito-671b-v2.1",
   "model_name": "cogito-671b-v2.1",
   "display_name": "deepcogito/cogito-671b-v2.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "deepcogito/cogito-671b-v2.1"
    }
   ],
   "released_at": "2025-10-24",
   "max_input_tokens": 163840,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepcogito/cogito-671b-v2.1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepcogito/cogito-671b-v2.1"
    }
   ]
  },
  {
   "slug": "other/cogito-671b-v2.1-FP8",
   "model_name": "cogito-671b-v2.1-FP8",
   "display_name": "deepcogito/cogito-671b-v2.1-FP8",
   "vendor": "other",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "deepcogito/cogito-671b-v2.1-FP8"
    }
   ],
   "released_at": "2025-10-25",
   "max_input_tokens": 163840,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepcogito/cogito-671b-v2.1-FP8"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepcogito/cogito-671b-v2.1-FP8"
    }
   ]
  },
  {
   "slug": "other/cogito-v2-1-671b",
   "model_name": "cogito-v2-1-671b",
   "display_name": "Deep Cogito: Cogito v2.1 671B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "deepcogito/cogito-v2.1-671b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "deepcogito/cogito-v2.1-671b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "deepcogito/cogito-v2-1-671b"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-11-14",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "family": "cogito",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepcogito/cogito-v2-1-671b",
    "deepcogito/cogito-v2.1-671b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Deep Cogito: Cogito v2.1 671B"
    }
   ]
  },
  {
   "slug": "other/compound",
   "model_name": "compound",
   "display_name": "Compound",
   "vendor": "other",
   "pricing": [],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-09-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "groq",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "groq/compound"
   ],
   "intro_i18n": {
    "zh-CN": "Compound 是一个由 GroqCloud 支持的复合 AI 系统，基于多个公开模型构建，能够智能选择工具回答用户问题。",
    "zh-TW": "Compound 是一個由 GroqCloud 支援的複合式 AI 系統，整合多個公開模型，能智慧選擇工具來回應用戶查詢。",
    "ja-JP": "Compound は、GroqCloud 上でサポートされる複数の公開モデルを活用した複合 AI システムで、ユーザーの質問に対してツールを知的かつ選択的に使用して応答します。",
    "ru-RU": "Compound — это составная ИИ-система, работающая на базе нескольких общедоступных моделей в GroqCloud, которая интеллектуально и избирательно использует инструменты для ответа на запросы пользователей."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Compound"
    }
   ]
  },
  {
   "slug": "other/compound-mini",
   "model_name": "compound-mini",
   "display_name": "Compound Mini",
   "vendor": "other",
   "pricing": [],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-09-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "groq",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "groq/compound-mini"
   ],
   "intro_i18n": {
    "zh-CN": "Compound-mini 是一个由 GroqCloud 支持的复合 AI 系统，基于公开模型构建，能够智能选择工具回答用户问题。",
    "zh-TW": "Compound-mini 是一個由 GroqCloud 支援的複合式 AI 系統，整合多個公開模型，能智慧選擇工具來回應用戶查詢。",
    "ja-JP": "Compound-mini は、GroqCloud 上でサポートされる公開モデルを活用した複合 AI システムで、ユーザーの質問に対してツールを知的かつ選択的に使用して応答します。",
    "ru-RU": "Compound-mini — это составная ИИ-система, работающая на базе общедоступных моделей в GroqCloud, которая интеллектуально и избирательно использует инструменты для ответа на запросы пользователей."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Compound Mini"
    }
   ]
  },
  {
   "slug": "other/container",
   "model_name": "container",
   "display_name": "container",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.03"
      }
     }
    }
   ],
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "container"
    }
   ]
  },
  {
   "slug": "other/cosmos3-super-reasoner",
   "model_name": "cosmos3-super-reasoner",
   "display_name": "cosmos3-super-reasoner",
   "vendor": "other",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.089"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.266"
      }
     }
    }
   ],
   "released_at": "2026-06-02",
   "max_input_tokens": 256000,
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cosmos3-super-reasoner"
    }
   ]
  },
  {
   "slug": "other/creative",
   "model_name": "creative",
   "display_name": "creative",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.05"
      }
     },
     "provider_model_id": "ClarityAI/creative"
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ClarityAI/creative"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "creative"
    }
   ]
  },
  {
   "slug": "other/crystal",
   "model_name": "crystal",
   "display_name": "crystal",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.05"
      }
     },
     "provider_model_id": "ClarityAI/crystal"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ClarityAI/crystal"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "crystal"
    }
   ]
  },
  {
   "slug": "other/csm-1b",
   "model_name": "csm-1b",
   "display_name": "csm-1b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "7"
      }
     },
     "provider_model_id": "sesame/csm-1b"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_input": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sesame/csm-1b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "csm-1b"
    }
   ]
  },
  {
   "slug": "other/custom",
   "model_name": "custom",
   "display_name": "Custom Model",
   "vendor": "other",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2024-01-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "auto",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Custom Model"
    }
   ]
  },
  {
   "slug": "other/Cydonia-24B-v2",
   "model_name": "Cydonia-24B-v2",
   "display_name": "The Drummer Cydonia 24B v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1207"
      }
     },
     "provider_model_id": "TheDrummer/Cydonia-24B-v2"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-02-17",
   "max_input_tokens": 16384,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/Cydonia-24B-v2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "The Drummer Cydonia 24B v2"
    }
   ]
  },
  {
   "slug": "other/Cydonia-24B-v4",
   "model_name": "Cydonia-24B-v4",
   "display_name": "The Drummer Cydonia 24B v4",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2414"
      }
     },
     "provider_model_id": "TheDrummer/Cydonia-24B-v4"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-07-22",
   "max_input_tokens": 16384,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/Cydonia-24B-v4"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "The Drummer Cydonia 24B v4"
    }
   ]
  },
  {
   "slug": "other/Cydonia-24B-v4.1",
   "model_name": "Cydonia-24B-v4.1",
   "display_name": "TheDrummer: Cydonia 24B V4.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "thedrummer/cydonia-24b-v4.1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1207"
      }
     },
     "provider_model_id": "TheDrummer/Cydonia-24B-v4.1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "thedrummer/cydonia-24b-v4.1"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-09-27",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2024-04",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/Cydonia-24B-v4.1",
    "thedrummer/cydonia-24b-v4.1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TheDrummer: Cydonia 24B V4.1"
    }
   ]
  },
  {
   "slug": "other/Cydonia-24B-v4.3",
   "model_name": "Cydonia-24B-v4.3",
   "display_name": "The Drummer Cydonia 24B v4.3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1207"
      }
     },
     "provider_model_id": "TheDrummer/Cydonia-24B-v4.3"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-12-25",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/Cydonia-24B-v4.3"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "The Drummer Cydonia 24B v4.3"
    }
   ]
  },
  {
   "slug": "other/databricks-gte-large-en",
   "model_name": "databricks-gte-large-en",
   "display_name": "databricks-gte-large-en",
   "vendor": "other",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12999000000000001"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 8192,
   "model_type": "text_embedding",
   "capabilities": {},
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-gte-large-en"
    }
   ]
  },
  {
   "slug": "other/databricks-mpt-30b-instruct",
   "model_name": "databricks-mpt-30b-instruct",
   "display_name": "databricks-mpt-30b-instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.00002"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.00002"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-mpt-30b-instruct"
    }
   ]
  },
  {
   "slug": "other/databricks-mpt-7b-instruct",
   "model_name": "databricks-mpt-7b-instruct",
   "display_name": "databricks-mpt-7b-instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "databricks",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.50001"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://www.databricks.com/product/pricing/foundation-model-serving",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "databricks-mpt-7b-instruct"
    }
   ]
  },
  {
   "slug": "other/deepreasoning",
   "model_name": "deepreasoning",
   "display_name": "DeepReasoning",
   "vendor": "other",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.0505"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.101"
      }
     }
    }
   ],
   "released_at": "2025-02-25",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepReasoning"
    }
   ]
  },
  {
   "slug": "other/DianJin-R1-32B",
   "model_name": "DianJin-R1-32B",
   "display_name": "DianJin-R1-32B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29426264"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.17705056"
      }
     }
    }
   ],
   "released_at": "2025-04-25",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17761344",
     "new": "1.17705056"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29440336",
     "new": "0.29426264"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17843152",
     "new": "1.17761344"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29460788",
     "new": "0.29440336"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17967376",
     "new": "1.17843152"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29491844",
     "new": "0.29460788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17991464",
     "new": "1.17967376"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29497866",
     "new": "0.29491844"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17949696",
     "new": "1.17991464"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29487424",
     "new": "0.29497866"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.1774316",
     "new": "1.17949696"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2943579",
     "new": "0.29487424"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DianJin-R1-32B"
    }
   ]
  },
  {
   "slug": "other/dmind-1",
   "model_name": "dmind-1",
   "display_name": "DMind-1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "dmind/dmind-1"
    }
   ],
   "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
   "released_at": "2025-06-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "dmind/dmind-1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DMind-1"
    }
   ]
  },
  {
   "slug": "other/dmind-1-mini",
   "model_name": "dmind-1-mini",
   "display_name": "DMind-1-Mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "dmind/dmind-1-mini"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-06-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "dmind/dmind-1-mini"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DMind-1-Mini"
    }
   ]
  },
  {
   "slug": "other/dots.ocr",
   "model_name": "dots.ocr",
   "display_name": "dots.ocr",
   "vendor": "other",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "rednote-hilab/dots.ocr"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "rednote",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "rednote-hilab/dots.ocr"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "dots.ocr"
    }
   ]
  },
  {
   "slug": "other/Dracarys-72B-Instruct",
   "model_name": "Dracarys-72B-Instruct",
   "display_name": "Llama 3.1 70B Dracarys 2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "abacusai/Dracarys-72B-Instruct"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-08-02",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "abacusai/Dracarys-72B-Instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 70B Dracarys 2"
    }
   ]
  },
  {
   "slug": "other/DreamShaper",
   "model_name": "DreamShaper",
   "display_name": "DreamShaper",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0006"
      }
     },
     "provider_model_id": "Lykon/DreamShaper"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Lykon/DreamShaper"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DreamShaper"
    }
   ]
  },
  {
   "slug": "other/duo-chat-fable-5",
   "model_name": "duo-chat-fable-5",
   "display_name": "Agentic Chat (Claude Fable 5)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Claude model for creative writing, analysis, and controlled agent workflows",
   "released_at": "2026-06-09",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-fable",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (Claude Fable 5)"
    }
   ]
  },
  {
   "slug": "other/duo-chat-haiku-4-5",
   "model_name": "duo-chat-haiku-4-5",
   "display_name": "Agentic Chat (Claude Haiku 4.5)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Fast Claude model for responsive assistance, classification, and lightweight agents",
   "released_at": "2026-01-08",
   "knowledge_cutoff": "2025-02",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-haiku",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (Claude Haiku 4.5)"
    }
   ]
  },
  {
   "slug": "other/duo-chat-opus-4-5",
   "model_name": "duo-chat-opus-4-5",
   "display_name": "Agentic Chat (Claude Opus 4.5)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-01-08",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (Claude Opus 4.5)"
    }
   ]
  },
  {
   "slug": "other/duo-chat-opus-4-6",
   "model_name": "duo-chat-opus-4-6",
   "display_name": "Agentic Chat (Claude Opus 4.6)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-02-05",
   "knowledge_cutoff": "2025-05",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (Claude Opus 4.6)"
    }
   ]
  },
  {
   "slug": "other/duo-chat-opus-4-7",
   "model_name": "duo-chat-opus-4-7",
   "display_name": "Agentic Chat (Claude Opus 4.7)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-04-16",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (Claude Opus 4.7)"
    }
   ]
  },
  {
   "slug": "other/duo-chat-opus-4-8",
   "model_name": "duo-chat-opus-4-8",
   "display_name": "Agentic Chat (Claude Opus 4.8)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
   "released_at": "2026-05-28",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-opus",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (Claude Opus 4.8)"
    }
   ]
  },
  {
   "slug": "other/duo-chat-sonnet-4-5",
   "model_name": "duo-chat-sonnet-4-5",
   "display_name": "Agentic Chat (Claude Sonnet 4.5)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2026-01-08",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (Claude Sonnet 4.5)"
    }
   ]
  },
  {
   "slug": "other/duo-chat-sonnet-4-6",
   "model_name": "duo-chat-sonnet-4-6",
   "display_name": "Agentic Chat (Claude Sonnet 4.6)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
   "released_at": "2026-02-17",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (Claude Sonnet 4.6)"
    }
   ]
  },
  {
   "slug": "other/duo-chat-sonnet-5",
   "model_name": "duo-chat-sonnet-5",
   "display_name": "Agentic Chat (Claude Sonnet 5)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "gitlab",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Everyday Claude agent model for coding, planning, browsing, and general work",
   "released_at": "2026-06-30",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "claude-sonnet",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Agentic Chat (Claude Sonnet 5)"
    }
   ]
  },
  {
   "slug": "other/e2e",
   "model_name": "e2e",
   "display_name": "End-to-End Encrypted",
   "vendor": "other",
   "pricing": [],
   "intro": "TrustedRouter privacy routing alias for end-to-end encrypted provider routes where available.",
   "released_at": "2026-06-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "End-to-End Encrypted"
    }
   ]
  },
  {
   "slug": "other/e2ee-venice-uncensored-24b-p",
   "model_name": "e2ee-venice-uncensored-24b-p",
   "display_name": "Venice Uncensored 1.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     }
    }
   ],
   "released_at": "2026-03-18",
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Venice Uncensored 1.1"
    }
   ]
  },
  {
   "slug": "other/e5",
   "model_name": "e5",
   "display_name": "e5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.034249185"
      }
     }
    }
   ],
   "released_at": "2025-09-11",
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343112244",
     "new": "0.034249185"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0342979791",
     "new": "0.0343112244"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343242429",
     "new": "0.0342979791"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343104252",
     "new": "0.0343242429"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343199361",
     "new": "0.0343104252"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.03414291",
     "new": "0.0343199361"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "e5"
    }
   ]
  },
  {
   "slug": "other/e5-base-v2",
   "model_name": "e5-base-v2",
   "display_name": "Intfloat: E5-Base-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "intfloat/e5-base-v2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "intfloat/e5-base-v2"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/intfloat/e5-base-v2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true,
    "stream": true
   },
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/intfloat/e5-base-v2",
    "intfloat/e5-base-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Intfloat: E5-Base-v2"
    }
   ]
  },
  {
   "slug": "other/e5-instruct",
   "model_name": "e5-instruct",
   "display_name": "e5-instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.034249185"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02283279"
      }
     }
    }
   ],
   "released_at": "2025-04-27",
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228741496",
     "new": "0.02283279"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343112244",
     "new": "0.034249185"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228653194",
     "new": "0.0228741496"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0342979791",
     "new": "0.0343112244"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228828286",
     "new": "0.0228653194"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343242429",
     "new": "0.0342979791"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228736168",
     "new": "0.0228828286"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343104252",
     "new": "0.0343242429"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228799574",
     "new": "0.0228736168"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343199361",
     "new": "0.0343104252"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.02276194",
     "new": "0.0228799574"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.03414291",
     "new": "0.0343199361"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "e5-instruct"
    }
   ]
  },
  {
   "slug": "other/e5-large",
   "model_name": "e5-large",
   "display_name": "e5-large",
   "vendor": "other",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.034249185"
      }
     }
    }
   ],
   "released_at": "2025-09-11",
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343112244",
     "new": "0.034249185"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0342979791",
     "new": "0.0343112244"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343242429",
     "new": "0.0342979791"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343104252",
     "new": "0.0343242429"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343199361",
     "new": "0.0343104252"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.03414291",
     "new": "0.0343199361"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "e5-large"
    }
   ]
  },
  {
   "slug": "other/e5-large-instruct",
   "model_name": "e5-large-instruct",
   "display_name": "e5-large-instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.034249185"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02283279"
      }
     }
    }
   ],
   "released_at": "2025-04-27",
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228741496",
     "new": "0.02283279"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343112244",
     "new": "0.034249185"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228653194",
     "new": "0.0228741496"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0342979791",
     "new": "0.0343112244"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228828286",
     "new": "0.0228653194"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343242429",
     "new": "0.0342979791"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228736168",
     "new": "0.0228828286"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343104252",
     "new": "0.0343242429"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228799574",
     "new": "0.0228736168"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.0343199361",
     "new": "0.0343104252"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.02276194",
     "new": "0.0228799574"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.03414291",
     "new": "0.0343199361"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "e5-large-instruct"
    }
   ]
  },
  {
   "slug": "other/e5-large-v2",
   "model_name": "e5-large-v2",
   "display_name": "E5 Large v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "intfloat/e5-large-v2"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "intfloat/e5-large-v2"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepinfra/intfloat/e5-large-v2"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2023-05-19",
   "max_input_tokens": 512,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "text-embedding",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/intfloat/e5-large-v2",
    "intfloat/e5-large-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "E5 Large v2"
    }
   ]
  },
  {
   "slug": "other/efficient",
   "model_name": "efficient",
   "display_name": "Auto Efficient",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.325"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.95"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0325"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.40625"
      }
     },
     "provider_model_id": "kilo-auto/efficient"
    }
   ],
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kilo-auto/efficient"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Auto Efficient"
    }
   ]
  },
  {
   "slug": "other/elephant",
   "model_name": "elephant",
   "display_name": "Ling-2.6-flash",
   "vendor": "other",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2026-04-10",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ling-2.6-flash"
    }
   ]
  },
  {
   "slug": "other/elephant-alpha",
   "model_name": "elephant-alpha",
   "display_name": "elephant-alpha",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/elephant-alpha"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "openrouter/elephant-alpha"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "elephant-alpha"
    }
   ]
  },
  {
   "slug": "other/embed-v-4-0",
   "model_name": "embed-v-4-0",
   "display_name": "embed-v-4-0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://azuremarketplace.microsoft.com/pt-br/marketplace/apps/cohere.cohere-embed-4-offer?tab=PlansAndPrice",
   "max_input_tokens": 128000,
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "embed-v-4-0"
    }
   ]
  },
  {
   "slug": "other/embedding-2",
   "model_name": "embedding-2",
   "display_name": "embedding-2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0686"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0686"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "embedding-2"
    }
   ]
  },
  {
   "slug": "other/embedding-3",
   "model_name": "embedding-3",
   "display_name": "embedding-3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0686"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0686"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "embedding-3"
    }
   ]
  },
  {
   "slug": "other/embedding-v1",
   "model_name": "embedding-v1",
   "display_name": "embedding-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "embedding-v1"
    }
   ]
  },
  {
   "slug": "other/enhance",
   "model_name": "enhance",
   "display_name": "enhance",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/enhance"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/enhance"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "enhance"
    }
   ]
  },
  {
   "slug": "other/erase",
   "model_name": "erase",
   "display_name": "erase",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/erase"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/erase"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "erase"
    }
   ]
  },
  {
   "slug": "other/erase_foreground",
   "model_name": "erase_foreground",
   "display_name": "erase_foreground",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/erase_foreground"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/erase_foreground"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "erase_foreground"
    }
   ]
  },
  {
   "slug": "other/EuroLLM-22B-Instruct-2512",
   "model_name": "EuroLLM-22B-Instruct-2512",
   "display_name": "utter-project/EuroLLM-22B-Instruct-2512",
   "vendor": "other",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "utter-project/EuroLLM-22B-Instruct-2512"
    }
   ],
   "released_at": "2025-12-05",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "utter-project/EuroLLM-22B-Instruct-2512"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "utter-project/EuroLLM-22B-Instruct-2512"
    }
   ]
  },
  {
   "slug": "other/exa-answer",
   "model_name": "exa-answer",
   "display_name": "Exa (Answer)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-06-04",
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Exa (Answer)"
    }
   ]
  },
  {
   "slug": "other/exa-research",
   "model_name": "exa-research",
   "display_name": "Exa (Research)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-06-04",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Exa (Research)"
    }
   ]
  },
  {
   "slug": "other/exa-research-pro",
   "model_name": "exa-research-pro",
   "display_name": "Exa (Research Pro)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-06-04",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Exa (Research Pro)"
    }
   ]
  },
  {
   "slug": "other/expand",
   "model_name": "expand",
   "display_name": "expand",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/expand"
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/expand"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "expand"
    }
   ]
  },
  {
   "slug": "other/expert-model-zzkj",
   "model_name": "expert-model-zzkj",
   "display_name": "zzkj",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "69"
      }
     }
    }
   ],
   "released_at": "2025-02-17",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zzkj"
    }
   ]
  },
  {
   "slug": "other/expert-model-zzkj-genetics",
   "model_name": "expert-model-zzkj-genetics",
   "display_name": "zzkj-genetics",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "86"
      }
     }
    }
   ],
   "released_at": "2025-02-17",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zzkj-genetics"
    }
   ]
  },
  {
   "slug": "other/expert-model-zzkj-lite",
   "model_name": "expert-model-zzkj-lite",
   "display_name": "zzkj-lite",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    }
   ],
   "released_at": "2025-02-17",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zzkj-lite"
    }
   ]
  },
  {
   "slug": "other/expert-model-zzkj-think",
   "model_name": "expert-model-zzkj-think",
   "display_name": "zzkj-think",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "86"
      }
     }
    }
   ],
   "released_at": "2025-02-17",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zzkj-think"
    }
   ]
  },
  {
   "slug": "other/fare-20b",
   "model_name": "fare-20b",
   "display_name": "FARE-20B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/fare-20b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/fare-20b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FARE-20B"
    }
   ]
  },
  {
   "slug": "other/farui-plus",
   "model_name": "farui-plus",
   "display_name": "farui-plus",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.9"
      }
     }
    }
   ],
   "released_at": "2024-08-06",
   "max_input_tokens": 12000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "farui-plus"
    }
   ]
  },
  {
   "slug": "other/fast",
   "model_name": "fast",
   "display_name": "Fast",
   "vendor": "other",
   "pricing": [],
   "intro": "TrustedRouter speed routing alias that prefers low-latency healthy model endpoints.",
   "released_at": "2026-06-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Fast"
    }
   ]
  },
  {
   "slug": "other/fast-sdxl",
   "model_name": "fast-sdxl",
   "display_name": "Fast SDXL",
   "vendor": "other",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2023-07-26",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "stable-diffusion",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fal-ai/fast-sdxl"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Fast SDXL"
    }
   ]
  },
  {
   "slug": "other/fastgpt",
   "model_name": "fastgpt",
   "display_name": "Web Answer",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.5"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-08-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Web Answer"
    }
   ]
  },
  {
   "slug": "other/fibo",
   "model_name": "fibo",
   "display_name": "fibo",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/fibo"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/fibo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "fibo"
    }
   ]
  },
  {
   "slug": "other/fibo_edit",
   "model_name": "fibo_edit",
   "display_name": "fibo_edit",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/fibo_edit"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/fibo_edit"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "fibo_edit"
    }
   ]
  },
  {
   "slug": "other/fimbulvetr-11b-v2",
   "model_name": "fimbulvetr-11b-v2",
   "display_name": "fimbulvetr-11b-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "sao10k/fimbulvetr-11b-v2"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sao10k/fimbulvetr-11b-v2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "fimbulvetr-11b-v2"
    }
   ]
  },
  {
   "slug": "other/Fin-R1",
   "model_name": "Fin-R1",
   "display_name": "Fin-R1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29426264"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.17705056"
      }
     }
    }
   ],
   "released_at": "2025-03-21",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17761344",
     "new": "1.17705056"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29440336",
     "new": "0.29426264"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17843152",
     "new": "1.17761344"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29460788",
     "new": "0.29440336"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17967376",
     "new": "1.17843152"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29491844",
     "new": "0.29460788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17991464",
     "new": "1.17967376"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29497866",
     "new": "0.29491844"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.17949696",
     "new": "1.17991464"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29487424",
     "new": "0.29497866"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.1774316",
     "new": "1.17949696"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2943579",
     "new": "0.29487424"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Fin-R1"
    }
   ]
  },
  {
   "slug": "other/firefunction-v1",
   "model_name": "firefunction-v1",
   "display_name": "FireFunction V1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/firefunction-v1"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/firefunction-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FireFunction V1"
    }
   ]
  },
  {
   "slug": "other/firefunction-v2",
   "model_name": "firefunction-v2",
   "display_name": "FireFunction V2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/firefunction-v2"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/firefunction-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "FireFunction V2"
    }
   ]
  },
  {
   "slug": "other/firesearch-ocr-v6",
   "model_name": "firesearch-ocr-v6",
   "display_name": "Firesearch OCR V6",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/firesearch-ocr-v6"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/firesearch-ocr-v6"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Firesearch OCR V6"
    }
   ]
  },
  {
   "slug": "other/fireworks-asr-large",
   "model_name": "fireworks-asr-large",
   "display_name": "fireworks-asr-large",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "speech_recognition",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "fireworks-asr-large"
    }
   ]
  },
  {
   "slug": "other/fireworks-asr-v2",
   "model_name": "fireworks-asr-v2",
   "display_name": "fireworks-asr-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "speech_recognition",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "fireworks-asr-v2"
    }
   ]
  },
  {
   "slug": "other/fireworks/models/mirothinker-1p7",
   "model_name": "fireworks/models/mirothinker-1p7",
   "display_name": "MiroThinker-1.7",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mirothinker-1p7"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mirothinker-1p7"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiroThinker-1.7"
    }
   ]
  },
  {
   "slug": "other/fireworks/models/molmo2-4b",
   "model_name": "fireworks/models/molmo2-4b",
   "display_name": "Molmo2-4B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/molmo2-4b"
    }
   ],
   "max_input_tokens": 36864,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/molmo2-4b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Molmo2-4B"
    }
   ]
  },
  {
   "slug": "other/fireworks/models/molmo2-8b",
   "model_name": "fireworks/models/molmo2-8b",
   "display_name": "Molmo2-8B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/molmo2-8b"
    }
   ],
   "max_input_tokens": 36864,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/molmo2-8b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Molmo2-8B"
    }
   ]
  },
  {
   "slug": "other/fireworks/models/paddleocr-vl-1-6",
   "model_name": "fireworks/models/paddleocr-vl-1-6",
   "display_name": "PaddleOCR VL 1.6",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "accounts/fireworks/models/paddleocr-vl-1-6"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/paddleocr-vl-1-6"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PaddleOCR VL 1.6"
    }
   ]
  },
  {
   "slug": "other/flan-t5-xl-3b",
   "model_name": "flan-t5-xl-3b",
   "display_name": "flan-t5-xl-3b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "flan-t5-xl-3b"
    }
   ]
  },
  {
   "slug": "other/free",
   "model_name": "free",
   "display_name": "Kilo Auto Free",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "kilo-auto/free"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/free"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2026-03-15",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kilo-auto/free",
    "openrouter/free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kilo Auto Free"
    }
   ]
  },
  {
   "slug": "other/frontier",
   "model_name": "frontier",
   "display_name": "Kilo Auto Frontier",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "6.25"
      }
     },
     "provider_model_id": "kilo-auto/frontier"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2026-03-15",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kilo-auto/frontier"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kilo Auto Frontier"
    }
   ]
  },
  {
   "slug": "other/fugu",
   "model_name": "fugu",
   "display_name": "Fugu",
   "vendor": "other",
   "pricing": [],
   "intro": "Multi-agent model for routing expert agents across complex analytical tasks",
   "released_at": "2026-06-15",
   "max_input_tokens": 1000000,
   "max_output_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "fugu",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Fugu"
    }
   ]
  },
  {
   "slug": "other/fugu-ultra",
   "model_name": "fugu-ultra",
   "display_name": "Fugu Ultra",
   "vendor": "other",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "sakana/fugu-ultra"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "31.5"
      }
     },
     "provider_model_id": "sakana/fugu-ultra"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "sakana/fugu-ultra"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.5758"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "45.4545"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.5152"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "sakana/fugu-ultra"
    },
    {
     "provider": "sakana",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "fugu-ultra-20260615",
     "tracks": [
      {
       "label": ">272K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "sakana/fugu-ultra"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "sakana/fugu-ultra",
     "tracks": [
      {
       "label": ">272.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "1.5",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 272001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Quality-first multi-agent model for hard research, analysis, and competitions",
   "released_at": "2026-06-21",
   "max_input_tokens": 1000000,
   "max_output_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "aura",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fugu-ultra-20260615",
    "sakana/fugu-ultra"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Fugu Ultra"
    }
   ]
  },
  {
   "slug": "other/fusion",
   "model_name": "fusion",
   "display_name": "Fusion",
   "vendor": "other",
   "pricing": [],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2026-06-13",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "openrouter/fusion"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Fusion"
    }
   ]
  },
  {
   "slug": "other/gen_fill",
   "model_name": "gen_fill",
   "display_name": "gen_fill",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/gen_fill"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/gen_fill"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gen_fill"
    }
   ]
  },
  {
   "slug": "other/goliath-120b",
   "model_name": "goliath-120b",
   "display_name": "Goliath 120B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6.5625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.375"
      }
     },
     "provider_model_id": "alpindale/goliath-120b"
    }
   ],
   "capabilities": {},
   "max_input_tokens": 6144,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "deprecated": true,
   "released_at": "2023-11-10",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alpindale/goliath-120b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Goliath 120B"
    }
   ]
  },
  {
   "slug": "other/greg-1-mini",
   "model_name": "greg-1-mini",
   "display_name": "Greg 1 Mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     }
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2026-01-27",
   "max_input_tokens": 229376,
   "max_output_tokens": 229376,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Greg 1 Mini"
    }
   ]
  },
  {
   "slug": "other/greg-2-super",
   "model_name": "greg-2-super",
   "display_name": "Greg 2 Super",
   "vendor": "other",
   "pricing": [
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "crofai/greg-2-super"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2026-06-14",
   "max_input_tokens": 229376,
   "max_output_tokens": 229376,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "crofai/greg-2-super"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Greg 2 Super"
    }
   ]
  },
  {
   "slug": "other/greg-2-ultra",
   "model_name": "greg-2-ultra",
   "display_name": "Greg 2 Ultra",
   "vendor": "other",
   "pricing": [
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "crofai/greg-2-ultra"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2026-06-14",
   "max_input_tokens": 229376,
   "max_output_tokens": 229376,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "crofai/greg-2-ultra"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Greg 2 Ultra"
    }
   ]
  },
  {
   "slug": "other/greg-rp",
   "model_name": "greg-rp",
   "display_name": "Greg (Roleplay)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2026-01-27",
   "max_input_tokens": 229376,
   "max_output_tokens": 229376,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Greg (Roleplay)"
    }
   ]
  },
  {
   "slug": "other/gte-base",
   "model_name": "gte-base",
   "display_name": "Thenlper: GTE-Base",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "thenlper/gte-base"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "thenlper/gte-base"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/thenlper/gte-base"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true,
    "stream": true
   },
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/thenlper/gte-base",
    "thenlper/gte-base"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Thenlper: GTE-Base"
    }
   ]
  },
  {
   "slug": "other/gte-large",
   "model_name": "gte-large",
   "display_name": "Thenlper: GTE-Large",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "thenlper/gte-large"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "thenlper/gte-large"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepinfra/thenlper/gte-large"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true,
    "stream": true
   },
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/thenlper/gte-large",
    "thenlper/gte-large"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Thenlper: GTE-Large"
    }
   ]
  },
  {
   "slug": "other/gte-large-en-v1.5",
   "model_name": "gte-large-en-v1.5",
   "display_name": "GTE Large (v1.5)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2024-03-27",
   "max_input_tokens": 8192,
   "max_output_tokens": 1024,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "text-embedding",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GTE Large (v1.5)"
    }
   ]
  },
  {
   "slug": "other/gte-rerank-v2",
   "model_name": "gte-rerank-v2",
   "display_name": "gte-rerank-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "gte-rerank-v2"
    }
   ]
  },
  {
   "slug": "other/healer-alpha",
   "model_name": "healer-alpha",
   "display_name": "healer-alpha",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/healer-alpha"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 32000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "audio_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "openrouter/healer-alpha"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "healer-alpha"
    }
   ]
  },
  {
   "slug": "other/hermes-high",
   "model_name": "hermes-high",
   "display_name": "Hermes High",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25.007"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-11",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes High"
    }
   ]
  },
  {
   "slug": "other/hermes-low",
   "model_name": "hermes-low",
   "display_name": "Hermes Low",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-11",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes Low"
    }
   ]
  },
  {
   "slug": "other/hermes-medium",
   "model_name": "hermes-medium",
   "display_name": "Hermes Medium",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-11",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hermes Medium"
    }
   ]
  },
  {
   "slug": "other/hermes3-405b",
   "model_name": "hermes3-405b",
   "display_name": "hermes3-405b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "hermes3-405b"
    }
   ]
  },
  {
   "slug": "other/hermes3-70b",
   "model_name": "hermes3-70b",
   "display_name": "hermes3-70b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "hermes3-70b"
    }
   ]
  },
  {
   "slug": "other/hermes3-8b",
   "model_name": "hermes3-8b",
   "display_name": "hermes3-8b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "lambda",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "hermes3-8b"
    }
   ]
  },
  {
   "slug": "other/HiDream-I1-Dev",
   "model_name": "HiDream-I1-Dev",
   "display_name": "HiDream-I1-Dev",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.0045"
      }
     },
     "provider_model_id": "HiDream-ai/HiDream-I1-Dev"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "HiDream-ai/HiDream-I1-Dev"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HiDream-I1-Dev"
    }
   ]
  },
  {
   "slug": "other/HiDream-I1-Fast",
   "model_name": "HiDream-I1-Fast",
   "display_name": "HiDream-I1-Fast",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.0032"
      }
     },
     "provider_model_id": "HiDream-ai/HiDream-I1-Fast"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "HiDream-ai/HiDream-I1-Fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HiDream-I1-Fast"
    }
   ]
  },
  {
   "slug": "other/HiDream-I1-Full",
   "model_name": "HiDream-I1-Full",
   "display_name": "HiDream-I1-Full",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.009"
      }
     },
     "provider_model_id": "HiDream-ai/HiDream-I1-Full"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "HiDream-ai/HiDream-I1-Full"
   ],
   "intro_i18n": {
    "zh-CN": "HiDream-I1 是 HiDream 发布的新一代开源基础图像生成模型，拥有 170 亿参数（Flux 为 120 亿），能够在数秒内提供行业领先的图像质量。",
    "zh-TW": "HiDream-I1 是 HiDream 推出的全新開源基礎影像生成模型。擁有 17B 參數（Flux 為 12B），能在數秒內提供業界領先的影像品質。",
    "ja-JP": "HiDream-I1は、HiDreamがリリースした新しいオープンソースのベース画像生成モデルです。17Bパラメータ（Fluxは12B）を持ち、業界トップクラスの画像品質を数秒で提供します。",
    "ru-RU": "HiDream-I1 — это новая открытая базовая модель генерации изображений, выпущенная HiDream. С 17 миллиардами параметров (Flux имеет 12 миллиардов) она обеспечивает лидирующее в отрасли качество изображений за считанные секунды."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HiDream-I1-Full"
    }
   ]
  },
  {
   "slug": "other/HiggsAudioV2.5",
   "model_name": "HiggsAudioV2.5",
   "display_name": "HiggsAudioV2.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "20"
      }
     },
     "provider_model_id": "bosonai/HiggsAudioV2.5"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "bosonai/HiggsAudioV2.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HiggsAudioV2.5"
    }
   ]
  },
  {
   "slug": "other/holo2-30b-a3b",
   "model_name": "holo2-30b-a3b",
   "display_name": "holo2-30b-a3b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    }
   ],
   "released_at": "2025-12-10",
   "max_input_tokens": 22000,
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "holo2-30b-a3b"
    }
   ]
  },
  {
   "slug": "other/Holo3-35B-A3B",
   "model_name": "Holo3-35B-A3B",
   "display_name": "Holo3-35B-A3B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "holo3-35b-a3b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Hcompany/Holo3-35B-A3B"
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-01-01",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "deprecated": true,
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Hcompany/Holo3-35B-A3B",
    "holo3-35b-a3b",
    "holo3-35b-a3b:thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Holo3-35B-A3B"
    }
   ]
  },
  {
   "slug": "other/huggingface/distilbert-sst-2-int8",
   "model_name": "huggingface/distilbert-sst-2-int8",
   "display_name": "DistilBERT SST-2 INT8",
   "vendor": "other",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.026"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/huggingface/distilbert-sst-2-int8"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.026"
      }
     },
     "provider_model_id": "@cf/huggingface/distilbert-sst-2-int8"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-04-03",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "distilbert",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/huggingface/distilbert-sst-2-int8",
    "workers-ai/@cf/huggingface/distilbert-sst-2-int8"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DistilBERT SST-2 INT8"
    }
   ]
  },
  {
   "slug": "other/hunter-alpha",
   "model_name": "hunter-alpha",
   "display_name": "hunter-alpha",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/hunter-alpha"
    }
   ],
   "max_input_tokens": 1048576,
   "max_output_tokens": 32000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "openrouter/hunter-alpha"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "hunter-alpha"
    }
   ]
  },
  {
   "slug": "other/image-1",
   "model_name": "image-1",
   "display_name": "image-1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "40"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "40"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "image-1"
    }
   ]
  },
  {
   "slug": "other/image-1-edit",
   "model_name": "image-1-edit",
   "display_name": "image-1-edit",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "120"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "120"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "image-1-edit"
    }
   ]
  },
  {
   "slug": "other/image-1-watermark",
   "model_name": "image-1-watermark",
   "display_name": "image-1-watermark",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "image-1-watermark"
    }
   ]
  },
  {
   "slug": "other/imagegeneration@002",
   "model_name": "imagegeneration@002",
   "display_name": "imagegeneration@002",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagegeneration@002"
    }
   ]
  },
  {
   "slug": "other/imagegeneration@005",
   "model_name": "imagegeneration@005",
   "display_name": "imagegeneration@005",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagegeneration@005"
    }
   ]
  },
  {
   "slug": "other/imagegeneration@006",
   "model_name": "imagegeneration@006",
   "display_name": "imagegeneration@006",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "imagegeneration@006"
    }
   ]
  },
  {
   "slug": "other/INTELLECT-3",
   "model_name": "INTELLECT-3",
   "display_name": "INTELLECT 3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.219"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.202"
      }
     },
     "provider_model_id": "intellect-3"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "prime-intellect/intellect-3"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "PrimeIntellect/INTELLECT-3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "prime-intellect/intellect-3"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "prime-intellect/intellect-3"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-11-26",
   "knowledge_cutoff": "2025-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "deprecated": true,
   "status": "deprecated",
   "model_type": "text_generation",
   "family": "glm",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "PrimeIntellect/INTELLECT-3",
    "intellect-3",
    "prime-intellect/intellect-3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "INTELLECT 3"
    }
   ]
  },
  {
   "slug": "other/interfaze-beta",
   "model_name": "interfaze-beta",
   "display_name": "Interfaze Beta",
   "vendor": "other",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "interfaze/interfaze-beta"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-10-07",
   "max_input_tokens": 1000000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "interfaze/interfaze-beta"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Interfaze Beta"
    }
   ]
  },
  {
   "slug": "other/intern-latest",
   "model_name": "intern-latest",
   "display_name": "Intern",
   "vendor": "other",
   "pricing": [
    {
     "provider": "internlm",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2026-05-22",
   "max_input_tokens": 262144,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "默认指向我们最新发布的Intern系列模型，目前设置为intern-s2-preview。",
    "zh-TW": "默認指向我們最新發布的 Intern 系列模型，目前設置為 intern-s2-preview。",
    "ja-JP": "デフォルトでは、現在intern-s2-previewに設定されている最新のInternシリーズモデルを指します。",
    "ru-RU": "По умолчанию указывает на нашу последнюю выпущенную модель серии Intern, в настоящее время установленную на intern-s2-preview."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Intern"
    }
   ]
  },
  {
   "slug": "other/intern-s1",
   "model_name": "intern-s1",
   "display_name": "Intern-S1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "internlm",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2025-07-26",
   "max_input_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "开源多模态推理模型不仅展现了强大的通用能力，还在广泛的科学任务中实现了最先进的性能。",
    "zh-TW": "這款開源多模態推理模型不僅展現了強大的通用能力，還在廣泛的科學任務中達到了最先進的性能。",
    "ja-JP": "オープンソースのマルチモーダル推論モデルは、汎用能力が強力であるだけでなく、幅広い科学的タスクで最先端の性能を達成しています。",
    "ru-RU": "Открытая мультимодальная модель рассуждений демонстрирует не только сильные универсальные способности, но и достигает передовых результатов в широком спектре научных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Intern-S1"
    }
   ]
  },
  {
   "slug": "other/intern-s1-mini",
   "model_name": "intern-s1-mini",
   "display_name": "Intern-S1-Mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "internlm",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2025-08-20",
   "max_input_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "一个轻量级多模态大模型，具备强大的科学推理能力。",
    "zh-TW": "一款輕量級多模態大模型，具備強大的科學推理能力。",
    "ja-JP": "科学的推論能力に優れた軽量マルチモーダル大規模モデル。",
    "ru-RU": "Легковесная мультимодальная большая модель с сильными научными способностями к рассуждению."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Intern-S1-Mini"
    }
   ]
  },
  {
   "slug": "other/intern-s1-pro",
   "model_name": "intern-s1-pro",
   "display_name": "Intern-S1-Pro",
   "vendor": "other",
   "pricing": [
    {
     "provider": "internlm",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2026-02-04",
   "max_input_tokens": 262144,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "我们推出了最先进的开源多模态推理模型，目前在整体性能上是表现最好的开源多模态大语言模型。",
    "zh-TW": "我們推出了最先進的開源多模態推理模型，目前在整體性能上是表現最好的開源多模態大語言模型。",
    "ja-JP": "私たちは、最も高度なオープンソースのマルチモーダル推論モデルを発表しました。現在、全体的な性能においてトップのオープンソースマルチモーダル大規模言語モデルです。",
    "ru-RU": "Мы запустили нашу самую продвинутую открытую мультимодальную модель рассуждений, которая в настоящее время является лучшей среди открытых мультимодальных больших языковых моделей по общим показателям."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Intern-S1-Pro"
    }
   ]
  },
  {
   "slug": "other/intern-s2-preview",
   "model_name": "intern-s2-preview",
   "display_name": "Intern-S2-Preview",
   "vendor": "other",
   "pricing": [
    {
     "provider": "internlm",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2026-05-22",
   "max_input_tokens": 262144,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "我们新发布的35B-A3B科学多模态推理模型，支持256K上下文窗口。通过任务扩展和架构优化，专为增强科学发现和通用代理能力而设计。",
    "zh-TW": "我們新發布的35B-A3B科學多模態推理模型，支持256K上下文窗口。通過任務擴展和架構優化，專為增強科學發現和通用代理能力而設計。",
    "ja-JP": "新たにリリースされた35B-A3B科学マルチモーダル推論モデルで、256Kコンテキストウィンドウをサポートします。タスクスケーリングとアーキテクチャの最適化を通じて、科学的発見と汎用エージェント機能を強化するよう設計されています。",
    "ru-RU": "Наша недавно выпущенная научная мультимодальная модель рассуждений с 35B-A3B поддерживает контекстное окно на 256K. Благодаря масштабированию задач и оптимизации архитектуры, она специально разработана для улучшения научных открытий и универсальных агентных возможностей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Intern-S2-Preview"
    }
   ]
  },
  {
   "slug": "other/internvl2.5-38b-mpo",
   "model_name": "internvl2.5-38b-mpo",
   "display_name": "InternVL2.5 38B MPO",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "InternVL2.5 38B MPO 是一款多模态预训练模型，专注于复杂图文推理任务。",
    "zh-TW": "InternVL2.5 38B MPO 是一款多模態預訓練模型，專為複雜圖文推理任務設計。",
    "ja-JP": "InternVL2.5 38B MPO は、複雑な画像と言語の推論に対応するマルチモーダル事前学習モデルです。",
    "ru-RU": "InternVL2.5 38B MPO — мультимодальная предварительно обученная модель для сложного логического вывода на основе изображений и текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "InternVL2.5 38B MPO"
    }
   ]
  },
  {
   "slug": "other/internvl3-14b",
   "model_name": "internvl3-14b",
   "display_name": "InternVL3 14B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "InternVL3 14B 是一款中等规模的多模态模型，在性能与成本之间取得平衡。",
    "zh-TW": "InternVL3 14B 是一款中型多模態模型，在效能與成本之間取得平衡。",
    "ja-JP": "InternVL3 14B は、性能とコストのバランスに優れた中規模マルチモーダルモデルです。",
    "ru-RU": "InternVL3 14B — мультимодальная модель среднего размера, обеспечивающая баланс между производительностью и стоимостью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "InternVL3 14B"
    }
   ]
  },
  {
   "slug": "other/internvl3-1b",
   "model_name": "internvl3-1b",
   "display_name": "InternVL3 1B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "InternVL3 1B 是一款轻量级多模态模型，适用于资源受限的部署场景。",
    "zh-TW": "InternVL3 1B 是一款輕量級多模態模型，適合資源受限的部署場景。",
    "ja-JP": "InternVL3 1B は、リソース制約のある環境向けの軽量マルチモーダルモデルです。",
    "ru-RU": "InternVL3 1B — легковесная мультимодальная модель для развертывания в условиях ограниченных ресурсов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "InternVL3 1B"
    }
   ]
  },
  {
   "slug": "other/internvl3-38b",
   "model_name": "internvl3-38b",
   "display_name": "InternVL3 38B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/internvl3-38b"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/internvl3-38b"
   ],
   "intro_i18n": {
    "zh-CN": "InternVL3 38B 是一款大型开源多模态模型，专注于高精度图文理解。",
    "zh-TW": "InternVL3 38B 是一款大型開源多模態模型，專為高準確度圖文理解任務設計。",
    "ja-JP": "InternVL3 38B は、高精度な画像と言語の理解に対応する大規模オープンソースマルチモーダルモデルです。",
    "ru-RU": "InternVL3 38B — крупная открытая мультимодальная модель для высокоточного понимания изображений и текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "InternVL3 38B"
    }
   ]
  },
  {
   "slug": "other/internvl3-78b",
   "model_name": "internvl3-78b",
   "display_name": "InternVL3 78B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/internvl3-78b"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/internvl3-78b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "InternVL3 78B"
    }
   ]
  },
  {
   "slug": "other/InternVL3-78B-TEE",
   "model_name": "InternVL3-78B-TEE",
   "display_name": "InternVL3 78B TEE",
   "vendor": "other",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     },
     "provider_model_id": "OpenGVLab/InternVL3-78B-TEE"
    }
   ],
   "released_at": "2025-01-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "opengvlab",
   "capabilities": {
    "vision": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "OpenGVLab/InternVL3-78B-TEE"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "InternVL3 78B TEE"
    }
   ]
  },
  {
   "slug": "other/internvl3-8b",
   "model_name": "internvl3-8b",
   "display_name": "InternVL3 8B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/internvl3-8b"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/internvl3-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "InternVL3 8B"
    }
   ]
  },
  {
   "slug": "other/internvl3.5-241b-a28b",
   "model_name": "internvl3.5-241b-a28b",
   "display_name": "InternVL3.5-241B-A28B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "internlm",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2025-08-28",
   "max_input_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "我们新发布的多模态大模型，增强了图像与文本理解以及长序列图像理解能力，性能可媲美领先的闭源模型。",
    "zh-TW": "我們新發布的多模態大模型，增強了圖像與文本的理解能力以及長序列圖像理解能力，性能可媲美領先的閉源模型。",
    "ja-JP": "新たにリリースされたマルチモーダル大規模モデルは、画像とテキストの理解および長いシーケンスの画像理解能力を強化し、主要なクローズドソースモデルに匹敵する性能を達成しています。",
    "ru-RU": "Наша недавно выпущенная мультимодальная большая модель обладает улучшенным пониманием изображений и текста, а также способностями к долгосрочному восприятию изображений, достигая производительности, сопоставимой с ведущими закрытыми моделями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "InternVL3.5-241B-A28B"
    }
   ]
  },
  {
   "slug": "other/internvl3.5-latest",
   "model_name": "internvl3.5-latest",
   "display_name": "InternVL3.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "internlm",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2025-08-28",
   "max_input_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "默认指向InternVL3.5系列的最新模型，目前设置为internvl3.5-241b-a28b。",
    "zh-TW": "默認指向 InternVL3.5 系列的最新模型，目前設置為 internvl3.5-241b-a28b。",
    "ja-JP": "デフォルトでは、現在internvl3.5-241b-a28bに設定されているInternVL3.5シリーズの最新モデルを指します。",
    "ru-RU": "По умолчанию указывает на последнюю модель серии InternVL3.5, в настоящее время установленную на internvl3.5-241b-a28b."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "InternVL3.5"
    }
   ]
  },
  {
   "slug": "other/intfloat-e5-base-v2",
   "model_name": "intfloat-e5-base-v2",
   "display_name": "DeepInfra: intfloat/e5-base-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/intfloat-e5-base-v2"
    }
   ],
   "released_at": "2024-01-10",
   "max_input_tokens": 512,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/intfloat-e5-base-v2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "DeepInfra: intfloat/e5-base-v2"
    }
   ]
  },
  {
   "slug": "other/irag-1.0",
   "model_name": "irag-1.0",
   "display_name": "ERNIE iRAG",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.020588"
      }
     }
    }
   ],
   "released_at": "2025-02-05",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "ERNIE iRAG 是一款图像检索增强生成模型，支持图像搜索、图文检索与内容生成任务。",
    "zh-TW": "ERNIE iRAG 是一款圖像檢索增強生成模型，支援圖像搜尋、圖文檢索與內容生成任務。",
    "ja-JP": "ERNIE iRAG は、画像検索、画像と言語の検索、コンテンツ生成に対応する画像検索拡張生成モデルです。",
    "ru-RU": "ERNIE iRAG — модель генерации с дополнением через поиск изображений, предназначенная для поиска изображений, извлечения информации из изображений и текста, а также генерации контента."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ERNIE iRAG"
    }
   ]
  },
  {
   "slug": "other/jais-13b-chat",
   "model_name": "jais-13b-chat",
   "display_name": "jais-13b-chat",
   "vendor": "other",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "500"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2000"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "jais-13b-chat"
    }
   ]
  },
  {
   "slug": "other/jais-30b-chat",
   "model_name": "jais-30b-chat",
   "display_name": "JAIS 30b Chat",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3200"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9710"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3200"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9710"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "core42/jais-30b-chat"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2023-08-30",
   "knowledge_cutoff": "2023-03",
   "max_input_tokens": 8192,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "jais",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true
   },
   "docs_url": "https://azure.microsoft.com/en-us/products/ai-services/ai-foundry/models/jais-30b-chat",
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "core42/jais-30b-chat"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "JAIS 30b Chat"
    }
   ]
  },
  {
   "slug": "other/japanese-stable-diffusion-xl",
   "model_name": "japanese-stable-diffusion-xl",
   "display_name": "japanese-stable-diffusion-xl",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.00013"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.00013"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "japanese-stable-diffusion-xl"
    }
   ]
  },
  {
   "slug": "other/K-EXAONE-236B-A23B",
   "model_name": "K-EXAONE-236B-A23B",
   "display_name": "LGAI-EXAONE/K-EXAONE-236B-A23B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "friendli",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "LGAI-EXAONE/K-EXAONE-236B-A23B"
    }
   ],
   "released_at": "2025-12-31",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "LGAI-EXAONE/K-EXAONE-236B-A23B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LGAI-EXAONE/K-EXAONE-236B-A23B"
    }
   ]
  },
  {
   "slug": "other/K2-Think",
   "model_name": "K2-Think",
   "display_name": "K2-Think",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.68"
      }
     },
     "provider_model_id": "LLM360/K2-Think"
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2025-07-26",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "LLM360/K2-Think"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "K2-Think"
    }
   ]
  },
  {
   "slug": "other/k2p5",
   "model_name": "k2p5",
   "display_name": "Kimi K2.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kimi-for-coding",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2026-01",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.5"
    }
   ]
  },
  {
   "slug": "other/k2p6",
   "model_name": "k2p6",
   "display_name": "Kimi K2.6",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kimi-for-coding",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Kimi reasoning model for long-horizon research, planning, and tool use",
   "released_at": "2026-04",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.6"
    }
   ]
  },
  {
   "slug": "other/k2p7",
   "model_name": "k2p7",
   "display_name": "Kimi K2.7 Code",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kimi-for-coding",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
   "released_at": "2026-06-12",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kimi K2.7 Code"
    }
   ]
  },
  {
   "slug": "other/kat-coder",
   "model_name": "kat-coder",
   "display_name": "kat-coder",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kat-coder"
    }
   ]
  },
  {
   "slug": "other/KAT-Coder-Air-V1",
   "model_name": "KAT-Coder-Air-V1",
   "display_name": "KAT Coder Air V1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-10-28",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "KAT-Coder 系列中的轻量化版本，专为 Agentic Coding 设计，全面覆盖各类编程任务与场景。通过大规模基于智能体的强化学习，实现智能行为涌现，在编码性能上显著优于同类模型。",
    "zh-TW": "KAT-Coder 系列中的輕量版，專為 Agentic Coding 設計，完整覆蓋多樣程式開發任務與情境。藉由大規模基於智能體的強化學習，實現智能行為的湧現，程式效能大幅超越同級模型。",
    "ja-JP": "KAT-Coder シリーズの軽量版で、エージェントコーディング向けに特化されています。多様なプログラミングタスクとシナリオを幅広くカバーし、大規模エージェント強化学習により知的行動の創発を実現し、同等モデルを大きく上回るコーディング性能を発揮します。",
    "ru-RU": "Облегчённая версия серии KAT-Coder. Специально разработана для Agentic Coding и охватывает широкий спектр программных задач и сценариев. Благодаря крупномасштабному агентному обучению с подкреплением демонстрирует возникновение интеллектуального поведения и значительно превосходит сопоставимые модели по качеству кода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "KAT Coder Air V1"
    }
   ]
  },
  {
   "slug": "other/kat-coder-air-v2.5",
   "model_name": "kat-coder-air-v2.5",
   "display_name": "KAT-Coder-Air-V2.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.027"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.135"
      }
     },
     "provider_model_id": "kuaishou/kat-coder-air-v2.5"
    }
   ],
   "released_at": "2026-07-08",
   "max_input_tokens": 256000,
   "capabilities": {
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kuaishou/kat-coder-air-v2.5"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "zenmux",
     "charge": "cache_read",
     "old": "0.03",
     "new": "0.027"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "zenmux",
     "charge": "completion",
     "old": "0.6",
     "new": "0.54"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "zenmux",
     "charge": "prompt",
     "old": "0.15",
     "new": "0.135"
    },
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "KAT-Coder-Air-V2.5"
    }
   ]
  },
  {
   "slug": "other/KAT-Coder-Exp-72B-1010",
   "model_name": "KAT-Coder-Exp-72B-1010",
   "display_name": "KAT Coder Exp 72B 1010",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-10-28",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "structured_output": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "KAT-Coder-Exp-72B 是 KAT-Coder 系列的强化学习创新实验版本，在 SWE-Bench verified 基准上取得 74.6% 的卓越成绩，刷新开源模型记录。该模型专注于 Agentic Coding，目前仅支持 SWE-Agent 框架，但也可用于简单对话。",
    "zh-TW": "KAT-Coder-Exp-72B 是 KAT-Coder 系列中專注 RL 創新的實驗版本，在 SWE-Bench verified 基準上達成 74.6% 的亮眼成績，刷新開源模型紀錄。其專注於 Agentic Coding，目前僅支援 SWE-Agent scaffold，也可用於簡易對話。",
    "ja-JP": "KAT-Coder-Exp-72B は KAT-Coder シリーズの強化学習実験モデルで、SWE-Bench verified ベンチマークで 74.6% の記録的性能を達成し、オープンソースモデルの新記録を樹立しました。エージェントコーディングに特化しており、現在は SWE-Agent フレームワークのみをサポートしますが、簡単な対話にも利用できます。",
    "ru-RU": "KAT-Coder-Exp-72B — экспериментальная версия серии KAT-Coder с инновациями в области RL. Показывает выдающийся результат 74.6% на бенчмарке SWE-Bench verified, установив новый рекорд для открытых моделей. Сфокусирована на Agentic Coding и в настоящее время поддерживает только SWE-Agent scaffold, но также подходит для простых диалогов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "KAT Coder Exp 72B 1010"
    }
   ]
  },
  {
   "slug": "other/kat-coder-pro-v2.5",
   "model_name": "kat-coder-pro-v2.5",
   "display_name": "KAT-Coder-Pro-V2.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.776"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.444"
      }
     },
     "provider_model_id": "kuaishou/kat-coder-pro-v2.5"
    }
   ],
   "released_at": "2026-07-08",
   "max_input_tokens": 256000,
   "capabilities": {
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kuaishou/kat-coder-pro-v2.5"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "zenmux",
     "charge": "cache_read",
     "old": "0.15",
     "new": "0.09"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "zenmux",
     "charge": "completion",
     "old": "2.96",
     "new": "1.776"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "zenmux",
     "charge": "prompt",
     "old": "0.74",
     "new": "0.444"
    },
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "KAT-Coder-Pro-V2.5"
    }
   ]
  },
  {
   "slug": "other/kat-dev-32b",
   "model_name": "kat-dev-32b",
   "display_name": "KAT Dev 32B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     },
     "provider_model_id": "accounts/fireworks/models/kat-dev-32b"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/kat-dev-32b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "KAT Dev 32B"
    }
   ]
  },
  {
   "slug": "other/kat-dev-72b-exp",
   "model_name": "kat-dev-72b-exp",
   "display_name": "kat-dev-72b-exp",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kat-dev-72b-exp"
    }
   ]
  },
  {
   "slug": "other/Kokoro-82M",
   "model_name": "Kokoro-82M",
   "display_name": "Kokoro 82M",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.62"
      }
     },
     "provider_model_id": "hexgrad/Kokoro-82M"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "10"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "hexgrad/Kokoro-82M"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "released_at": "2026-03-10",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hexgrad/Kokoro-82M"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kokoro 82M"
    }
   ]
  },
  {
   "slug": "other/l3-70b-euryale-v2.1",
   "model_name": "l3-70b-euryale-v2.1",
   "display_name": "L3 70B Euryale V2.1\t",
   "vendor": "other",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.48"
      }
     },
     "provider_model_id": "sao10k/l3-70b-euryale-v2.1"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.48"
      }
     },
     "provider_model_id": "sao10k/l3-70b-euryale-v2.1"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.48"
      }
     },
     "provider_model_id": "sao10K/l3-70b-euryale-v2.1"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2024-06-18",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sao10K/l3-70b-euryale-v2.1",
    "sao10k/l3-70b-euryale-v2.1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "L3 70B Euryale V2.1\t"
    }
   ]
  },
  {
   "slug": "other/l3-8b-lunaris",
   "model_name": "l3-8b-lunaris",
   "display_name": "Sao10k L3 8B Lunaris\t",
   "vendor": "other",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "sao10k/l3-8b-lunaris"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "sao10k/l3-8b-lunaris"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "sao10K/l3-8b-lunaris"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "novita/sao10k/l3-8b-lunaris"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2024-11-28",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "novita/sao10k/l3-8b-lunaris",
    "sao10K/l3-8b-lunaris",
    "sao10k/l3-8b-lunaris"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sao10k L3 8B Lunaris\t"
    }
   ]
  },
  {
   "slug": "other/L3-8B-Lunaris-v1",
   "model_name": "L3-8B-Lunaris-v1",
   "display_name": "Sao10K/L3-8B-Lunaris-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "Sao10K/L3-8B-Lunaris-v1"
    }
   ],
   "released_at": "2024-06-26",
   "max_input_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Sao10K/L3-8B-Lunaris-v1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sao10K/L3-8B-Lunaris-v1"
    }
   ]
  },
  {
   "slug": "other/L3-8B-Lunaris-v1-Turbo",
   "model_name": "L3-8B-Lunaris-v1-Turbo",
   "display_name": "Sao10K/L3-8B-Lunaris-v1-Turbo",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "Sao10K/L3-8B-Lunaris-v1-Turbo"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-07-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Sao10K/L3-8B-Lunaris-v1-Turbo",
    "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sao10K/L3-8B-Lunaris-v1-Turbo"
    }
   ]
  },
  {
   "slug": "other/l3-euryale-70b",
   "model_name": "l3-euryale-70b",
   "display_name": "Sao10k: Llama 3 Euryale 70B v2.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.48"
      }
     },
     "provider_model_id": "sao10k/l3-euryale-70b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.48"
      }
     },
     "provider_model_id": "sao10k/l3-euryale-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-06-18",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sao10k/l3-euryale-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sao10k: Llama 3 Euryale 70B v2.1"
    }
   ]
  },
  {
   "slug": "other/l3-lunaris-8b",
   "model_name": "l3-lunaris-8b",
   "display_name": "Sao10K: Llama 3 8B Lunaris",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "sao10k/l3-lunaris-8b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "sao10k/l3-lunaris-8b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-08-13",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "family": "llama",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sao10k/l3-lunaris-8b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sao10K: Llama 3 8B Lunaris"
    }
   ]
  },
  {
   "slug": "other/L3.1-70B-Celeste-V0.1-BF16",
   "model_name": "L3.1-70B-Celeste-V0.1-BF16",
   "display_name": "Llama 3.1 70B Celeste v0.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "nothingiisreal/L3.1-70B-Celeste-V0.1-BF16"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nothingiisreal/L3.1-70B-Celeste-V0.1-BF16"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 70B Celeste v0.1"
    }
   ]
  },
  {
   "slug": "other/L3.1-70B-Hanami-x1",
   "model_name": "L3.1-70B-Hanami-x1",
   "display_name": "Sao10K: Llama 3.1 70B Hanami x1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "sao10k/l3.1-70b-hanami-x1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "Sao10K/L3.1-70B-Hanami-x1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "sao10k/l3.1-70b-hanami-x1"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-01-08",
   "max_input_tokens": 16000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "family": "llama",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Sao10K/L3.1-70B-Hanami-x1",
    "sao10k/l3.1-70b-hanami-x1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sao10K: Llama 3.1 70B Hanami x1"
    }
   ]
  },
  {
   "slug": "other/l3.1-euryale-70b",
   "model_name": "l3.1-euryale-70b",
   "display_name": "Sao10K: Llama 3.1 Euryale 70B v2.2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "sao10k/l3.1-euryale-70b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "sao10k/l3.1-euryale-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-08-28",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2023-12",
   "family": "llama",
   "deprecated": true,
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sao10k/l3.1-euryale-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sao10K: Llama 3.1 Euryale 70B v2.2"
    }
   ]
  },
  {
   "slug": "other/L3.3-Cu-Mai-R1-70b",
   "model_name": "L3.3-Cu-Mai-R1-70b",
   "display_name": "Llama 3.3 70B Cu Mai",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "Steelskull/L3.3-Cu-Mai-R1-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Steelskull/L3.3-Cu-Mai-R1-70b"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 70B Cu Mai"
    }
   ]
  },
  {
   "slug": "other/L3.3-Electra-R1-70b",
   "model_name": "L3.3-Electra-R1-70b",
   "display_name": "Steelskull Electra R1 70b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.69989"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.69989"
      }
     },
     "provider_model_id": "Steelskull/L3.3-Electra-R1-70b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.95"
      }
     },
     "provider_model_id": "steelskull/l3.3-electra-r1-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Steelskull/L3.3-Electra-R1-70b",
    "steelskull/l3.3-electra-r1-70b"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Steelskull Electra R1 70b"
    }
   ]
  },
  {
   "slug": "other/l3.3-euryale-70b",
   "model_name": "l3.3-euryale-70b",
   "display_name": "Sao10K: Llama 3.3 Euryale 70B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "sao10k/l3.3-euryale-70b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "sao10k/l3.3-euryale-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-18",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-12",
   "family": "llama",
   "deprecated": true,
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sao10k/l3.3-euryale-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sao10K: Llama 3.3 Euryale 70B"
    }
   ]
  },
  {
   "slug": "other/L3.3-MS-Evalebis-70b",
   "model_name": "L3.3-MS-Evalebis-70b",
   "display_name": "MS Evalebis 70b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "Steelskull/L3.3-MS-Evalebis-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Steelskull/L3.3-MS-Evalebis-70b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MS Evalebis 70b"
    }
   ]
  },
  {
   "slug": "other/L3.3-MS-Evayale-70B",
   "model_name": "L3.3-MS-Evayale-70B",
   "display_name": "Evayale 70b ",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "Steelskull/L3.3-MS-Evayale-70B"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Steelskull/L3.3-MS-Evayale-70B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Evayale 70b "
    }
   ]
  },
  {
   "slug": "other/L3.3-MS-Nevoria-70b",
   "model_name": "L3.3-MS-Nevoria-70b",
   "display_name": "Steelskull Nevoria 70b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "Steelskull/L3.3-MS-Nevoria-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Steelskull/L3.3-MS-Nevoria-70b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Steelskull Nevoria 70b"
    }
   ]
  },
  {
   "slug": "other/L3.3-Nevoria-R1-70b",
   "model_name": "L3.3-Nevoria-R1-70b",
   "display_name": "Steelskull Nevoria R1 70b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "Steelskull/L3.3-Nevoria-R1-70b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Steelskull/L3.3-Nevoria-R1-70b"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Steelskull Nevoria R1 70b"
    }
   ]
  },
  {
   "slug": "other/laguna-m.1:free",
   "model_name": "laguna-m.1:free",
   "display_name": "Laguna M.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "poolside/laguna-m.1:free"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "poolside/laguna-m.1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "poolside/laguna-m.1"
    },
    {
     "provider": "poolside",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "poolside/laguna-m.1"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-04-28",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "poolside/laguna-m.1",
    "poolside/laguna-m.1:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Laguna M.1"
    }
   ]
  },
  {
   "slug": "other/laguna-xs-2.1:free",
   "model_name": "laguna-xs-2.1:free",
   "display_name": "Laguna XS 2.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "poolside/laguna-xs-2.1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "poolside/laguna-xs-2.1"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-07-02",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "temperature",
     "tool_choice",
     "tools"
    ],
    "defaults": {
     "temperature": 0.7,
     "top_p": 0.9
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "poolside/laguna-xs-2.1",
    "poolside/laguna-xs-2.1:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Laguna XS 2.1"
    }
   ]
  },
  {
   "slug": "other/laguna-xs.2:free",
   "model_name": "laguna-xs.2:free",
   "display_name": "Laguna XS.2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "poolside/laguna-xs.2:free"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "poolside/laguna-xs.2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "poolside/laguna-xs.2"
    },
    {
     "provider": "poolside",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "poolside/laguna-xs.2"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-04-28",
   "max_input_tokens": 262144,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "temperature",
     "tool_choice",
     "tools"
    ],
    "defaults": {
     "temperature": 0.7,
     "top_p": 0.9
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "poolside/laguna-xs.2",
    "poolside/laguna-xs.2:free"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "delisted",
     "note": "deprecated"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Laguna XS.2"
    }
   ]
  },
  {
   "slug": "other/language-v1-analyze-sentiment",
   "model_name": "language-v1-analyze-sentiment",
   "display_name": "language-v1-analyze-sentiment",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "language-v1-analyze-sentiment"
    }
   ]
  },
  {
   "slug": "other/language-v1-classify-text-v1",
   "model_name": "language-v1-classify-text-v1",
   "display_name": "language-v1-classify-text-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "2"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "language-v1-classify-text-v1"
    }
   ]
  },
  {
   "slug": "other/language-v1-moderate-text",
   "model_name": "language-v1-moderate-text",
   "display_name": "language-v1-moderate-text",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "5"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "safety_detection",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "language-v1-moderate-text"
    }
   ]
  },
  {
   "slug": "other/large",
   "model_name": "large",
   "display_name": "GLM 5.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "ambient/large"
    }
   ],
   "released_at": "2026-04-07",
   "max_input_tokens": 202752,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ambient/large"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.1"
    }
   ]
  },
  {
   "slug": "other/LegalOne-8B",
   "model_name": "LegalOne-8B",
   "display_name": "LegalOne-8B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29426264"
      }
     }
    }
   ],
   "released_at": "2026-02-03",
   "max_input_tokens": 32000,
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29440336",
     "new": "0.29426264"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29460788",
     "new": "0.29440336"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29491844",
     "new": "0.29460788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29497866",
     "new": "0.29491844"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29487424",
     "new": "0.29497866"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2943579",
     "new": "0.29487424"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LegalOne-8B"
    }
   ]
  },
  {
   "slug": "other/linkup-research-high",
   "model_name": "linkup-research-high",
   "display_name": "Linkup Research High",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "787.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "787.5"
      }
     }
    }
   ],
   "released_at": "2026-06-05",
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Linkup Research High"
    }
   ]
  },
  {
   "slug": "other/linkup-research-low",
   "model_name": "linkup-research-low",
   "display_name": "Linkup Research Low",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "131.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "131.25"
      }
     }
    }
   ],
   "released_at": "2026-06-05",
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Linkup Research Low"
    }
   ]
  },
  {
   "slug": "other/linkup-research-medium",
   "model_name": "linkup-research-medium",
   "display_name": "Linkup Research Medium",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "262.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "262.5"
      }
     }
    }
   ],
   "released_at": "2026-06-05",
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Linkup Research Medium"
    }
   ]
  },
  {
   "slug": "other/linkup-research-xhigh",
   "model_name": "linkup-research-xhigh",
   "display_name": "Linkup Research XHigh",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1312.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1312.5"
      }
     }
    }
   ],
   "released_at": "2026-06-05",
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Linkup Research XHigh"
    }
   ]
  },
  {
   "slug": "other/llemma_7b",
   "model_name": "llemma_7b",
   "display_name": "EleutherAI: Llemma 7b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "eleutherai/llemma_7b"
    }
   ],
   "capabilities": {},
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "released_at": "2025-04-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "eleutherai/llemma_7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "EleutherAI: Llemma 7b"
    }
   ]
  },
  {
   "slug": "other/LTX-2.3-Distilled-Diffusers",
   "model_name": "LTX-2.3-Distilled-Diffusers",
   "display_name": "LTX-2.3-Distilled-Diffusers",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.035"
      }
     },
     "provider_model_id": "FastVideo/LTX-2.3-Distilled-Diffusers"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "FastVideo/LTX-2.3-Distilled-Diffusers"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LTX-2.3-Distilled-Diffusers"
    }
   ]
  },
  {
   "slug": "other/LTX2-Distilled-Diffusers",
   "model_name": "LTX2-Distilled-Diffusers",
   "display_name": "LTX2-Distilled-Diffusers",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.036"
      }
     },
     "provider_model_id": "FastVideo/LTX2-Distilled-Diffusers"
    }
   ],
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio"
    ],
    "output": [
     "video",
     "audio"
    ]
   },
   "model_type": "omni",
   "capabilities": {
    "vision": true,
    "audio_input": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "FastVideo/LTX2-Distilled-Diffusers"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LTX2-Distilled-Diffusers"
    }
   ]
  },
  {
   "slug": "other/lucid-origin",
   "model_name": "lucid-origin",
   "display_name": "Lucid Origin",
   "vendor": "other",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-06-01",
   "max_input_tokens": 4096,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "lucid",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "leonardo-ai/lucid-origin"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Lucid Origin"
    }
   ]
  },
  {
   "slug": "other/lucid-realism",
   "model_name": "lucid-realism",
   "display_name": "Lucid Realism",
   "vendor": "other",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2025-06-01",
   "max_input_tokens": 4096,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "lucid",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "leonardo-ai/lucid-realism"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Lucid Realism"
    }
   ]
  },
  {
   "slug": "other/lucidnova-rf1-100b",
   "model_name": "lucidnova-rf1-100b",
   "display_name": "LucidNova RF1 100B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "lucidquery",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2024-12-28",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 120000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LucidNova RF1 100B"
    }
   ]
  },
  {
   "slug": "other/lucidquery-agi-01-frontier",
   "model_name": "lucidquery-agi-01-frontier",
   "display_name": "AGI-01 Frontier",
   "vendor": "other",
   "pricing": [
    {
     "provider": "lucidquery",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "22"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-06-16",
   "knowledge_cutoff": "2026-06",
   "max_input_tokens": 300000,
   "max_output_tokens": 120000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "agi",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AGI-01 Frontier"
    }
   ]
  },
  {
   "slug": "other/lucidquery-agi-01-swift",
   "model_name": "lucidquery-agi-01-swift",
   "display_name": "AGI-01 Swift",
   "vendor": "other",
   "pricing": [
    {
     "provider": "lucidquery",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-06-16",
   "knowledge_cutoff": "2026-06",
   "max_input_tokens": 300000,
   "max_output_tokens": 120000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "agi",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AGI-01 Swift"
    }
   ]
  },
  {
   "slug": "other/lucidquery-nexus-coder",
   "model_name": "lucidquery-nexus-coder",
   "display_name": "LucidQuery Nexus Coder",
   "vendor": "other",
   "pricing": [
    {
     "provider": "lucidquery",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2025-09-01",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 250000,
   "max_output_tokens": 60000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "lucid",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "LucidQuery Nexus Coder"
    }
   ]
  },
  {
   "slug": "other/Lumimaid-v0.2-70B",
   "model_name": "Lumimaid-v0.2-70B",
   "display_name": "Lumimaid v0.2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "NeverSleep/Lumimaid-v0.2-70B"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-01",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "NeverSleep/Lumimaid-v0.2-70B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Lumimaid v0.2"
    }
   ]
  },
  {
   "slug": "other/lyria-002",
   "model_name": "lyria-002",
   "display_name": "lyria-002",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.06"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "music_generation",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "lyria-002"
    }
   ]
  },
  {
   "slug": "other/M-Prometheus-14B",
   "model_name": "M-Prometheus-14B",
   "display_name": "M-Prometheus 14B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Unbabel/M-Prometheus-14B"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2026-05-29",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Unbabel/M-Prometheus-14B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "M-Prometheus 14B"
    }
   ]
  },
  {
   "slug": "other/m2.7",
   "model_name": "m2.7",
   "display_name": "MiniMax M2.7",
   "vendor": "other",
   "pricing": [
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiniMax M2.7"
    }
   ]
  },
  {
   "slug": "other/magibu-11b-v8",
   "model_name": "magibu-11b-v8",
   "display_name": "Magibu 11B v8",
   "vendor": "other",
   "pricing": [
    {
     "provider": "llmtr",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "llmtr/magibu-11b-v8"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2026-06-05",
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llmtr/magibu-11b-v8"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Magibu 11B v8"
    }
   ]
  },
  {
   "slug": "other/Magidonia-24B-v4.3",
   "model_name": "Magidonia-24B-v4.3",
   "display_name": "The Drummer Magidonia 24B v4.3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1207"
      }
     },
     "provider_model_id": "TheDrummer/Magidonia-24B-v4.3"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-12-25",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/Magidonia-24B-v4.3"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "The Drummer Magidonia 24B v4.3"
    }
   ]
  },
  {
   "slug": "other/magnum-72b",
   "model_name": "magnum-72b",
   "display_name": "magnum-72b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      }
     },
     "provider_model_id": "alpindale/magnum-72b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "alpindale/magnum-72b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "magnum-72b"
    }
   ]
  },
  {
   "slug": "other/magnum-v2-72b",
   "model_name": "magnum-v2-72b",
   "display_name": "Magnum V2 72B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.992"
      }
     },
     "provider_model_id": "anthracite-org/magnum-v2-72b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "anthracite-org/magnum-v2-72b"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-01",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "anthracite-org/magnum-v2-72b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Magnum V2 72B"
    }
   ]
  },
  {
   "slug": "other/magnum-v4-72b",
   "model_name": "magnum-v4-72b",
   "display_name": "Magnum v4 72B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "anthracite-org/magnum-v4-72b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.992"
      }
     },
     "provider_model_id": "anthracite-org/magnum-v4-72b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "anthracite-org/magnum-v4-72b"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2024-10-22",
   "max_input_tokens": 16384,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2024-06",
   "family": "llama",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_a",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "anthracite-org/magnum-v4-72b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Magnum v4 72B"
    }
   ]
  },
  {
   "slug": "other/mai-code-1-flash-picker",
   "model_name": "mai-code-1-flash-picker",
   "display_name": "MAI-Code-1-Flash",
   "vendor": "other",
   "pricing": [
    {
     "provider": "github-copilot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    }
   ],
   "intro": "Microsoft coding model built for fast, efficient assistance in everyday developer workflows",
   "released_at": "2026-06-02",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mai",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MAI-Code-1-Flash"
    }
   ]
  },
  {
   "slug": "other/mai-image-2",
   "model_name": "mai-image-2",
   "display_name": "mai-image-2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mai-image-2"
    }
   ]
  },
  {
   "slug": "other/MAI-Image-2.5-Flash",
   "model_name": "MAI-Image-2.5-Flash",
   "display_name": "MAI-Image-2.5-Flash",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.0338"
      }
     }
    }
   ],
   "docs_url": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/new-mai-models-in-microsoft-foundry-across-text-image-voice-and-speech/4524632",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MAI-Image-2.5-Flash"
    }
   ]
  },
  {
   "slug": "other/MAI-Image-2e",
   "model_name": "MAI-Image-2e",
   "display_name": "mai-image-2e",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.5"
      }
     },
     "provider_model_id": "mai-image-2e"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     }
    }
   ],
   "docs_url": "https://aka.ms/mai-image-2e-foundryblog",
   "model_type": "image_generation",
   "capabilities": {
    "prompt_caching": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mai-image-2e"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mai-image-2e"
    }
   ]
  },
  {
   "slug": "other/MAI-UI-8B",
   "model_name": "MAI-UI-8B",
   "display_name": "MAI-UI-8B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.205983848"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.205983848"
      }
     }
    }
   ],
   "released_at": "2026-01-15",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206082352",
     "new": "0.205983848"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206082352",
     "new": "0.205983848"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206225516",
     "new": "0.206082352"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206225516",
     "new": "0.206082352"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206442908",
     "new": "0.206225516"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206442908",
     "new": "0.206225516"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206485062",
     "new": "0.206442908"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206485062",
     "new": "0.206442908"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206411968",
     "new": "0.206485062"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.206411968",
     "new": "0.206485062"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.20605053",
     "new": "0.206411968"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.20605053",
     "new": "0.206411968"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MAI-UI-8B"
    }
   ]
  },
  {
   "slug": "other/main/models/mm-poly-8b",
   "model_name": "main/models/mm-poly-8b",
   "display_name": "MM Poly 8B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "clarifai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.658"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.11"
      }
     },
     "provider_model_id": "clarifai/main/models/mm-poly-8b"
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2025-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mm-poly",
   "capabilities": {
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "clarifai/main/models/mm-poly-8b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MM Poly 8B"
    }
   ]
  },
  {
   "slug": "other/manta-flash-1.0",
   "model_name": "manta-flash-1.0",
   "display_name": "Manta Flash 1.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "meganova-ai/manta-flash-1.0"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-12-20",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meganova-ai/manta-flash-1.0"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Manta Flash 1.0"
    }
   ]
  },
  {
   "slug": "other/manta-mini-1.0",
   "model_name": "manta-mini-1.0",
   "display_name": "Manta Mini 1.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "meganova-ai/manta-mini-1.0"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-12-20",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meganova-ai/manta-mini-1.0"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Manta Mini 1.0"
    }
   ]
  },
  {
   "slug": "other/manta-pro-1.0",
   "model_name": "manta-pro-1.0",
   "display_name": "Manta Pro 1.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.060000000000000005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "meganova-ai/manta-pro-1.0"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2025-12-20",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meganova-ai/manta-pro-1.0"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Manta Pro 1.0"
    }
   ]
  },
  {
   "slug": "other/medlm-large",
   "model_name": "medlm-large",
   "display_name": "medlm-large",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "5"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "medlm-large"
    }
   ]
  },
  {
   "slug": "other/medlm-medium",
   "model_name": "medlm-medium",
   "display_name": "medlm-medium",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.5"
      }
     }
    }
   ],
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "medlm-medium"
    }
   ]
  },
  {
   "slug": "other/megrez-3b-instruct",
   "model_name": "megrez-3b-instruct",
   "display_name": "Megrez 3B Instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Megrez 3B Instruct 是来自悟问星穹的小型高效模型。",
    "zh-TW": "Megrez 3B Instruct 是來自無問星穹的小型高效模型。",
    "ja-JP": "Megrez 3B InstructはWuwen Xinqiongによる小型で効率的なモデルです。",
    "ru-RU": "Megrez 3B Instruct — это компактная и эффективная модель от Wuwen Xinqiong."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Megrez 3B Instruct"
    }
   ]
  },
  {
   "slug": "other/Mellum2-12B-A2.5B-Instruct",
   "model_name": "Mellum2-12B-A2.5B-Instruct",
   "display_name": "Mellum2 12B A2.5B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "JetBrains/Mellum2-12B-A2.5B-Instruct"
    }
   ],
   "intro": "Mellum2-12B-A2.5B-Instruct is a fast MoE model with 131K context built for coding, tool use, and low-latency AI workflows.",
   "released_at": "2026-06-01",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "JetBrains/Mellum2-12B-A2.5B-Instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "capability",
     "note": "open_weights: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "JetBrains: Mellum2 12B A2.5B"
    }
   ]
  },
  {
   "slug": "other/mercury-coder-small-beta",
   "model_name": "mercury-coder-small-beta",
   "display_name": "mercury-coder-small-beta",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mercury-coder-small-beta"
    }
   ]
  },
  {
   "slug": "other/midnight-rose-70b",
   "model_name": "midnight-rose-70b",
   "display_name": "Midnight Rose 70B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "sophosympatheia/midnight-rose-70b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "sophosympatheia/midnight-rose-70b"
    }
   ],
   "capabilities": {},
   "max_input_tokens": 4096,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sophosympatheia/midnight-rose-70b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Midnight Rose 70B"
    }
   ]
  },
  {
   "slug": "other/minicpm-v-4.5",
   "model_name": "minicpm-v-4.5",
   "display_name": "minicpm-v-4.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.584"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.985"
      }
     }
    }
   ],
   "released_at": "2026-06-02",
   "max_input_tokens": 32000,
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "minicpm-v-4.5"
    }
   ]
  },
  {
   "slug": "other/mirothinker-1-7-deepresearch",
   "model_name": "mirothinker-1-7-deepresearch",
   "display_name": "MiroThinker 1.7 Deep Research",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "miromind/mirothinker-1-7-deepresearch"
    }
   ],
   "intro": "Research model for long-horizon investigation, synthesis, and analytical reports",
   "released_at": "2026-05-11",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "miromind/mirothinker-1-7-deepresearch"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiroThinker 1.7 Deep Research"
    }
   ]
  },
  {
   "slug": "other/mirothinker-1-7-deepresearch-mini",
   "model_name": "mirothinker-1-7-deepresearch-mini",
   "display_name": "MiroThinker 1.7 Deep Research Mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "miromind/mirothinker-1-7-deepresearch-mini"
    }
   ],
   "intro": "Research model for long-horizon investigation, synthesis, and analytical reports",
   "released_at": "2026-05-11",
   "max_input_tokens": 262144,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "miromind/mirothinker-1-7-deepresearch-mini"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiroThinker 1.7 Deep Research Mini"
    }
   ]
  },
  {
   "slug": "other/MiroThinker-v1.5-235B",
   "model_name": "MiroThinker-v1.5-235B",
   "display_name": "MiroThinker V1.5 235B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "miromind-ai/MiroThinker-v1.5-235B"
    }
   ],
   "released_at": "2026-01-10",
   "max_input_tokens": 262144,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "miromind-ai/MiroThinker-v1.5-235B"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiroThinker V1.5 235B"
    }
   ]
  },
  {
   "slug": "other/MN-12B-Inferor-v0.0",
   "model_name": "MN-12B-Inferor-v0.0",
   "display_name": "Mistral Nemo Inferor 12B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25499999999999995"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "Infermatic/MN-12B-Inferor-v0.0"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2024-07-01",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-nemo",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Infermatic/MN-12B-Inferor-v0.0"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Nemo Inferor 12B"
    }
   ]
  },
  {
   "slug": "other/MN-12B-Mag-Mell-R1",
   "model_name": "MN-12B-Mag-Mell-R1",
   "display_name": "Mag Mell R1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "inflatebot/MN-12B-Mag-Mell-R1"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2024-07-01",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-nemo",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inflatebot/MN-12B-Mag-Mell-R1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mag Mell R1"
    }
   ]
  },
  {
   "slug": "other/mn-celeste-12b",
   "model_name": "mn-celeste-12b",
   "display_name": "mn-celeste-12b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "nothingiisreal/mn-celeste-12b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nothingiisreal/mn-celeste-12b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mn-celeste-12b"
    }
   ]
  },
  {
   "slug": "other/mn-inferor-12b",
   "model_name": "mn-inferor-12b",
   "display_name": "mn-inferor-12b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "infermatic/mn-inferor-12b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "infermatic/mn-inferor-12b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mn-inferor-12b"
    }
   ]
  },
  {
   "slug": "other/MN-LooseCannon-12B-v1",
   "model_name": "MN-LooseCannon-12B-v1",
   "display_name": "MN-LooseCannon-12B-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "GalrionSoftworks/MN-LooseCannon-12B-v1"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2024-07-01",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-nemo",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "GalrionSoftworks/MN-LooseCannon-12B-v1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MN-LooseCannon-12B-v1"
    }
   ]
  },
  {
   "slug": "other/mn-starcannon-12b",
   "model_name": "mn-starcannon-12b",
   "display_name": "mn-starcannon-12b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "aetherwiing/mn-starcannon-12b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "aetherwiing/mn-starcannon-12b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mn-starcannon-12b"
    }
   ]
  },
  {
   "slug": "other/model_router",
   "model_name": "model_router",
   "display_name": "model_router",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "docs_url": "https://azure.microsoft.com/en-us/pricing/details/ai-services/",
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "model_router"
    }
   ]
  },
  {
   "slug": "other/model-router",
   "model_name": "model-router",
   "display_name": "Model Router",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "model-router-2025-05-19"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2025-05-19",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "model-router",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "model-router-2025-05-19",
    "model-router-2025-08-07",
    "model-router-2025-11-18"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Model Router"
    }
   ]
  },
  {
   "slug": "other/molmo-2-8b",
   "model_name": "molmo-2-8b",
   "display_name": "AllenAI: Molmo2 8B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "allenai/molmo-2-8b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "allenai/molmo-2-8b"
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 36864,
   "max_output_tokens": 36864,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/molmo-2-8b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AllenAI: Molmo2 8B"
    }
   ]
  },
  {
   "slug": "other/Molmo-7B-D-0924",
   "model_name": "Molmo-7B-D-0924",
   "display_name": "Molmo-7B-D-0924",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "allenai/Molmo-7B-D-0924"
    }
   ],
   "max_input_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/Molmo-7B-D-0924"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Molmo-7B-D-0924"
    }
   ]
  },
  {
   "slug": "other/MS3.2-24B-Magnum-Diamond",
   "model_name": "MS3.2-24B-Magnum-Diamond",
   "display_name": "MS3.2 24B Magnum Diamond",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "Doctor-Shotgun/MS3.2-24B-Magnum-Diamond"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2025-11-24",
   "max_input_tokens": 16384,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Doctor-Shotgun/MS3.2-24B-Magnum-Diamond"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MS3.2 24B Magnum Diamond"
    }
   ]
  },
  {
   "slug": "other/MS3.2-The-Omega-Directive-24B-Unslop-v2.0",
   "model_name": "MS3.2-The-Omega-Directive-24B-Unslop-v2.0",
   "display_name": "Omega Directive 24B Unslop v2.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-12-08",
   "max_input_tokens": 16384,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Omega Directive 24B Unslop v2.0"
    }
   ]
  },
  {
   "slug": "other/mt0-xxl-13b",
   "model_name": "mt0-xxl-13b",
   "display_name": "mt0-xxl-13b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "ibm-watsonx",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "500"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2000"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mt0-xxl-13b"
    }
   ]
  },
  {
   "slug": "other/multi-qa-mpnet-base-dot-v1",
   "model_name": "multi-qa-mpnet-base-dot-v1",
   "display_name": "Multi-QA-mpnet-base-dot-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/multi-qa-mpnet-base-dot-v1"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.009"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/multi-qa-mpnet-base-dot-v1"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/sentence-transformers/multi-qa-mpnet-base-dot-v1"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2021-08-30",
   "max_input_tokens": 512,
   "max_output_tokens": 768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "text-embedding",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/sentence-transformers/multi-qa-mpnet-base-dot-v1",
    "sentence-transformers/multi-qa-mpnet-base-dot-v1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Multi-QA-mpnet-base-dot-v1"
    }
   ]
  },
  {
   "slug": "other/multilingual-e5-large",
   "model_name": "multilingual-e5-large",
   "display_name": "Multilingual-E5-large",
   "vendor": "other",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "intfloat/multilingual-e5-large"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "intfloat/multilingual-e5-large"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "intfloat/multilingual-e5-large"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "deepinfra/intfloat/multilingual-e5-large"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "released_at": "2025-09-11",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 512,
   "max_output_tokens": 1024,
   "family": "text-embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/intfloat/multilingual-e5-large",
    "intfloat/multilingual-e5-large"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Multilingual-E5-large"
    }
   ]
  },
  {
   "slug": "other/multilingual-e5-large-instruct",
   "model_name": "multilingual-e5-large-instruct",
   "display_name": "E5 Multi-Lingual Large Embeddings 0.6B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02283279"
      }
     },
     "provider_model_id": "intfloat/multilingual-e5-large-instruct"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "intfloat/multilingual-e5-large-instruct"
    },
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.114"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.114"
      }
     },
     "provider_model_id": "intfloat/multilingual-e5-large-instruct"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0005"
      }
     },
     "provider_model_id": "deepinfra/intfloat/multilingual-e5-large-instruct"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "intfloat/multilingual-e5-large-instruct"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2024-06-01",
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "text-embedding",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "model_type": "text_embedding",
   "knowledge_cutoff": "2025-04",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/intfloat/multilingual-e5-large-instruct",
    "intfloat/multilingual-e5-large-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228741496",
     "new": "0.02283279"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228653194",
     "new": "0.0228741496"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228828286",
     "new": "0.0228653194"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228736168",
     "new": "0.0228828286"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.0228799574",
     "new": "0.0228736168"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.02276194",
     "new": "0.0228799574"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "E5 Multi-Lingual Large Embeddings 0.6B"
    }
   ]
  },
  {
   "slug": "other/multilingual-e5-large-instruct-maas",
   "model_name": "multilingual-e5-large-instruct-maas",
   "display_name": "multilingual-e5-large-instruct-maas",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "intfloat/multilingual-e5-large-instruct-maas",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "intfloat/multilingual-e5-large-instruct-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "multilingual-e5-large-instruct-maas"
    }
   ]
  },
  {
   "slug": "other/multimodalembedding@001",
   "model_name": "multimodalembedding@001",
   "display_name": "multimodalembedding@001",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "input_video_plus": {
       "unit": "per_request",
       "price": "0.002"
      },
      "input_video_standard": {
       "unit": "per_request",
       "price": "0.001"
      },
      "input_video_essential": {
       "unit": "per_request",
       "price": "0.0005"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "completion": "0.8"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "asia-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "asia-northeast3"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "asia-southeast1"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "europe-west1"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "europe-west2"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "europe-west3"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "europe-west4"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "europe-west9"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "northamerica-northeast1"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.0001"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "us-central1"
    }
   ],
   "max_input_tokens": 32,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "multimodal_embedding",
   "capabilities": {
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "multimodalembedding@001"
    }
   ]
  },
  {
   "slug": "other/musesteamer-2.0-lite-i2v",
   "model_name": "musesteamer-2.0-lite-i2v",
   "display_name": "MuseSteamer 2.0 Lite I2V",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.102941"
      }
     }
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "与Turbo相比，性能更优，性价比更高。",
    "zh-TW": "相比Turbo，性能更優，性價比更高。",
    "ja-JP": "Turboと比較して、優れたコストパフォーマンスで卓越したパフォーマンスを提供します。",
    "ru-RU": "По сравнению с Turbo, обеспечивает превосходную производительность с отличным соотношением цены и качества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MuseSteamer 2.0 Lite I2V"
    }
   ]
  },
  {
   "slug": "other/musesteamer-2.0-pro-i2v",
   "model_name": "musesteamer-2.0-pro-i2v",
   "display_name": "MuseSteamer 2.0 Pro I2V",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.367647"
      }
     }
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "基于Turbo，支持1080P动态视频生成，提供更高的视觉质量和增强的视频表现力。",
    "zh-TW": "基於Turbo，支持1080P動態影像生成，提供更高的視覺質量及增強的影像表現力。",
    "ja-JP": "Turboをベースに、1080Pの動的ビデオ生成をサポートし、より高い視覚品質とビデオ表現力を提供します。",
    "ru-RU": "На основе Turbo поддерживает генерацию динамического видео в разрешении 1080P, предлагая более высокое визуальное качество и улучшенную выразительность видео."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MuseSteamer 2.0 Pro I2V"
    }
   ]
  },
  {
   "slug": "other/musesteamer-2.0-turbo-i2v",
   "model_name": "musesteamer-2.0-turbo-i2v",
   "display_name": "MuseSteamer 2.0 Turbo I2V",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.205882"
      }
     }
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "支持5秒720P无声动态视频生成，具有电影级视觉效果、复杂的摄像机运动以及真实的角色情感和动作。",
    "zh-TW": "支持5秒720P無聲動態影像生成，具有電影級視覺效果、複雜相機運動及真實角色情感及動作。",
    "ja-JP": "5秒間の720P無音動的ビデオ生成をサポートし、映画品質のビジュアル、複雑なカメラ動作、リアルなキャラクターの感情とアクションを特徴とします。",
    "ru-RU": "Поддерживает генерацию 5-секундного немого динамического видео в разрешении 720P, с кинематографическим качеством визуальных эффектов, сложными движениями камеры и реалистичными эмоциями и действиями персонажей."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MuseSteamer 2.0 Turbo I2V"
    }
   ]
  },
  {
   "slug": "other/musesteamer-2.0-turbo-i2v-audio",
   "model_name": "musesteamer-2.0-turbo-i2v-audio",
   "display_name": "MuseSteamer 2.0 Turbo I2V Audio",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.367647"
      }
     }
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "支持5秒和10秒720P动态视频生成并带有声音。实现多人对话音视频创作，声音与画面同步，画质达到电影级别，摄像机运动达到大师级水平。",
    "zh-TW": "支持5秒及10秒720P動態影像生成並帶有聲音。實現多角色對話音視創作，聲音與影像同步，電影級影像及大師級相機運動。",
    "ja-JP": "5秒および10秒の720P動的ビデオ生成を音声付きでサポートします。複数人の会話型音声ビジュアル作成を可能にし、音声とビジュアルが同期し、映画品質の画像とマスタークラスのカメラ動作を実現します。",
    "ru-RU": "Поддерживает генерацию динамического видео длиной 5 и 10 секунд в разрешении 720P со звуком. Позволяет создавать аудиовизуальные материалы с участием нескольких персонажей, с синхронизированным звуком и визуальными эффектами, кинематографическим качеством изображения и мастерскими движениями камеры."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MuseSteamer 2.0 Turbo I2V Audio"
    }
   ]
  },
  {
   "slug": "other/musesteamer-air-i2v",
   "model_name": "musesteamer-air-i2v",
   "display_name": "MuseSteamer Air I2V",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.147059"
      }
     }
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "百度MuseSteamer Air视频生成模型在主体一致性、物理真实感、摄像机运动效果和生成速度方面表现出色。支持5秒720P无声动态视频生成，提供电影级视觉效果、快速生成和卓越的性价比。",
    "zh-TW": "百度MuseSteamer Air影像生成模型在主題一致性、物理真實性、相機運動效果及生成速度方面表現出色。支持5秒720P無聲動態影像生成，提供電影級視覺效果、快速生成及卓越性價比。",
    "ja-JP": "Baidu MuseSteamer Airビデオ生成モデルは、被写体の一貫性、物理的リアリズム、カメラ動作効果、生成速度において優れた性能を発揮します。5秒間の720P無音動的ビデオ生成をサポートし、映画品質のビジュアル、高速生成、優れたコストパフォーマンスを提供します。",
    "ru-RU": "Модель генерации видео Baidu MuseSteamer Air демонстрирует отличные результаты в согласованности объектов, физическом реализме, эффектах движения камеры и скорости генерации. Поддерживает генерацию 5-секундного немого динамического видео в разрешении 720P, обеспечивая кинематографическое качество визуальных эффектов, быструю генерацию и отличное соотношение цены и качества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MuseSteamer Air I2V"
    }
   ]
  },
  {
   "slug": "other/musesteamer-air-image",
   "model_name": "musesteamer-air-image",
   "display_name": "MuseSteamer Air Image",
   "vendor": "other",
   "pricing": [
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.007353"
      }
     }
    }
   ],
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "musesteamer-air-image是百度搜索团队开发的图像生成模型，具有卓越的性价比。它可以根据用户提示快速生成清晰、动作连贯的图像，将用户描述轻松转化为视觉效果。",
    "zh-TW": "musesteamer-air-image 是百度搜索團隊開發的圖像生成模型，提供卓越的性價比。它能根據用戶提示快速生成清晰且動作連貫的圖像，輕鬆將用戶描述轉化為視覺效果。",
    "ja-JP": "musesteamer-air-imageは、Baiduの検索チームによって開発された画像生成モデルで、優れたコストパフォーマンスを提供します。ユーザーのプロンプトに基づいて、明確でアクション一貫性のある画像を迅速に生成し、ユーザーの説明を簡単にビジュアルに変換します。",
    "ru-RU": "musesteamer-air-image — это модель генерации изображений, разработанная командой поиска Baidu для обеспечения исключительного соотношения цены и качества. Она может быстро создавать четкие, согласованные по действиям изображения на основе пользовательских подсказок, легко превращая описания пользователей в визуальные образы."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MuseSteamer Air Image"
    }
   ]
  },
  {
   "slug": "other/mythalion-13b",
   "model_name": "mythalion-13b",
   "display_name": "mythalion-13b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "pygmalionai/mythalion-13b"
    }
   ],
   "max_input_tokens": 8192,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pygmalionai/mythalion-13b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "mythalion-13b"
    }
   ]
  },
  {
   "slug": "other/MythoMax-L2-13b",
   "model_name": "MythoMax-L2-13b",
   "display_name": "Mythomax L2 13B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "Gryphe/MythoMax-L2-13b"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "Gryphe/MythoMax-L2-13b"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "mythomax-l2-13b"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mythomax-l2-13b"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "gryphe/mythomax-l2-13b"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "gryphe/mythomax-l2-13b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      }
     },
     "provider_model_id": "Gryphe/MythoMax-L2-13b"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "mythomax-l2-13b"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "gryphe/mythomax-l2-13b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "gryphe/mythomax-l2-13b"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     },
     "provider_model_id": "novita/gryphe/mythomax-l2-13b"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "deepinfra/Gryphe/MythoMax-L2-13b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Gryphe/MythoMax-L2-13b"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2024-04-25",
   "max_input_tokens": 4096,
   "max_output_tokens": 3200,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2023-06",
   "family": "llama",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_a",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Gryphe/MythoMax-L2-13b",
    "accounts/fireworks/models/mythomax-l2-13b",
    "deepinfra/Gryphe/MythoMax-L2-13b",
    "gryphe/mythomax-l2-13b",
    "mythomax-l2-13b",
    "novita/gryphe/mythomax-l2-13b"
   ],
   "intro_i18n": {
    "zh-CN": "MythoMax-L2（13B）是一款面向多领域和复杂任务的创新模型。",
    "zh-TW": "MythoMax-L2（13B）是一款創新模型，適用於多領域與複雜任務。",
    "ja-JP": "MythoMax-L2（13B）は、多様な分野と複雑なタスクに対応する革新的なモデルです。",
    "ru-RU": "MythoMax-L2 (13B) — инновационная модель для различных областей и сложных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mythomax L2 13B"
    }
   ]
  },
  {
   "slug": "other/NemoMix-Unleashed-12B",
   "model_name": "NemoMix-Unleashed-12B",
   "display_name": "NemoMix 12B Unleashed",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "MarinaraSpaghetti/NemoMix-Unleashed-12B"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2024-07-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-nemo",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MarinaraSpaghetti/NemoMix-Unleashed-12B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NemoMix 12B Unleashed"
    }
   ]
  },
  {
   "slug": "other/NeuralDaredevil-8B-abliterated",
   "model_name": "NeuralDaredevil-8B-abliterated",
   "display_name": "Neural Daredevil 8B abliterated",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.44"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     },
     "provider_model_id": "mlabonne/NeuralDaredevil-8B-abliterated"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-01",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mlabonne/NeuralDaredevil-8B-abliterated"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Neural Daredevil 8B abliterated"
    }
   ]
  },
  {
   "slug": "other/nex-n2-mini",
   "model_name": "nex-n2-mini",
   "display_name": "Nex-N2-Mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "nex-agi/nex-n2-mini"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "nex-agi/nex-n2-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "nex-agi/nex-n2-mini"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-06-24",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "agi",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "reasoning",
     "response_format",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.7,
     "top_p": 0.95,
     "top_k": 40
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nex-agi/nex-n2-mini"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "open_weights: false→true"
    },
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "Nex-N2-Mini"
    }
   ]
  },
  {
   "slug": "other/nex-n2-pro",
   "model_name": "nex-n2-pro",
   "display_name": "Nex-N2-Pro",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "nex-agi/nex-n2-pro"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "nex-agi/nex-n2-pro"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "nex-agi/nex-n2-pro"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-06-08",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "agi",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "reasoning",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.7,
     "top_p": 0.95,
     "top_k": 40
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "nex-agi/nex-n2-pro",
    "nex-agi/nex-n2-pro:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nex-N2-Pro"
    }
   ]
  },
  {
   "slug": "other/NexusRaven-V2-13B",
   "model_name": "NexusRaven-V2-13B",
   "display_name": "NexusRaven-V2-13B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Nexusflow/NexusRaven-V2-13B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Nexusflow/NexusRaven-V2-13B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "NexusRaven-V2-13B"
    }
   ]
  },
  {
   "slug": "other/nomic-embed-text",
   "model_name": "nomic-embed-text",
   "display_name": "Nomic Embed Text v1.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "tinfoil",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2024-02",
   "max_input_tokens": 8192,
   "max_output_tokens": 768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nomic Embed Text v1.5"
    }
   ]
  },
  {
   "slug": "other/noromaid-20b",
   "model_name": "noromaid-20b",
   "display_name": "Noromaid 20B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "neversleep/noromaid-20b"
    }
   ],
   "capabilities": {},
   "released_at": "2023-11-26",
   "max_input_tokens": 4096,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "neversleep/noromaid-20b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Noromaid 20B"
    }
   ]
  },
  {
   "slug": "other/nova-2-pro-v1",
   "model_name": "nova-2-pro-v1",
   "display_name": "Nova 2 Pro",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nova",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-12-03",
   "max_input_tokens": 1000000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "nova-pro",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nova 2 Pro"
    }
   ]
  },
  {
   "slug": "other/nova-lite-1.0",
   "model_name": "nova-lite-1.0",
   "display_name": "Nova-Lite-1.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0697"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2828"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0383"
      }
     }
    }
   ],
   "released_at": "2024-12-09",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nova-Lite-1.0"
    }
   ]
  },
  {
   "slug": "other/nova-lite-2",
   "model_name": "nova-lite-2",
   "display_name": "Nova-Lite-2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3838"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.1919"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2111"
      }
     }
    }
   ],
   "released_at": "2025-12-04",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nova-Lite-2"
    }
   ]
  },
  {
   "slug": "other/nova-micro-1.0",
   "model_name": "nova-micro-1.0",
   "display_name": "Nova-Micro-1.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0404"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1616"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0222"
      }
     }
    }
   ],
   "released_at": "2024-12-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nova-Micro-1.0"
    }
   ]
  },
  {
   "slug": "other/nova-premier-1.0",
   "model_name": "nova-premier-1.0",
   "display_name": "Nova-Premier-1.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.0303"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.1515"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.6667"
      }
     }
    }
   ],
   "released_at": "2025-09-15",
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Nova-Premier-1.0"
    }
   ]
  },
  {
   "slug": "other/o4",
   "model_name": "o4",
   "display_name": "o4",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.66"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 200000,
   "max_output_tokens": 100000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "o4"
    }
   ]
  },
  {
   "slug": "other/olmo-2-0325-32b-instruct",
   "model_name": "olmo-2-0325-32b-instruct",
   "display_name": "AllenAI: Olmo 2 32B Instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "allenai/olmo-2-0325-32b-instruct"
    }
   ],
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2025-03-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/olmo-2-0325-32b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AllenAI: Olmo 2 32B Instruct"
    }
   ]
  },
  {
   "slug": "other/olmo-3-32b-think",
   "model_name": "olmo-3-32b-think",
   "display_name": "AllenAI: Olmo 3 32B Think",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "allenai/olmo-3-32b-think"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.44999999999999996"
      }
     },
     "provider_model_id": "allenai/olmo-3-32b-think"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "allenai/olmo-3-32b-think"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2025-11-22",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "structured_output": true,
    "open_weights": true
   },
   "family": "allenai",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.6,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/olmo-3-32b-think"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AllenAI: Olmo 3 32B Think"
    }
   ]
  },
  {
   "slug": "other/Olmo-3-7B-Instruct",
   "model_name": "Olmo-3-7B-Instruct",
   "display_name": "AllenAI: Olmo 3 7B Instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "allenai/Olmo-3-7B-Instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "allenai/olmo-3-7b-instruct"
    }
   ],
   "released_at": "2025-11-21",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/Olmo-3-7B-Instruct",
    "allenai/olmo-3-7b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AllenAI: Olmo 3 7B Instruct"
    }
   ]
  },
  {
   "slug": "other/olmo-3-7b-think",
   "model_name": "olmo-3-7b-think",
   "display_name": "AllenAI: Olmo 3 7B Think",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "allenai/olmo-3-7b-think"
    }
   ],
   "released_at": "2025-11-21",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/olmo-3-7b-think"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AllenAI: Olmo 3 7B Think"
    }
   ]
  },
  {
   "slug": "other/Olmo-3.1-32B-Instruct",
   "model_name": "Olmo-3.1-32B-Instruct",
   "display_name": "AllenAI: Olmo 3.1 32B Instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "allenai/Olmo-3.1-32B-Instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "allenai/olmo-3.1-32b-instruct"
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "stream": true
   },
   "released_at": "2026-01-06",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/Olmo-3.1-32B-Instruct",
    "allenai/olmo-3.1-32b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AllenAI: Olmo 3.1 32B Instruct"
    }
   ]
  },
  {
   "slug": "other/olmo-3.1-32b-think",
   "model_name": "olmo-3.1-32b-think",
   "display_name": "AllenAI: Olmo 3.1 32B Think",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "allenai/olmo-3.1-32b-think"
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "structured_output": true,
    "reasoning": true
   },
   "released_at": "2025-12-16",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/olmo-3.1-32b-think"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AllenAI: Olmo 3.1 32B Think"
    }
   ]
  },
  {
   "slug": "other/OLMo-7B",
   "model_name": "OLMo-7B",
   "display_name": "OLMo-7B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "allenai/OLMo-7B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/OLMo-7B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OLMo-7B"
    }
   ]
  },
  {
   "slug": "other/olmOCR-2-7B-1025",
   "model_name": "olmOCR-2-7B-1025",
   "display_name": "deepinfra/allenai/olmOCR-2-7B-1025",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "allenai/olmOCR-2-7B-1025"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     },
     "provider_model_id": "deepinfra/allenai/olmOCR-2-7B-1025"
    }
   ],
   "max_input_tokens": 16384,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "released_at": "2025-11-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/olmOCR-2-7B-1025",
    "deepinfra/allenai/olmOCR-2-7B-1025"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra/allenai/olmOCR-2-7B-1025"
    }
   ]
  },
  {
   "slug": "other/olmOCR-7B-0725-FP8",
   "model_name": "olmOCR-7B-0725-FP8",
   "display_name": "olmOCR-7B-0725-FP8",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "allenai/olmOCR-7B-0725-FP8"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "allenai/olmOCR-7B-0725-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "olmOCR-7B-0725-FP8"
    }
   ]
  },
  {
   "slug": "other/openhands-lm-32b-v0.1",
   "model_name": "openhands-lm-32b-v0.1",
   "display_name": "openhands-lm-32b-v0.1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.4"
      }
     },
     "provider_model_id": "all-hands/openhands-lm-32b-v0.1"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "all-hands/openhands-lm-32b-v0.1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "openhands-lm-32b-v0.1"
    }
   ]
  },
  {
   "slug": "other/openorca-7b",
   "model_name": "openorca-7b",
   "display_name": "Mistral 7B OpenOrca",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/openorca-7b"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/openorca-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral 7B OpenOrca"
    }
   ]
  },
  {
   "slug": "other/Ornith-1.0-35B",
   "model_name": "Ornith-1.0-35B",
   "display_name": "deepreinforce-ai/Ornith-1.0-35B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "deepreinforce-ai/Ornith-1.0-35B"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "video_input": true
   },
   "max_output_tokens": 262144,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepreinforce-ai/Ornith-1.0-35B"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "limit",
     "new": "262144",
     "note": "max_output_tokens"
    },
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "structured_output: true→false"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepreinforce-ai/Ornith-1.0-35B"
    }
   ]
  },
  {
   "slug": "other/orpheus-3b-0.1-ft",
   "model_name": "orpheus-3b-0.1-ft",
   "display_name": "Orpheus 3B 0.1 FT",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "15"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "canopylabs/orpheus-3b-0.1-ft"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "released_at": "2025-08-20",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "canopylabs/orpheus-3b-0.1-ft"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Orpheus 3B 0.1 FT"
    }
   ]
  },
  {
   "slug": "other/orpheus-arabic-saudi",
   "model_name": "orpheus-arabic-saudi",
   "display_name": "Canopy Labs Orpheus Arabic Saudi",
   "vendor": "other",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "40"
      }
     },
     "provider_model_id": "canopylabs/orpheus-arabic-saudi"
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-12-16",
   "max_input_tokens": 4000,
   "max_output_tokens": 50000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "canopylabs",
   "status": "beta",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "audio_output": true
   },
   "model_type": "speech_synthesis",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "canopylabs/orpheus-arabic-saudi"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Canopy Labs Orpheus Arabic Saudi"
    }
   ]
  },
  {
   "slug": "other/orpheus-v1-english",
   "model_name": "orpheus-v1-english",
   "display_name": "Canopy Labs Orpheus V1 English",
   "vendor": "other",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "models-dev+truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "22"
      }
     },
     "provider_model_id": "canopylabs/orpheus-v1-english"
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-12-19",
   "max_input_tokens": 4000,
   "max_output_tokens": 50000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "canopylabs",
   "status": "beta",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "audio_output": true
   },
   "model_type": "speech_synthesis",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "canopylabs/orpheus-v1-english"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Canopy Labs Orpheus V1 English"
    }
   ]
  },
  {
   "slug": "other/osmosis-structure-0.6b",
   "model_name": "osmosis-structure-0.6b",
   "display_name": "Osmosis Structure 0.6B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "inference",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "osmosis/osmosis-structure-0.6b"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 4000,
   "max_output_tokens": 2048,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "osmosis",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "osmosis/osmosis-structure-0.6b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Osmosis Structure 0.6B"
    }
   ]
  },
  {
   "slug": "other/owl",
   "model_name": "owl",
   "display_name": "OWL",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2026-05-01",
   "max_input_tokens": 1048756,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "OWL"
    }
   ]
  },
  {
   "slug": "other/owl-alpha",
   "model_name": "owl-alpha",
   "display_name": "Owl Alpha",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/owl-alpha"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/owl-alpha"
    }
   ],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-04-28",
   "max_input_tokens": 1048756,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "status": "alpha",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "openrouter/owl-alpha"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Owl Alpha"
    }
   ]
  },
  {
   "slug": "other/p-image",
   "model_name": "p-image",
   "display_name": "p-image",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.005"
      }
     },
     "provider_model_id": "PrunaAI/p-image"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "PrunaAI/p-image"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "p-image"
    }
   ]
  },
  {
   "slug": "other/p-image-Edit",
   "model_name": "p-image-Edit",
   "display_name": "p-image-Edit",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.01"
      }
     },
     "provider_model_id": "PrunaAI/p-image-Edit"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "PrunaAI/p-image-Edit"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "p-image-Edit"
    }
   ]
  },
  {
   "slug": "other/p-video",
   "model_name": "p-video",
   "display_name": "p-video",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.02"
      }
     },
     "provider_model_id": "PrunaAI/p-video"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image",
     "audio"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "PrunaAI/p-video"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "p-video"
    }
   ]
  },
  {
   "slug": "other/paddleocr-vl",
   "model_name": "paddleocr-vl",
   "display_name": "PaddleOCR-VL",
   "vendor": "other",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "paddlepaddle/paddleocr-vl"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "paddlepaddle/paddleocr-vl"
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2025-10-22",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "paddlepaddle/paddleocr-vl"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PaddleOCR-VL"
    }
   ]
  },
  {
   "slug": "other/PaddleOCR-VL-1.5",
   "model_name": "PaddleOCR-VL-1.5",
   "display_name": "PaddlePaddle/PaddleOCR-VL-1.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "PaddlePaddle/PaddleOCR-VL-1.5"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "PaddlePaddle/PaddleOCR-VL-1.5"
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2026-01-29",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "PaddlePaddle/PaddleOCR-VL-1.5"
   ],
   "intro_i18n": {
    "zh-CN": "PaddleOCR-VL-1.5 是 PaddleOCR-VL 系列的升级版本，在 OmniDocBench v1.5 文档解析基准测试中取得了 94.5% 的准确率，超越了主流通用大模型和专业文档解析模型。该模型创新性地支持文档元素的不规则边界框定位，能够高效处理扫描、倾斜和屏幕截图图像。",
    "zh-TW": "PaddleOCR-VL-1.5 是 PaddleOCR-VL 系列的升級版本，在 OmniDocBench v1.5 文件解析基準測試中達到 94.5% 的準確率，超越主流通用大型模型與專業文件解析模型。創新地支援文件元素的不規則邊界框定位，能有效處理掃描、傾斜與螢幕截圖等圖像。",
    "ja-JP": "PaddleOCR-VL-1.5は、PaddleOCR-VLシリーズのアップグレード版で、OmniDocBench v1.5文書解析ベンチマークで94.5%の精度を達成し、汎用大規模モデルや専門的な文書解析モデルを上回ります。不規則なバウンディングボックスによる文書要素の位置特定を革新的にサポートし、スキャン画像、傾いた画像、スクリーンショットなどにも高精度で対応します。",
    "ru-RU": "PaddleOCR-VL-1.5 — обновлённая версия серии PaddleOCR-VL, достигшая точности 94,5% на бенчмарке OmniDocBench v1.5 по разбору документов, превзойдя ведущие универсальные и специализированные модели. Впервые реализована поддержка локализации элементов документа с нерегулярными рамками, что позволяет эффективно обрабатывать отсканированные, наклонённые и снятые с экрана изображения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PaddlePaddle/PaddleOCR-VL-1.5"
    }
   ]
  },
  {
   "slug": "other/PaddlePaddle/PaddleOCR-VL-0.9B",
   "model_name": "PaddlePaddle/PaddleOCR-VL-0.9B",
   "display_name": "deepinfra/PaddlePaddle/PaddleOCR-VL-0.9B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "deepinfra/PaddlePaddle/PaddleOCR-VL-0.9B"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "prompt_caching": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2025-11-14",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/PaddlePaddle/PaddleOCR-VL-0.9B"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "deepinfra/PaddlePaddle/PaddleOCR-VL-0.9B"
    }
   ]
  },
  {
   "slug": "other/pangu-pro-moe",
   "model_name": "pangu-pro-moe",
   "display_name": "ascend-tribe/pangu-pro-moe",
   "vendor": "other",
   "pricing": [
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "ascend-tribe/pangu-pro-moe"
    }
   ],
   "released_at": "2025-07-02",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "pangu",
   "capabilities": {
    "reasoning": true,
    "stream": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "ascend-tribe/pangu-pro-moe"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ascend-tribe/pangu-pro-moe"
    }
   ]
  },
  {
   "slug": "other/paraphrase-MiniLM-L6-v2",
   "model_name": "paraphrase-MiniLM-L6-v2",
   "display_name": "Sentence Transformers: paraphrase-MiniLM-L6-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/paraphrase-MiniLM-L6-v2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "sentence-transformers/paraphrase-minilm-l6-v2"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/sentence-transformers/paraphrase-MiniLM-L6-v2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true,
    "stream": true
   },
   "max_input_tokens": 512,
   "max_output_tokens": 512,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/sentence-transformers/paraphrase-MiniLM-L6-v2",
    "sentence-transformers/paraphrase-MiniLM-L6-v2",
    "sentence-transformers/paraphrase-minilm-l6-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sentence Transformers: paraphrase-MiniLM-L6-v2"
    }
   ]
  },
  {
   "slug": "other/pareto-code",
   "model_name": "pareto-code",
   "display_name": "Pareto Code Router",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "openrouter/pareto-code"
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2026-04-21",
   "max_input_tokens": 200000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "openrouter/pareto-code"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pareto Code Router"
    }
   ]
  },
  {
   "slug": "other/perceptron-mk1",
   "model_name": "perceptron-mk1",
   "display_name": "Perceptron: Perceptron Mk1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "perceptron/perceptron-mk1"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "perceptron/perceptron-mk1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "perceptron/perceptron-mk1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "perceptron/perceptron-mk1"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-05-12",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perceptron/perceptron-mk1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Perceptron: Perceptron Mk1"
    }
   ]
  },
  {
   "slug": "other/pfnet/plamo-embedding-1b",
   "model_name": "pfnet/plamo-embedding-1b",
   "display_name": "PLaMo Embedding 1B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.019"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "workers-ai/@cf/pfnet/plamo-embedding-1b"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.019"
      }
     },
     "provider_model_id": "@cf/pfnet/plamo-embedding-1b"
    }
   ],
   "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
   "released_at": "2025-09-25",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "plamo",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/pfnet/plamo-embedding-1b",
    "workers-ai/@cf/pfnet/plamo-embedding-1b"
   ],
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PLaMo Embedding 1B"
    }
   ]
  },
  {
   "slug": "other/Platypus2-70B-instruct",
   "model_name": "Platypus2-70B-instruct",
   "display_name": "Platypus2-70B-instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "garage-bAInd/Platypus2-70B-instruct"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "garage-bAInd/Platypus2-70B-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Platypus2-70B-instruct"
    }
   ]
  },
  {
   "slug": "other/playai-tts",
   "model_name": "playai-tts",
   "display_name": "playai-tts",
   "vendor": "other",
   "pricing": [
    {
     "provider": "groq",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "50"
      }
     }
    }
   ],
   "max_output_tokens": 10000,
   "model_type": "speech_synthesis",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "playai-tts"
    }
   ]
  },
  {
   "slug": "other/playground-v2-1024px-aesthetic",
   "model_name": "playground-v2-1024px-aesthetic",
   "display_name": "playground-v2-1024px-aesthetic",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.00013"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.00013"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "playground-v2-1024px-aesthetic"
    }
   ]
  },
  {
   "slug": "other/playground-v2-5-1024px-aesthetic",
   "model_name": "playground-v2-5-1024px-aesthetic",
   "display_name": "playground-v2-5-1024px-aesthetic",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.00013"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.00013"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "playground-v2-5-1024px-aesthetic"
    }
   ]
  },
  {
   "slug": "other/plutotext-r3-emotional",
   "model_name": "plutotext-r3-emotional",
   "display_name": "plutotext-r3-emotional",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "plutotext-r3-emotional"
    }
   ]
  },
  {
   "slug": "other/ppio-kat-coder",
   "model_name": "ppio-kat-coder",
   "display_name": "kat-coder",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "kat-coder"
    }
   ]
  },
  {
   "slug": "other/pythia-12b",
   "model_name": "pythia-12b",
   "display_name": "Pythia 12B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/pythia-12b"
    }
   ],
   "max_input_tokens": 2048,
   "max_output_tokens": 2048,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/pythia-12b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pythia 12B"
    }
   ]
  },
  {
   "slug": "other/Qwerky-72B",
   "model_name": "Qwerky-72B",
   "display_name": "Qwerky 72B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "featherless-ai/Qwerky-72B"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "qwerky-72b:free"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-03-20",
   "max_input_tokens": 32000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwerky",
   "capabilities": {},
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "featherless-ai/Qwerky-72B",
    "qwerky-72b:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Qwerky 72B"
    }
   ]
  },
  {
   "slug": "other/realtime-tts-1.5-max",
   "model_name": "realtime-tts-1.5-max",
   "display_name": "realtime-tts-1.5-max",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "50"
      }
     },
     "provider_model_id": "inworld-ai/realtime-tts-1.5-max"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "realtime_speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inworld-ai/realtime-tts-1.5-max"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "realtime-tts-1.5-max"
    }
   ]
  },
  {
   "slug": "other/realtime-tts-1.5-mini",
   "model_name": "realtime-tts-1.5-mini",
   "display_name": "realtime-tts-1.5-mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "25"
      }
     },
     "provider_model_id": "inworld-ai/realtime-tts-1.5-mini"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "realtime_speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inworld-ai/realtime-tts-1.5-mini"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "realtime-tts-1.5-mini"
    }
   ]
  },
  {
   "slug": "other/realtime-tts-2",
   "model_name": "realtime-tts-2",
   "display_name": "realtime-tts-2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "35"
      }
     },
     "provider_model_id": "inworld-ai/realtime-tts-2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "realtime_speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "inworld-ai/realtime-tts-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "realtime-tts-2"
    }
   ]
  },
  {
   "slug": "other/RedPajama-INCITE-7B-Base",
   "model_name": "RedPajama-INCITE-7B-Base",
   "display_name": "RedPajama-INCITE-7B-Base",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "togethercomputer/RedPajama-INCITE-7B-Base"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/RedPajama-INCITE-7B-Base"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "RedPajama-INCITE-7B-Base"
    }
   ]
  },
  {
   "slug": "other/RedPajama-INCITE-7B-Chat",
   "model_name": "RedPajama-INCITE-7B-Chat",
   "display_name": "RedPajama-INCITE-7B-Chat",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "togethercomputer/RedPajama-INCITE-7B-Chat"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/RedPajama-INCITE-7B-Chat"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "RedPajama-INCITE-7B-Chat"
    }
   ]
  },
  {
   "slug": "other/RedPajama-INCITE-7B-Instruct",
   "model_name": "RedPajama-INCITE-7B-Instruct",
   "display_name": "RedPajama-INCITE-7B-Instruct",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "togethercomputer/RedPajama-INCITE-7B-Instruct"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/RedPajama-INCITE-7B-Instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "RedPajama-INCITE-7B-Instruct"
    }
   ]
  },
  {
   "slug": "other/RedPajama-INCITE-Base-3B-v1",
   "model_name": "RedPajama-INCITE-Base-3B-v1",
   "display_name": "RedPajama-INCITE-Base-3B-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "togethercomputer/RedPajama-INCITE-Base-3B-v1"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/RedPajama-INCITE-Base-3B-v1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "RedPajama-INCITE-Base-3B-v1"
    }
   ]
  },
  {
   "slug": "other/RedPajama-INCITE-Chat-3B-v1",
   "model_name": "RedPajama-INCITE-Chat-3B-v1",
   "display_name": "RedPajama-INCITE-Chat-3B-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "togethercomputer/RedPajama-INCITE-Chat-3B-v1"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/RedPajama-INCITE-Chat-3B-v1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "RedPajama-INCITE-Chat-3B-v1"
    }
   ]
  },
  {
   "slug": "other/RedPajama-INCITE-Instruct-3B-v1",
   "model_name": "RedPajama-INCITE-Instruct-3B-v1",
   "display_name": "RedPajama-INCITE-Instruct-3B-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "togethercomputer/RedPajama-INCITE-Instruct-3B-v1"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/RedPajama-INCITE-Instruct-3B-v1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "RedPajama-INCITE-Instruct-3B-v1"
    }
   ]
  },
  {
   "slug": "other/relace-apply-3",
   "model_name": "relace-apply-3",
   "display_name": "Relace: Relace Apply 3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "relace/relace-apply-3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "relace/relace-apply-3"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-09-26",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "relace/relace-apply-3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Relace: Relace Apply 3"
    }
   ]
  },
  {
   "slug": "other/relace-search",
   "model_name": "relace-search",
   "display_name": "Relace: Relace Search",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "relace/relace-search"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "relace/relace-search"
    }
   ],
   "intro": "Tool-capable chat model for instruction following and agentic application workflows",
   "released_at": "2025-12-09",
   "max_input_tokens": 256000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "max_tokens",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "relace/relace-search"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Relace: Relace Search"
    }
   ]
  },
  {
   "slug": "other/ReMM-SLERP-L2-13B",
   "model_name": "ReMM-SLERP-L2-13B",
   "display_name": "ReMM SLERP 13B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "provider_model_id": "undi95/remm-slerp-l2-13b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7989999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2069999999999999"
      }
     },
     "provider_model_id": "undi95/remm-slerp-l2-13b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     },
     "provider_model_id": "undi95/remm-slerp-l2-13b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "Undi95/ReMM-SLERP-L2-13B"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2023-07-22",
   "max_input_tokens": 6144,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2023-06",
   "family": "llama",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_a",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Undi95/ReMM-SLERP-L2-13B",
    "remm-slerp-l2-13b",
    "undi95/remm-slerp-l2-13b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ReMM SLERP 13B"
    }
   ]
  },
  {
   "slug": "other/remove_background",
   "model_name": "remove_background",
   "display_name": "remove_background",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.018"
      }
     },
     "provider_model_id": "Bria/remove_background"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/remove_background"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "remove_background"
    }
   ]
  },
  {
   "slug": "other/replace_background",
   "model_name": "replace_background",
   "display_name": "replace_background",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.04"
      }
     },
     "provider_model_id": "Bria/replace_background"
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Bria/replace_background"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "replace_background"
    }
   ]
  },
  {
   "slug": "other/reranker",
   "model_name": "reranker",
   "display_name": "reranker",
   "vendor": "other",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11416395"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11416395"
      }
     }
    }
   ],
   "released_at": "2025-04-23",
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114370748",
     "new": "0.11416395"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114370748",
     "new": "0.11416395"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114326597",
     "new": "0.114370748"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114326597",
     "new": "0.114370748"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114414143",
     "new": "0.114326597"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114414143",
     "new": "0.114326597"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114368084",
     "new": "0.114414143"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114368084",
     "new": "0.114414143"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.114399787",
     "new": "0.114368084"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.114399787",
     "new": "0.114368084"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "0.1138097",
     "new": "0.114399787"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.1138097",
     "new": "0.114399787"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "reranker"
    }
   ]
  },
  {
   "slug": "other/rime-arcana-v2",
   "model_name": "rime-arcana-v2",
   "display_name": "Rime Labs Arcana v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "10"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "rime-labs/rime-arcana-v2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "rime-labs/rime-arcana-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Rime Labs Arcana v2"
    }
   ]
  },
  {
   "slug": "other/rime-arcana-v3",
   "model_name": "rime-arcana-v3",
   "display_name": "rime-arcana-v3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "10"
      }
     },
     "provider_model_id": "rime-labs/rime-arcana-v3"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "rime-labs/rime-arcana-v3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rime-arcana-v3"
    }
   ]
  },
  {
   "slug": "other/rime-arcana-v3-turbo",
   "model_name": "rime-arcana-v3-turbo",
   "display_name": "rime-arcana-v3-turbo",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "10"
      }
     },
     "provider_model_id": "rime-labs/rime-arcana-v3-turbo"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "rime-labs/rime-arcana-v3-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rime-arcana-v3-turbo"
    }
   ]
  },
  {
   "slug": "other/rime-mist-v2",
   "model_name": "rime-mist-v2",
   "display_name": "rime-mist-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "10"
      }
     },
     "provider_model_id": "rime-labs/rime-mist-v2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "rime-labs/rime-mist-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rime-mist-v2"
    }
   ]
  },
  {
   "slug": "other/rime-mist-v3",
   "model_name": "rime-mist-v3",
   "display_name": "rime-mist-v3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "10"
      }
     },
     "provider_model_id": "rime-labs/rime-mist-v3"
    }
   ],
   "max_input_tokens": 448,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "rime-labs/rime-mist-v3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rime-mist-v3"
    }
   ]
  },
  {
   "slug": "other/rime-mist-v3-omni",
   "model_name": "rime-mist-v3-omni",
   "display_name": "rime-mist-v3-omni",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "10"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "rime-labs/rime-mist-v3-omni"
    }
   ],
   "max_input_tokens": 448,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "rime-labs/rime-mist-v3-omni"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rime-mist-v3-omni"
    }
   ]
  },
  {
   "slug": "other/Ring-2.5-1T",
   "model_name": "Ring-2.5-1T",
   "display_name": "Ring-2.5-1T",
   "vendor": "other",
   "pricing": [
    {
     "provider": "antgroup",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "released_at": "2026-02-15",
   "max_input_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "与之前发布的Ring-1T相比，Ring-2.5-1T在生成效率、推理深度和长时间任务执行能力三个关键维度上实现了显著提升：**生成效率**：通过采用高比例的线性注意力机制，Ring-2.5-1T将内存访问开销减少了10倍以上。在处理超过32K令牌的序列时，其生成吞吐量提高了3倍以上，非常适合深度推理和长时间任务执行。**深度推理**：基于RLVR，引入了密集奖励机制，为推理过程的严谨性提供反馈。这使得Ring-2.5-1T在IMO 2025和CMO 2025（自评）中达到了金牌级表现。**长时间任务执行**：通过大规模完全异步的基于代理的强化学习训练，模型显著增强了其在长时间内自主执行复杂任务的能力。这使得Ring-2.5-1T能够无缝集成到Claude Code和OpenClaw个人AI助手等代理编程框架中。",
    "zh-TW": "與先前發布的 Ring-1T 相比，Ring-2.5-1T 在生成效率、推理深度和長期任務執行能力三個關鍵維度上實現了顯著提升：**生成效率**：通過採用高比例的線性注意力機制，Ring-2.5-1T 將內存訪問開銷降低了超過 10 倍。在處理超過 32K 令牌的序列時，其生成吞吐量提高了超過 3 倍，特別適合深度推理和長期任務執行。**深度推理**：基於 RLVR，引入了一種密集獎勵機制，為推理過程的嚴謹性提供反饋。這使得 Ring-2.5-1T 在 IMO 2025 和 CMO 2025（自評）中達到了金牌級別的表現。**長期任務執行**：通過大規模完全異步的基於代理的強化學習訓練，該模型顯著增強了其在長時間內自主執行複雜任務的能力。這使得 Ring-2.5-1T 能夠無縫集成到 Claude Code 和 OpenClaw 個人 AI 助手等代理編程框架中。",
    "ja-JP": "以前リリースされたRing-1Tと比較して、Ring-2.5-1Tは生成効率、推論深度、長期タスク実行能力の3つの主要な側面で大幅な改善を達成しています。生成効率**: 線形注意メカニズムを高割合で活用することで、Ring-2.5-1Tはメモリアクセスオーバーヘッドを10倍以上削減します。32Kトークンを超えるシーケンスを処理する際、生成スループットが3倍以上向上し、深い推論や長期タスク実行に特に適しています。推論深度**: RLVRを基盤に、推論プロセスの厳密さにフィードバックを提供する密な報酬メカニズムを導入しています。これにより、Ring-2.5-1TはIMO 2025およびCMO 2025で金メダルレベルの性能を達成します（自己評価）。長期タスク実行**: 大規模な完全非同期エージェントベースの強化学習トレーニングを通じて、モデルは複雑なタスクを長期間にわたって自律的に実行する能力を大幅に向上させます。これにより、Ring-2.5-1TはClaude CodeやOpenClawの個人AIアシスタントなどのエージェントプログラミングフレームワークとシームレスに統合できます。",
    "ru-RU": "По сравнению с ранее выпущенной Ring-1T, Ring-2.5-1T достигает значительных улучшений по трем ключевым направлениям: эффективность генерации, глубина рассуждений и способность выполнения задач на длинных горизонтах: **Эффективность генерации**: Используя высокую долю линейных механизмов внимания, Ring-2.5-1T снижает накладные расходы на доступ к памяти более чем в 10 раз. При обработке последовательностей, превышающих 32K токенов, она обеспечивает более чем в 3 раза большую пропускную способность генерации, что делает её особенно подходящей для глубоких рассуждений и выполнения задач на длинных горизонтах. **Глубокие рассуждения**: На основе RLVR введен плотный механизм вознаграждения, который предоставляет обратную связь о строгости процесса рассуждений. Это позволяет Ring-2.5-1T достигать уровня золотой медали как на IMO 2025, так и на CMO 2025 (самооценка). **Выполнение задач на длинных горизонтах**: Благодаря крупномасштабному полностью асинхронному обучению с подкреплением на основе агентов, модель значительно улучшает свою способность автономно выполнять сложные задачи в течение длительных периодов. Это позволяет Ring-2.5-1T бесшовно интегрироваться с фреймворками программирования агентов, такими как Claude Code и OpenClaw персональные ИИ-ассистенты."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Ring-2.5-1T"
    }
   ]
  },
  {
   "slug": "other/rnj-1",
   "model_name": "rnj-1",
   "display_name": "rnj-1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "rnj-1"
    }
   ]
  },
  {
   "slug": "other/rnj-1:8b",
   "model_name": "rnj-1:8b",
   "display_name": "rnj-1:8b",
   "vendor": "other",
   "pricing": [],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-12-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "rnj",
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "rnj-1:8b"
    }
   ]
  },
  {
   "slug": "other/roc",
   "model_name": "roc",
   "display_name": "roc",
   "vendor": "other",
   "pricing": [
    {
     "provider": "evroc",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11.516"
      }
     },
     "provider_model_id": "evroc/roc"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-06-06",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "evroc/roc"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "roc"
    }
   ]
  },
  {
   "slug": "other/rocinante-12b",
   "model_name": "rocinante-12b",
   "display_name": "TheDrummer: Rocinante 12B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     },
     "provider_model_id": "thedrummer/rocinante-12b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "thedrummer/rocinante-12b"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2024-09-30",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-04",
   "deprecated": true,
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "thedrummer/rocinante-12b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TheDrummer: Rocinante 12B"
    }
   ]
  },
  {
   "slug": "other/Rocinante-12B-v1.1",
   "model_name": "Rocinante-12B-v1.1",
   "display_name": "Rocinante 12b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.408"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.595"
      }
     },
     "provider_model_id": "TheDrummer/Rocinante-12B-v1.1"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2024-01-01",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/Rocinante-12B-v1.1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Rocinante 12b"
    }
   ]
  },
  {
   "slug": "other/rolm-ocr",
   "model_name": "rolm-ocr",
   "display_name": "Rolm OCR",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/rolm-ocr"
    }
   ],
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/rolm-ocr"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Rolm OCR"
    }
   ]
  },
  {
   "slug": "other/route-llm",
   "model_name": "route-llm",
   "display_name": "Route LLM",
   "vendor": "other",
   "pricing": [
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2024-01-01",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "gpt",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Route LLM"
    }
   ]
  },
  {
   "slug": "other/router",
   "model_name": "router",
   "display_name": "Switchpoint Router",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.4"
      }
     },
     "provider_model_id": "switchpoint/router"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.4"
      }
     },
     "provider_model_id": "switchpoint/router"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2025-07-12",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "audio_input": true
   },
   "docs_url": "https://openrouter.ai/switchpoint/router",
   "model_type": "text_generation",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "switchpoint/router"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "capability",
     "note": "structured_output: true→false"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Switchpoint Router"
    }
   ]
  },
  {
   "slug": "other/saaras:v3",
   "model_name": "saaras:v3",
   "display_name": "Sarvam: Saaras V3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "88"
      }
     },
     "provider_model_id": "sarvam/saaras:v3"
    }
   ],
   "released_at": "2026-02-11",
   "max_input_tokens": 2046,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "pdf_input": true,
    "audio_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sarvam/saaras:v3"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sarvam: Saaras V3"
    }
   ]
  },
  {
   "slug": "other/Sao10K/L3-8B-Stheno-v3.2",
   "model_name": "Sao10K/L3-8B-Stheno-v3.2",
   "display_name": "L3 8B Stheno V3.2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "L3-8B-Stheno-v3.2"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "sao10K/L3-8B-stheno-v3.2"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "novita/Sao10K/L3-8B-Stheno-v3.2"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-11-29",
   "max_input_tokens": 8192,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "L3-8B-Stheno-v3.2",
    "novita/Sao10K/L3-8B-Stheno-v3.2",
    "sao10K/L3-8B-stheno-v3.2",
    "sao10k/L3-8B-Stheno-v3.2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "L3 8B Stheno V3.2"
    }
   ]
  },
  {
   "slug": "other/Sao10K/L3.1-70B-Euryale-v2.2",
   "model_name": "Sao10K/L3.1-70B-Euryale-v2.2",
   "display_name": "Llama 3.1 70B Euryale",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "L3.1-70B-Euryale-v2.2"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.306"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.357"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "max_input_tokens": 20480,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "prompt_caching": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "L3.1-70B-Euryale-v2.2",
    "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.1 70B Euryale"
    }
   ]
  },
  {
   "slug": "other/Sao10K/L3.3-70B-Euryale-v2.3",
   "model_name": "Sao10K/L3.3-70B-Euryale-v2.3",
   "display_name": "Llama 3.3 70B Euryale",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.65"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "L3.3-70B-Euryale-v2.3"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-12-06",
   "max_input_tokens": 20480,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {
    "prompt_caching": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "L3.3-70B-Euryale-v2.3",
    "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Llama 3.3 70B Euryale"
    }
   ]
  },
  {
   "slug": "other/sao10k/l31-70b-euryale-v2.2",
   "model_name": "sao10k/l31-70b-euryale-v2.2",
   "display_name": "L31 70B Euryale V2.2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.48"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.48"
      }
     },
     "provider_model_id": "l31-70b-euryale-v2.2"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.48"
      }
     },
     "provider_model_id": "sao10K/l31-70b-euryale-v2.2"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.48"
      }
     },
     "provider_model_id": "novita/sao10k/l31-70b-euryale-v2.2"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2024-09-19",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "l31-70b-euryale-v2.2",
    "novita/sao10k/l31-70b-euryale-v2.2",
    "sao10K/l31-70b-euryale-v2.2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "L31 70B Euryale V2.2"
    }
   ]
  },
  {
   "slug": "other/sarvam-105b",
   "model_name": "sarvam-105b",
   "display_name": "Sarvam-105B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "sarvam/sarvam-105b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.045"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.177"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      }
     }
    }
   ],
   "intro": "Flagship Indian-language reasoning model for enterprise multilingual applications",
   "released_at": "2026-02-18",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "sarvam",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sarvam/sarvam-105b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sarvam-105B"
    }
   ]
  },
  {
   "slug": "other/sarvam-30b",
   "model_name": "sarvam-30b",
   "display_name": "Sarvam-30B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "sarvam/sarvam-30b"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.028"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.111"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.017"
      }
     }
    }
   ],
   "intro": "Efficient Indian-language reasoning model for chat, coding, and multilingual work",
   "released_at": "2026-02-18",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "sarvam",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "sarvam/sarvam-30b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sarvam-30B"
    }
   ]
  },
  {
   "slug": "other/semantic-ranker-default",
   "model_name": "semantic-ranker-default",
   "display_name": "semantic-ranker-default",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1000"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "semantic-ranker-default"
    }
   ]
  },
  {
   "slug": "other/semantic-ranker-default-002",
   "model_name": "semantic-ranker-default-002",
   "display_name": "semantic-ranker-default-002",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1000"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "semantic-ranker-default-002"
    }
   ]
  },
  {
   "slug": "other/semantic-ranker-default-003",
   "model_name": "semantic-ranker-default-003",
   "display_name": "semantic-ranker-default-003",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1000"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "semantic-ranker-default-003"
    }
   ]
  },
  {
   "slug": "other/semantic-ranker-default-004",
   "model_name": "semantic-ranker-default-004",
   "display_name": "semantic-ranker-default-004",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1000"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "semantic-ranker-default-004"
    }
   ]
  },
  {
   "slug": "other/semantic-ranker-fast-004",
   "model_name": "semantic-ranker-fast-004",
   "display_name": "semantic-ranker-fast-004",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1000"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "semantic-ranker-fast-004"
    }
   ]
  },
  {
   "slug": "other/sense-chat-5",
   "model_name": "sense-chat-5",
   "display_name": "SenseChat-5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    }
   ],
   "released_at": "2024-04-23",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "SenseChat-5"
    }
   ]
  },
  {
   "slug": "other/sense-chat-turbo",
   "model_name": "sense-chat-turbo",
   "display_name": "SenseChat-Turbo",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    }
   ],
   "released_at": "2024-04-23",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "SenseChat-Turbo"
    }
   ]
  },
  {
   "slug": "other/sense-nova-v6-pro",
   "model_name": "sense-nova-v6-pro",
   "display_name": "SenseNova-V6-Pro",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     }
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "SenseNova-V6-Pro"
    }
   ]
  },
  {
   "slug": "other/sense-nova-v6-reasoner",
   "model_name": "sense-nova-v6-reasoner",
   "display_name": "SenseNova-V6-Reasoner",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      }
     }
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "SenseNova-V6-Reasoner"
    }
   ]
  },
  {
   "slug": "other/sense-nova-v6-turbo",
   "model_name": "sense-nova-v6-turbo",
   "display_name": "SenseNova-V6-Turbo",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.65"
      }
     }
    }
   ],
   "released_at": "2025-05-07",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "SenseNova-V6-Turbo"
    }
   ]
  },
  {
   "slug": "other/siliconflow-ascend-tribe-pangu-pro-moe",
   "model_name": "siliconflow-ascend-tribe-pangu-pro-moe",
   "display_name": "ascend-tribe/pangu-pro-moe",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.572"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "ascend-tribe/pangu-pro-moe"
    }
   ]
  },
  {
   "slug": "other/sincap",
   "model_name": "sincap",
   "display_name": "Sincap",
   "vendor": "other",
   "pricing": [
    {
     "provider": "llmtr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2026-05-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sincap"
    }
   ]
  },
  {
   "slug": "other/Sinong1.0-32B",
   "model_name": "Sinong1.0-32B",
   "display_name": "Sinong1.0-32B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29426264"
      }
     }
    }
   ],
   "released_at": "2026-01-15",
   "max_input_tokens": 32000,
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29440336",
     "new": "0.29426264"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29460788",
     "new": "0.29440336"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29491844",
     "new": "0.29460788"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29497866",
     "new": "0.29491844"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.29487424",
     "new": "0.29497866"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2943579",
     "new": "0.29487424"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sinong1.0-32B"
    }
   ]
  },
  {
   "slug": "other/Skyfall-31B-v4.2",
   "model_name": "Skyfall-31B-v4.2",
   "display_name": "TheDrummer Skyfall 31B v4.2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "TheDrummer/Skyfall-31B-v4.2"
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2026-03-26",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/Skyfall-31B-v4.2"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TheDrummer Skyfall 31B v4.2"
    }
   ]
  },
  {
   "slug": "other/skyfall-36b-v2",
   "model_name": "skyfall-36b-v2",
   "display_name": "TheDrummer: Skyfall 36B V2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "thedrummer/skyfall-36b-v2"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.493"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.493"
      }
     },
     "provider_model_id": "TheDrummer/skyfall-36b-v2"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "thedrummer/skyfall-36b-v2"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2025-03-11",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2024-06",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/skyfall-36b-v2",
    "thedrummer/skyfall-36b-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TheDrummer: Skyfall 36B V2"
    }
   ]
  },
  {
   "slug": "other/small",
   "model_name": "small",
   "display_name": "Kilo Auto Small",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "kilo-auto/small"
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2026-03-15",
   "max_input_tokens": 400000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "kilo-auto/small"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Kilo Auto Small"
    }
   ]
  },
  {
   "slug": "other/snowflake-arctic-embed-l-v2.0",
   "model_name": "snowflake-arctic-embed-l-v2.0",
   "display_name": "snowflake-arctic-embed-l-v2.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "snowflake-arctic-embed-l-v2.0"
    }
   ]
  },
  {
   "slug": "other/snowflake-arctic-embed-m-v2.0",
   "model_name": "snowflake-arctic-embed-m-v2.0",
   "display_name": "snowflake-arctic-embed-m-v2.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "snowflake",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "snowflake-arctic-embed-m-v2.0"
    }
   ]
  },
  {
   "slug": "other/sofya-research",
   "model_name": "sofya-research",
   "display_name": "Sofya Research",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "65.625"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "65.625"
      }
     }
    }
   ],
   "released_at": "2026-06-19",
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Sofya Research"
    }
   ]
  },
  {
   "slug": "other/solar-mini",
   "model_name": "solar-mini",
   "display_name": "solar-mini",
   "vendor": "other",
   "pricing": [
    {
     "provider": "upstage",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2024-06-12",
   "knowledge_cutoff": "2024-09",
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "solar-mini",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Solar Mini 是一款紧凑型大语言模型，性能超越 GPT-3.5，具备强大的多语言能力，支持英语和韩语，提供高效的小体积解决方案。",
    "zh-TW": "Solar Mini 是一款緊湊型大型語言模型，效能超越 GPT-3.5，具備強大的多語言能力，支援英文與韓文，提供高效能且佔用資源小的解決方案。",
    "ja-JP": "Solar Miniは、GPT-3.5を上回る性能を持つコンパクトなLLMで、英語と韓国語に対応した多言語機能を備え、効率的な小型ソリューションを提供します。",
    "ru-RU": "Solar Mini — компактная LLM-модель, превосходящая GPT-3.5, с мощной многоязычной поддержкой английского и корейского языков, предлагающая эффективное решение с малым объемом."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "solar-mini"
    }
   ]
  },
  {
   "slug": "other/solar-pro",
   "model_name": "solar-pro",
   "display_name": "Solar Pro",
   "vendor": "other",
   "pricing": [
    {
     "provider": "upstage",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    }
   ],
   "released_at": "2024-11-26",
   "max_input_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Solar Pro 是 Upstage 推出的高智能大语言模型，专注于单 GPU 上的指令跟随任务，IFEval 得分超过 80。目前支持英语，完整版本计划于 2024 年 11 月发布，届时将扩展语言支持并提升上下文长度。",
    "zh-TW": "Solar Pro 是 Upstage 推出的高智慧大型語言模型，專注於單 GPU 上的指令遵循任務，IFEval 分數超過 80。目前支援英文，完整版本預計於 2024 年 11 月推出，將擴展語言支援與上下文長度。",
    "ja-JP": "Solar Proは、Upstageが提供する高知能LLMで、単一GPU上での指示追従に特化し、IFEvalスコア80以上を記録しています。現在は英語に対応しており、2024年11月の正式リリースでは対応言語とコンテキスト長が拡張される予定です。",
    "ru-RU": "Solar Pro — интеллектуальная LLM-модель от Upstage, ориентированная на следование инструкциям на одном GPU, с результатами IFEval выше 80. В настоящее время поддерживает английский язык; полный релиз с расширенной языковой поддержкой и увеличенным контекстом запланирован на ноябрь 2024 года."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Solar Pro"
    }
   ]
  },
  {
   "slug": "other/solar-pro2",
   "model_name": "solar-pro2",
   "display_name": "solar-pro2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "upstage",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2025-05-20",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 65536,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "solar-pro",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "solar-pro2"
    }
   ]
  },
  {
   "slug": "other/solar-pro3",
   "model_name": "solar-pro3",
   "display_name": "solar-pro3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "upstage",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2026-01",
   "knowledge_cutoff": "2025-03",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "solar-pro",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "solar-pro3"
    }
   ]
  },
  {
   "slug": "other/sonic",
   "model_name": "sonic",
   "display_name": "Cartesia Sonic",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "65"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "65"
      }
     },
     "provider_model_id": "cartesia/sonic"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "released_at": "2026-03-16",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cartesia/sonic"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cartesia Sonic"
    }
   ]
  },
  {
   "slug": "other/sonic-2",
   "model_name": "sonic-2",
   "display_name": "Cartesia Sonic 2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "65"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "65"
      }
     },
     "provider_model_id": "cartesia/sonic-2"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "released_at": "2026-03-25",
   "max_input_tokens": 448,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cartesia/sonic-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cartesia Sonic 2"
    }
   ]
  },
  {
   "slug": "other/sonic-3",
   "model_name": "sonic-3",
   "display_name": "Cartesia Sonic 3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "65"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "65"
      }
     },
     "provider_model_id": "cartesia/sonic-3"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "released_at": "2026-03-25",
   "max_input_tokens": 448,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cartesia/sonic-3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Cartesia Sonic 3"
    }
   ]
  },
  {
   "slug": "other/sonic-3.5",
   "model_name": "sonic-3.5",
   "display_name": "sonic-3.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "cartesia/sonic-3.5"
    }
   ],
   "max_input_tokens": 448,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "model_type": "speech_synthesis",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "cartesia/sonic-3.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sonic-3.5"
    }
   ]
  },
  {
   "slug": "other/sora",
   "model_name": "sora",
   "display_name": "sora",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.15"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sora"
    }
   ]
  },
  {
   "slug": "other/sorcererlm-8x22b",
   "model_name": "sorcererlm-8x22b",
   "display_name": "SorcererLM 8x22B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "raifle/sorcererlm-8x22b"
    }
   ],
   "capabilities": {},
   "released_at": "2024-11-08",
   "max_input_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "raifle/sorcererlm-8x22b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "SorcererLM 8x22B"
    }
   ]
  },
  {
   "slug": "other/SSD-1B",
   "model_name": "SSD-1B",
   "display_name": "SSD-1B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.00013"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.00013"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "SSD-1B"
    }
   ]
  },
  {
   "slug": "other/stable-audio-25/text-to-audio",
   "model_name": "stable-audio-25/text-to-audio",
   "display_name": "Stable Audio 2.5 (Text-to-Audio)",
   "vendor": "other",
   "pricing": [],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2025-10-08",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "fal-ai/stable-audio-25/text-to-audio"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Stable Audio 2.5 (Text-to-Audio)"
    }
   ]
  },
  {
   "slug": "other/stable-diffusion-3.5-large",
   "model_name": "stable-diffusion-3.5-large",
   "display_name": "Stable Diffusion 3.5 Large",
   "vendor": "other",
   "pricing": [
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-10-22",
   "max_input_tokens": 256,
   "max_output_tokens": 1,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "stable-diffusion",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Stable Diffusion 3.5 Large"
    }
   ]
  },
  {
   "slug": "other/stable-diffusion-xl-1024-v1-0",
   "model_name": "stable-diffusion-xl-1024-v1-0",
   "display_name": "stable-diffusion-xl-1024-v1-0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.00013"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.00013"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "stable-diffusion-xl-1024-v1-0"
    }
   ]
  },
  {
   "slug": "other/stablecode-3b",
   "model_name": "stablecode-3b",
   "display_name": "stablecode-3b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "stablecode-3b"
    }
   ]
  },
  {
   "slug": "other/Starcannon-Unleashed-12B-v1.0",
   "model_name": "Starcannon-Unleashed-12B-v1.0",
   "display_name": "Mistral Nemo Starcannon 12b v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.49299999999999994"
      }
     },
     "provider_model_id": "VongolaChouko/Starcannon-Unleashed-12B-v1.0"
    }
   ],
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2024-07-01",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mistral-nemo",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "VongolaChouko/Starcannon-Unleashed-12B-v1.0"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mistral Nemo Starcannon 12b v1"
    }
   ]
  },
  {
   "slug": "other/starcoder-16b",
   "model_name": "starcoder-16b",
   "display_name": "starcoder-16b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "starcoder-16b"
    }
   ]
  },
  {
   "slug": "other/starcoder-7b",
   "model_name": "starcoder-7b",
   "display_name": "starcoder-7b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "starcoder-7b"
    }
   ]
  },
  {
   "slug": "other/starcoder2-15b",
   "model_name": "starcoder2-15b",
   "display_name": "starcoder2-15b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "starcoder2-15b"
    }
   ]
  },
  {
   "slug": "other/starcoder2-3b",
   "model_name": "starcoder2-3b",
   "display_name": "starcoder2-3b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "starcoder2-3b"
    }
   ]
  },
  {
   "slug": "other/starcoder2-7b",
   "model_name": "starcoder2-7b",
   "display_name": "starcoder2-7b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "starcoder2-7b"
    }
   ]
  },
  {
   "slug": "other/StripedHyena-Hessian-7B",
   "model_name": "StripedHyena-Hessian-7B",
   "display_name": "StripedHyena-Hessian-7B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "togethercomputer/StripedHyena-Hessian-7B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/StripedHyena-Hessian-7B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "StripedHyena-Hessian-7B"
    }
   ]
  },
  {
   "slug": "other/StripedHyena-Nous-7B",
   "model_name": "StripedHyena-Nous-7B",
   "display_name": "StripedHyena-Nous-7B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "togethercomputer/StripedHyena-Nous-7B"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "togethercomputer/StripedHyena-Nous-7B"
   ],
   "intro_i18n": {
    "zh-CN": "StripedHyena Nous（7B）通过架构与策略提升计算效率。",
    "zh-TW": "StripedHyena Nous（7B）透過其架構與策略實現更高的運算效率。",
    "ja-JP": "StripedHyena Nous（7B）は、アーキテクチャと戦略により計算効率を向上させたモデルです。",
    "ru-RU": "StripedHyena Nous (7B) обеспечивает повышенную вычислительную эффективность благодаря своей архитектуре и стратегии."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "StripedHyena-Nous-7B"
    }
   ]
  },
  {
   "slug": "other/syn:large:text",
   "model_name": "syn:large:text",
   "display_name": "syn:large:text",
   "vendor": "other",
   "pricing": [
    {
     "provider": "synthetic",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    }
   ],
   "released_at": "2026-06-16",
   "max_input_tokens": 524288,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "syn:large:text"
    }
   ]
  },
  {
   "slug": "other/syn:large:vision",
   "model_name": "syn:large:vision",
   "display_name": "syn:large:vision",
   "vendor": "other",
   "pricing": [
    {
     "provider": "synthetic",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.95"
      }
     }
    }
   ],
   "released_at": "2026-06-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "syn:large:vision"
    }
   ]
  },
  {
   "slug": "other/syn:small:text",
   "model_name": "syn:small:text",
   "display_name": "syn:small:text",
   "vendor": "other",
   "pricing": [
    {
     "provider": "synthetic",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "released_at": "2026-01-19",
   "max_input_tokens": 196608,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "syn:small:text"
    }
   ]
  },
  {
   "slug": "other/syn:small:vision",
   "model_name": "syn:small:vision",
   "display_name": "syn:small:vision",
   "vendor": "other",
   "pricing": [
    {
     "provider": "synthetic",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     }
    }
   ],
   "released_at": "2026-04-21",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "syn:small:vision"
    }
   ]
  },
  {
   "slug": "other/synth",
   "model_name": "synth",
   "display_name": "Synth",
   "vendor": "other",
   "pricing": [],
   "intro": "TrustedRouter synthesis orchestration alias that combines multiple model responses into one answer.",
   "released_at": "2026-06-20",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Synth"
    }
   ]
  },
  {
   "slug": "other/synth-code",
   "model_name": "synth-code",
   "display_name": "Synth Code",
   "vendor": "other",
   "pricing": [],
   "intro": "TrustedRouter code synthesis orchestration alias that combines multiple model responses into one answer.",
   "released_at": "2026-06-20",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Synth Code"
    }
   ]
  },
  {
   "slug": "other/taichu_llm",
   "model_name": "taichu_llm",
   "display_name": "Taichu-LLM",
   "vendor": "other",
   "pricing": [
    {
     "provider": "taichu",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "紫东太初大语言模型是一款高性能文本生成模型，采用完全国产的全栈技术开发。通过对百亿参数基础模型的结构化压缩和任务优化，显著增强了复杂文本理解和知识推理能力。擅长长文档分析、跨语言信息提取和知识约束生成等场景。",
    "zh-TW": "紫東太初大語言模型是一款高性能文本生成模型，基於完全國產的全棧技術開發。通過對百億參數基礎模型的結構壓縮和任務特定優化，顯著增強了複雜文本理解和知識推理能力。它在長文檔分析、跨語言信息提取和知識約束生成等場景中表現出色。",
    "ja-JP": "Zidong Taichu大規模言語モデルは、完全に国内のフルスタック技術を使用して開発された高性能テキスト生成モデルです。1000億パラメータのベースモデルの構造的圧縮とタスク固有の最適化を通じて、複雑なテキスト理解と知識推論能力を大幅に向上させています。長文分析、クロスリンガル情報抽出、知識制約生成などのシナリオで優れた性能を発揮します。",
    "ru-RU": "Большая языковая модель Zidong Taichu — это высокопроизводительная модель генерации текста, разработанная с использованием полностью отечественных технологий полного цикла. Благодаря структурной компрессии базовой модели с сотнями миллиардов параметров и оптимизации для конкретных задач, она значительно улучшает понимание сложных текстов и возможности рассуждений на основе знаний. Она превосходит в таких сценариях, как анализ длинных документов, извлечение информации на разных языках и генерация, ограниченная знаниями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Taichu-LLM"
    }
   ]
  },
  {
   "slug": "other/taichu_llm_14b",
   "model_name": "taichu_llm_14b",
   "display_name": "Taichu-LLM-14B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "taichu",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "紫东太初大语言模型是一款高性能文本生成模型，采用完全国产的全栈技术开发。通过对百亿参数基础模型的结构化压缩和任务优化，显著增强了复杂文本理解和知识推理能力。擅长长文档分析、跨语言信息提取和知识约束生成等场景。",
    "zh-TW": "紫東太初大語言模型是一款高性能文本生成模型，基於完全國產的全棧技術開發。通過對百億參數基礎模型的結構壓縮和任務特定優化，顯著增強了複雜文本理解和知識推理能力。它在長文檔分析、跨語言信息提取和知識約束生成等場景中表現出色。",
    "ja-JP": "Zidong Taichu大規模言語モデルは、完全に国内のフルスタック技術を使用して開発された高性能テキスト生成モデルです。1000億パラメータのベースモデルの構造的圧縮とタスク固有の最適化を通じて、複雑なテキスト理解と知識推論能力を大幅に向上させています。長文分析、クロスリンガル情報抽出、知識制約生成などのシナリオで優れた性能を発揮します。",
    "ru-RU": "Большая языковая модель Zidong Taichu — это высокопроизводительная модель генерации текста, разработанная с использованием полностью отечественных технологий полного цикла. Благодаря структурной компрессии базовой модели с сотнями миллиардов параметров и оптимизации для конкретных задач, она значительно улучшает понимание сложных текстов и возможности рассуждений на основе знаний. Она превосходит в таких сценариях, как анализ длинных документов, извлечение информации на разных языках и генерация, ограниченная знаниями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Taichu-LLM-14B"
    }
   ]
  },
  {
   "slug": "other/taichu_llm_2b",
   "model_name": "taichu_llm_2b",
   "display_name": "Taichu-LLM-2B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "taichu",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.132353"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "紫东太初大语言模型是一款高性能文本生成模型，采用完全国产的全栈技术开发。通过对百亿参数基础模型的结构化压缩和任务优化，显著增强了复杂文本理解和知识推理能力。擅长长文档分析、跨语言信息提取和知识约束生成等场景。",
    "zh-TW": "紫東太初大語言模型是一款高性能文本生成模型，基於完全國產的全棧技術開發。通過對百億參數基礎模型的結構壓縮和任務特定優化，顯著增強了複雜文本理解和知識推理能力。它在長文檔分析、跨語言信息提取和知識約束生成等場景中表現出色。",
    "ja-JP": "Zidong Taichu大規模言語モデルは、完全に国内のフルスタック技術を使用して開発された高性能テキスト生成モデルです。1000億パラメータのベースモデルの構造的圧縮とタスク固有の最適化を通じて、複雑なテキスト理解と知識推論能力を大幅に向上させています。長文分析、クロスリンガル情報抽出、知識制約生成などのシナリオで優れた性能を発揮します。",
    "ru-RU": "Большая языковая модель Zidong Taichu — это высокопроизводительная модель генерации текста, разработанная с использованием полностью отечественных технологий полного цикла. Благодаря структурной компрессии базовой модели с сотнями миллиардов параметров и оптимизации для конкретных задач, она значительно улучшает понимание сложных текстов и возможности рассуждений на основе знаний. Она превосходит в таких сценариях, как анализ длинных документов, извлечение информации на разных языках и генерация, ограниченная знаниями."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Taichu-LLM-2B"
    }
   ]
  },
  {
   "slug": "other/taichu_o1",
   "model_name": "taichu_o1",
   "display_name": "Taichu-O1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "taichu",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "taichu_o1是下一代推理大模型，通过多模态交互和强化学习实现类人链式思维。支持复杂决策模拟，同时保持高精度输出，揭示可解释的推理路径。适用于策略分析、深度思考等场景。",
    "zh-TW": "taichu_o1 是一款下一代推理大模型，通過多模態交互和強化學習實現類人鏈式思維。它支持複雜的決策模擬，並在保持高精度輸出的同時，揭示可解釋的推理路徑。適用於策略分析、深度思考等場景。",
    "ja-JP": "taichu_o1は、マルチモーダルインタラクションと強化学習を通じて人間のような連鎖的思考を実現する次世代推論大規模モデルです。複雑な意思決定シミュレーションをサポートし、高精度な出力を維持しながら、解釈可能な推論経路を明らかにします。戦略分析、深い思考、類似のシナリオに適しています。",
    "ru-RU": "taichu_o1 — это модель больших рассуждений следующего поколения, которая достигает человеческого уровня цепочки размышлений через мультимодальное взаимодействие и обучение с подкреплением. Она поддерживает сложные симуляции принятия решений и, сохраняя высокую точность вывода, раскрывает интерпретируемые пути рассуждений. Она хорошо подходит для анализа стратегий, глубоких размышлений и подобных сценариев."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Taichu-O1"
    }
   ]
  },
  {
   "slug": "other/taichu4_vl_2b_nothinking",
   "model_name": "taichu4_vl_2b_nothinking",
   "display_name": "Taichu4.0-VL-2B-NoThinking",
   "vendor": "other",
   "pricing": [
    {
     "provider": "taichu",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Taichu4.0-VL 2B模型的无思维版本，具有较低的内存使用率、轻量化设计、快速响应速度和强大的多模态理解能力。",
    "zh-TW": "Taichu4.0-VL 2B 模型的無思考版本，具有較低的內存使用量、輕量化設計、快速響應速度和強大的多模態理解能力。",
    "ja-JP": "Taichu4.0-VL 2BモデルのNo-Thinkingバージョンは、メモリ使用量が少なく、軽量設計、高速応答速度、強力なマルチモーダル理解能力を特徴としています。",
    "ru-RU": "Версия Taichu4.0-VL 2B без мышления отличается меньшим использованием памяти, легким дизайном, высокой скоростью отклика и сильными мультимодальными возможностями понимания."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Taichu4.0-VL-2B-NoThinking"
    }
   ]
  },
  {
   "slug": "other/taichu4_vl_32b",
   "model_name": "taichu4_vl_32b",
   "display_name": "Taichu4.0-VL-32B-Thinking",
   "vendor": "other",
   "pricing": [
    {
     "provider": "taichu",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Taichu4.0-VL 32B模型的思维版本，适用于复杂的多模态理解和推理任务，在多模态数学推理、多模态代理能力以及一般图像和视觉理解方面表现卓越。",
    "zh-TW": "Taichu4.0-VL 32B 模型的思考版本，適用於複雜的多模態理解和推理任務，在多模態數學推理、多模態代理能力以及一般圖像和視覺理解方面表現出色。",
    "ja-JP": "Taichu4.0-VL 32BモデルのThinkingバージョンは、複雑なマルチモーダル理解と推論タスクに適しており、マルチモーダル数学的推論、マルチモーダルエージェント能力、一般的な画像および視覚理解において優れた性能を示します。",
    "ru-RU": "Версия Taichu4.0-VL 32B с мышлением подходит для сложных мультимодальных задач понимания и рассуждений, демонстрируя выдающиеся результаты в мультимодальных математических рассуждениях, возможностях мультимодальных агентов и общем понимании изображений и визуального контента."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Taichu4.0-VL-32B-Thinking"
    }
   ]
  },
  {
   "slug": "other/taichu4_vl_32b_nothinking",
   "model_name": "taichu4_vl_32b_nothinking",
   "display_name": "Taichu4.0-VL-32B-NoThinking",
   "vendor": "other",
   "pricing": [
    {
     "provider": "taichu",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Taichu4.0-VL 32B模型的无思维版本，专为复杂的图像与文本理解和视觉知识问答场景设计，擅长图像描述、视觉问答、视频理解和视觉定位任务。",
    "zh-TW": "Taichu4.0-VL 32B 模型的無思考版本，專為複雜的圖像與文本理解和視覺知識問答場景設計，擅長圖像描述、視覺問答、視頻理解和視覺定位任務。",
    "ja-JP": "Taichu4.0-VL 32BモデルのNo-Thinkingバージョンは、複雑な画像とテキストの理解および視覚知識QAシナリオ向けに設計されており、画像キャプション、視覚的質問応答、ビデオ理解、視覚的ローカリゼーションタスクに優れています。",
    "ru-RU": "Версия Taichu4.0-VL 32B без мышления предназначена для сложных сценариев понимания изображений и текста, а также визуальных вопросов и ответов, превосходя в описании изображений, визуальных вопросах и ответах, понимании видео и задачах визуальной локализации."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Taichu4.0-VL-32B-NoThinking"
    }
   ]
  },
  {
   "slug": "other/taichu4_vl_3b",
   "model_name": "taichu4_vl_3b",
   "display_name": "Taichu4.0-VL-3B-Thinking",
   "vendor": "other",
   "pricing": [
    {
     "provider": "taichu",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Taichu4.0-VL 3B模型的思维版本，能够高效执行多模态理解和推理任务，在视觉理解、视觉定位、OCR识别及相关能力方面全面升级。",
    "zh-TW": "Taichu4.0-VL 3B 模型的思考版本，能高效執行多模態理解和推理任務，在視覺理解、視覺定位、OCR 識別及相關能力方面進行了全面升級。",
    "ja-JP": "Taichu4.0-VL 3BモデルのThinkingバージョンは、マルチモーダル理解と推論タスクを効率的に実行し、視覚理解、視覚的ローカリゼーション、OCR認識、および関連能力において包括的なアップグレードを提供します。",
    "ru-RU": "Версия Taichu4.0-VL 3B с мышлением эффективно выполняет мультимодальные задачи понимания и рассуждений, с комплексными улучшениями в визуальном понимании, визуальной локализации, распознавании OCR и связанных возможностях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Taichu4.0-VL-3B-Thinking"
    }
   ]
  },
  {
   "slug": "other/tako",
   "model_name": "tako",
   "display_name": "Tako",
   "vendor": "other",
   "pricing": [],
   "intro": "Tool-capable chat model for instruction following and agentic application workflows",
   "released_at": "2024-08-15",
   "max_input_tokens": 2048,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "tako",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "trytako/tako"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Tako"
    }
   ]
  },
  {
   "slug": "other/tao-8k",
   "model_name": "tao-8k",
   "display_name": "tao-8k",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.068"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.068"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "tao-8k"
    }
   ]
  },
  {
   "slug": "other/tc-code-latest",
   "model_name": "tc-code-latest",
   "display_name": "Auto",
   "vendor": "other",
   "pricing": [
    {
     "provider": "tencent-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Automatic model router for matching prompts to suitable backends and budgets",
   "released_at": "2026-03-08",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "auto",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Auto"
    }
   ]
  },
  {
   "slug": "other/text-ada-001",
   "model_name": "text-ada-001",
   "display_name": "text-ada-001",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-ada-001"
    }
   ]
  },
  {
   "slug": "other/text-babbage-001",
   "model_name": "text-babbage-001",
   "display_name": "text-babbage-001",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-babbage-001"
    }
   ]
  },
  {
   "slug": "other/text-bison32k",
   "model_name": "text-bison32k",
   "display_name": "text-bison32k",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-bison32k"
    }
   ]
  },
  {
   "slug": "other/text-bison32k@002",
   "model_name": "text-bison32k@002",
   "display_name": "text-bison32k@002",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.25"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-bison32k@002"
    }
   ]
  },
  {
   "slug": "other/text-curie-001",
   "model_name": "text-curie-001",
   "display_name": "text-curie-001",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-curie-001"
    }
   ]
  },
  {
   "slug": "other/text-embedding",
   "model_name": "text-embedding",
   "display_name": "text-embedding",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-embedding"
    }
   ]
  },
  {
   "slug": "other/text-embedding-004",
   "model_name": "text-embedding-004",
   "display_name": "text-embedding-004",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0.025"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "region": "us-central1"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "released_at": "2024-05-14",
   "max_input_tokens": 2048,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-embedding-004"
    }
   ]
  },
  {
   "slug": "other/text-embedding-large-exp-03-07",
   "model_name": "text-embedding-large-exp-03-07",
   "display_name": "text-embedding-large-exp-03-07",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-embedding-large-exp-03-07"
    }
   ]
  },
  {
   "slug": "other/text-embedding-preview-0815",
   "model_name": "text-embedding-preview-0815",
   "display_name": "text-embedding-preview-0815",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-embedding-preview-0815"
    }
   ]
  },
  {
   "slug": "other/text-embedding-v1",
   "model_name": "text-embedding-v1",
   "display_name": "text-embedding-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-embedding-v1"
    }
   ]
  },
  {
   "slug": "other/text-embedding-v4",
   "model_name": "text-embedding-v4",
   "display_name": "text-embedding-v4",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_embedding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-embedding-v4"
    }
   ]
  },
  {
   "slug": "other/text-max",
   "model_name": "text-max",
   "display_name": "Text Max",
   "vendor": "other",
   "pricing": [],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2026-03-24",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Text Max"
    }
   ]
  },
  {
   "slug": "other/text-moderation-001",
   "model_name": "text-moderation-001",
   "display_name": "text-moderation-001",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "safety_detection",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-moderation-001"
    }
   ]
  },
  {
   "slug": "other/text-prime",
   "model_name": "text-prime",
   "display_name": "Text Prime",
   "vendor": "other",
   "pricing": [],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-02-26",
   "max_input_tokens": 128000,
   "max_output_tokens": 30000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Text Prime"
    }
   ]
  },
  {
   "slug": "other/text-search-ada-doc-001",
   "model_name": "text-search-ada-doc-001",
   "display_name": "text-search-ada-doc-001",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "20"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-search-ada-doc-001"
    }
   ]
  },
  {
   "slug": "other/text-standard",
   "model_name": "text-standard",
   "display_name": "Text Standard",
   "vendor": "other",
   "pricing": [],
   "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
   "released_at": "2026-02-26",
   "max_input_tokens": 128000,
   "max_output_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Text Standard"
    }
   ]
  },
  {
   "slug": "other/text-unicorn",
   "model_name": "text-unicorn",
   "display_name": "text-unicorn",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "28"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-unicorn"
    }
   ]
  },
  {
   "slug": "other/text-unicorn@001",
   "model_name": "text-unicorn@001",
   "display_name": "text-unicorn@001",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "28"
      }
     }
    }
   ],
   "max_output_tokens": 1024,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "text-unicorn@001"
    }
   ]
  },
  {
   "slug": "other/text2vec-base-chinese",
   "model_name": "text2vec-base-chinese",
   "display_name": "shibing624/text2vec-base-chinese",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "shibing624/text2vec-base-chinese"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.005"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.005"
      }
     },
     "provider_model_id": "deepinfra/shibing624/text2vec-base-chinese"
    }
   ],
   "max_input_tokens": 512,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "model_type": "text_embedding",
   "capabilities": {
    "prompt_caching": true
   },
   "max_output_tokens": 512,
   "released_at": "2025-10-01",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/shibing624/text2vec-base-chinese",
    "shibing624/text2vec-base-chinese"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "shibing624/text2vec-base-chinese"
    }
   ]
  },
  {
   "slug": "other/tng-r1t-chimera",
   "model_name": "tng-r1t-chimera",
   "display_name": "TNG: R1T Chimera",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.125"
      }
     },
     "provider_model_id": "tngtech/tng-r1t-chimera"
    }
   ],
   "released_at": "2025-11-26",
   "max_input_tokens": 163840,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "tngtech/tng-r1t-chimera"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TNG: R1T Chimera"
    }
   ]
  },
  {
   "slug": "other/TNG-R1T-Chimera-TEE",
   "model_name": "TNG-R1T-Chimera-TEE",
   "display_name": "TNG R1T Chimera TEE",
   "vendor": "other",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "tngtech/TNG-R1T-Chimera-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 163840,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "family": "tngtech",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "tngtech/TNG-R1T-Chimera-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TNG R1T Chimera TEE"
    }
   ]
  },
  {
   "slug": "other/TNG-R1T-Chimera-Turbo",
   "model_name": "TNG-R1T-Chimera-Turbo",
   "display_name": "TNG R1T Chimera Turbo",
   "vendor": "other",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "tngtech/TNG-R1T-Chimera-Turbo"
    }
   ],
   "released_at": "2026-01-27",
   "max_input_tokens": 163840,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "tngtech/TNG-R1T-Chimera-Turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TNG R1T Chimera Turbo"
    }
   ]
  },
  {
   "slug": "other/together-ai-21.1b-41b",
   "model_name": "together-ai-21.1b-41b",
   "display_name": "together-ai-21.1b-41b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "together-ai-21.1b-41b"
    }
   ]
  },
  {
   "slug": "other/together-ai-4.1b-8b",
   "model_name": "together-ai-4.1b-8b",
   "display_name": "together-ai-4.1b-8b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "together-ai-4.1b-8b"
    }
   ]
  },
  {
   "slug": "other/together-ai-41.1b-80b",
   "model_name": "together-ai-41.1b-80b",
   "display_name": "together-ai-41.1b-80b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "together-ai-41.1b-80b"
    }
   ]
  },
  {
   "slug": "other/together-ai-8.1b-21b",
   "model_name": "together-ai-8.1b-21b",
   "display_name": "together-ai-8.1b-21b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 1000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "together-ai-8.1b-21b"
    }
   ]
  },
  {
   "slug": "other/together-ai-81.1b-110b",
   "model_name": "together-ai-81.1b-110b",
   "display_name": "together-ai-81.1b-110b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    }
   ],
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "together-ai-81.1b-110b"
    }
   ]
  },
  {
   "slug": "other/together-ai-embedding-151m-to-350m",
   "model_name": "together-ai-embedding-151m-to-350m",
   "display_name": "together-ai-embedding-151m-to-350m",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.016"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "together-ai-embedding-151m-to-350m"
    }
   ]
  },
  {
   "slug": "other/together-ai-embedding-up-to-150m",
   "model_name": "together-ai-embedding-up-to-150m",
   "display_name": "together-ai-embedding-up-to-150m",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.008"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "model_type": "text_embedding",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "together-ai-embedding-up-to-150m"
    }
   ]
  },
  {
   "slug": "other/together-ai-up-to-4b",
   "model_name": "together-ai-up-to-4b",
   "display_name": "together-ai-up-to-4b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    }
   ],
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "together-ai-up-to-4b"
    }
   ]
  },
  {
   "slug": "other/topazlabs",
   "model_name": "topazlabs",
   "display_name": "TopazLabs",
   "vendor": "other",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-12-03",
   "max_input_tokens": 204,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "topazlabs",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "topazlabs-co/topazlabs"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TopazLabs"
    }
   ]
  },
  {
   "slug": "other/Toppy-M-7B",
   "model_name": "Toppy-M-7B",
   "display_name": "Toppy M 7B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "toppy-m-7b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "toppy-m-7b"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Undi95/Toppy-M-7B"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Undi95/Toppy-M-7B",
    "accounts/fireworks/models/toppy-m-7b",
    "toppy-m-7b",
    "undi95/toppy-m-7b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Toppy M 7B"
    }
   ]
  },
  {
   "slug": "other/trendyol-7b",
   "model_name": "trendyol-7b",
   "display_name": "Trendyol 7B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "llmtr",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "llmtr/trendyol-7b"
    }
   ],
   "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use",
   "released_at": "2026-06-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "llmtr/trendyol-7b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Trendyol 7B"
    }
   ]
  },
  {
   "slug": "other/tts",
   "model_name": "tts",
   "display_name": "tts",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "tts"
    }
   ]
  },
  {
   "slug": "other/tts-hd",
   "model_name": "tts-hd",
   "display_name": "tts-hd",
   "vendor": "other",
   "pricing": [
    {
     "provider": "azure",
     "official": false,
     "source": "portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "tts-hd"
    }
   ]
  },
  {
   "slug": "other/umans-coder",
   "model_name": "umans-coder",
   "display_name": "Umans Coder",
   "vendor": "other",
   "pricing": [
    {
     "provider": "umans-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      }
     }
    },
    {
     "provider": "umans-ai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
   "released_at": "2026-06-12",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "kimi-k2",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Umans Coder"
    }
   ]
  },
  {
   "slug": "other/umans-flash",
   "model_name": "umans-flash",
   "display_name": "Umans Flash",
   "vendor": "other",
   "pricing": [
    {
     "provider": "umans-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "umans-ai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
   "released_at": "2026-04-17",
   "max_input_tokens": 262144,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "qwen",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Umans Flash"
    }
   ]
  },
  {
   "slug": "other/unifuncs-u1",
   "model_name": "unifuncs-u1",
   "display_name": "u1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2025-08-21",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "u1"
    }
   ]
  },
  {
   "slug": "other/unifuncs-u1-pro",
   "model_name": "unifuncs-u1-pro",
   "display_name": "u1-pro",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    }
   ],
   "released_at": "2025-08-21",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "u1-pro"
    }
   ]
  },
  {
   "slug": "other/universal-summarizer",
   "model_name": "universal-summarizer",
   "display_name": "Universal Summarizer",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2023-05-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Universal Summarizer"
    }
   ]
  },
  {
   "slug": "other/unmoderated-gpt",
   "model_name": "unmoderated-gpt",
   "display_name": "unmoderated-gpt",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "safety_detection",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "unmoderated-gpt"
    },
    {
     "date": "2026-07-07",
     "kind": "delisted",
     "note": "unmoderated-gpt"
    },
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "unmoderated-gpt"
    }
   ]
  },
  {
   "slug": "other/unslopnemo-12b",
   "model_name": "unslopnemo-12b",
   "display_name": "TheDrummer: UnslopNemo 12B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "thedrummer/unslopnemo-12b"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "thedrummer/unslopnemo-12b"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2024-11-09",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2024-04",
   "model_type": "text_generation",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "thedrummer/unslopnemo-12b"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "TheDrummer: UnslopNemo 12B"
    }
   ]
  },
  {
   "slug": "other/UnslopNemo-12B-v4.1",
   "model_name": "UnslopNemo-12B-v4.1",
   "display_name": "UnslopNemo 12b v4",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.493"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.493"
      }
     },
     "provider_model_id": "TheDrummer/UnslopNemo-12B-v4.1"
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2024-01-01",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TheDrummer/UnslopNemo-12B-v4.1"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "UnslopNemo 12b v4"
    }
   ]
  },
  {
   "slug": "other/v0-1-5-lg",
   "model_name": "v0-1-5-lg",
   "display_name": "v0-1.5-lg",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "v0-1.5-lg"
    },
    {
     "provider": "v0",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     },
     "provider_model_id": "v0-1.5-lg"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-06-09",
   "max_input_tokens": 512000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "v0",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "v0-1.5-lg"
   ],
   "intro_i18n": {
    "zh-CN": "v0-1.5-lg 适用于高级思维或推理任务。",
    "zh-TW": "v0-1.5-lg 適用於進階思考或推理任務。",
    "ja-JP": "高度な思考や推論タスクに適したモデルです。",
    "ru-RU": "v0-1.5-lg подходит для задач, требующих продвинутого мышления и рассуждений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "v0-1.5-lg"
    }
   ]
  },
  {
   "slug": "other/v0-1-5-md",
   "model_name": "v0-1-5-md",
   "display_name": "v0-1.5-md",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "v0-1.5-md"
    },
    {
     "provider": "v0",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "v0-1.5-md"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "vercel/v0-1.5-md"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "vercel/v0-1.5-md"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-06-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "v0",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "v0-1.5-md",
    "vercel/v0-1.5-md"
   ],
   "intro_i18n": {
    "zh-CN": "v0-1.5-md 适用于日常任务和用户界面生成。",
    "zh-TW": "v0-1.5-md 適合日常任務與 UI 生成。",
    "ja-JP": "日常的なタスクやUI生成に適したモデルです。",
    "ru-RU": "v0-1.5-md подходит для повседневных задач и генерации пользовательских интерфейсов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "v0-1.5-md"
    }
   ]
  },
  {
   "slug": "other/v0-1-md",
   "model_name": "v0-1-md",
   "display_name": "v0-1.0-md",
   "vendor": "other",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2025-06-23",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "v0-1.0-md"
    }
   ]
  },
  {
   "slug": "other/v0-1.0-md",
   "model_name": "v0-1.0-md",
   "display_name": "v0-1.0-md",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "v0",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "vercel/v0-1.0-md"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "vercel/v0-1.0-md"
    }
   ],
   "intro": "Multimodal reasoning model for visual analysis, planning, and tool use",
   "released_at": "2025-05-22",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "v0",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vercel/v0-1.0-md"
   ],
   "intro_i18n": {
    "zh-CN": "v0-1.0-md 是通过 v0 API 提供的旧版模型。",
    "zh-TW": "v0-1.0-md 是透過 v0 API 提供的舊版模型。",
    "ja-JP": "v0 APIを通じて提供されるレガシーモデルです。",
    "ru-RU": "v0-1.0-md — устаревшая модель, доступная через API v0."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "v0-1.0-md"
    }
   ]
  },
  {
   "slug": "other/valkyrie-49b-v1",
   "model_name": "valkyrie-49b-v1",
   "display_name": "valkyrie-49b-v1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "valkyrie-49b-v1"
    }
   ]
  },
  {
   "slug": "other/vehicle-detector",
   "model_name": "vehicle-detector",
   "display_name": "vehicle-detector",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.001666666"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vehicle-detector"
    }
   ]
  },
  {
   "slug": "other/Veiled-Calla-12B",
   "model_name": "Veiled-Calla-12B",
   "display_name": "Veiled Calla 12B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "soob3123/Veiled-Calla-12B"
    }
   ],
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-04-13",
   "max_input_tokens": 32768,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "soob3123/Veiled-Calla-12B"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Veiled Calla 12B"
    }
   ]
  },
  {
   "slug": "other/venice-uncensored",
   "model_name": "venice-uncensored",
   "display_name": "Venice Uncensored",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    },
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-02-24",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "knowledge_cutoff": "2023-10",
   "family": "venice",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Venice Uncensored"
    }
   ]
  },
  {
   "slug": "other/venice-uncensored-1-2",
   "model_name": "venice-uncensored-1-2",
   "display_name": "Venice Uncensored 1.2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2026-04-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "venice",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Venice Uncensored 1.2"
    }
   ]
  },
  {
   "slug": "other/venice-uncensored-role-play",
   "model_name": "venice-uncensored-role-play",
   "display_name": "Venice Role Play Uncensored",
   "vendor": "other",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2026-02-20",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "venice",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Venice Role Play Uncensored"
    }
   ]
  },
  {
   "slug": "other/venice-uncensored:web",
   "model_name": "venice-uncensored:web",
   "display_name": "Venice Uncensored Web",
   "vendor": "other",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-05-01",
   "max_input_tokens": 80000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Venice Uncensored Web"
    }
   ]
  },
  {
   "slug": "other/veo-2.0-generate-exp",
   "model_name": "veo-2.0-generate-exp",
   "display_name": "veo-2.0-generate-exp",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-2.0-generate-exp"
    }
   ]
  },
  {
   "slug": "other/veo-2.0-generate-preview",
   "model_name": "veo-2.0-generate-preview",
   "display_name": "veo-2.0-generate-preview",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-2.0-generate-preview"
    }
   ]
  },
  {
   "slug": "other/veo-3.0-fast-generate-preview",
   "model_name": "veo-3.0-fast-generate-preview",
   "display_name": "veo-3.0-fast-generate-preview",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.0-fast-generate-preview"
    }
   ]
  },
  {
   "slug": "other/veo-3.0-generate-preview",
   "model_name": "veo-3.0-generate-preview",
   "display_name": "veo-3.0-generate-preview",
   "vendor": "other",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "portkey",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "veo-3.0-generate-preview"
    }
   ]
  },
  {
   "slug": "other/vicuna-13b-v1.5",
   "model_name": "vicuna-13b-v1.5",
   "display_name": "vicuna-13b-v1.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "lmsys/vicuna-13b-v1.5"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "lmsys/vicuna-13b-v1.5"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vicuna-13b-v1.5"
    }
   ]
  },
  {
   "slug": "other/vicuna-7b-v1.5",
   "model_name": "vicuna-7b-v1.5",
   "display_name": "vicuna-7b-v1.5",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "lmsys/vicuna-7b-v1.5"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "lmsys/vicuna-7b-v1.5"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vicuna-7b-v1.5"
    }
   ]
  },
  {
   "slug": "other/VirtueGuard-Text-Lite",
   "model_name": "VirtueGuard-Text-Lite",
   "display_name": "VirtueGuard-Text-Lite",
   "vendor": "other",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "Virtue-AI/VirtueGuard-Text-Lite"
    }
   ],
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "safety_detection",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Virtue-AI/VirtueGuard-Text-Lite"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "VirtueGuard-Text-Lite"
    }
   ]
  },
  {
   "slug": "other/virtuoso-medium-v2",
   "model_name": "virtuoso-medium-v2",
   "display_name": "virtuoso-medium-v2",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "virtuoso-medium-v2"
    }
   ]
  },
  {
   "slug": "other/voiceover-multilingual",
   "model_name": "voiceover-multilingual",
   "display_name": "voiceover-multilingual",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "voiceover-multilingual"
    }
   ]
  },
  {
   "slug": "other/voiceover-v3",
   "model_name": "voiceover-v3",
   "display_name": "voiceover-v3",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "75"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "voiceover-v3"
    }
   ]
  },
  {
   "slug": "other/wan2-2-t2v-a14b",
   "model_name": "wan2-2-t2v-a14b",
   "display_name": "Wan2.2-T2V-A14B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.036"
      }
     },
     "provider_model_id": "Wan-AI/Wan2.2-T2V-A14B"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.294118"
      }
     },
     "provider_model_id": "Wan-AI/Wan2.2-T2V-A14B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.66"
      }
     },
     "provider_model_id": "Wan-AI/Wan2.2-T2V-A14B"
    }
   ],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-07-28",
   "max_input_tokens": 100,
   "max_output_tokens": 1,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "open_weights": true
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Wan-AI/Wan2.2-T2V-A14B"
   ],
   "intro_i18n": {
    "zh-CN": "Wan2.2-T2V-A14B是阿里巴巴发布的首个采用专家混合（MoE）架构的开源视频生成模型。该模型专为文本转视频（T2V）生成任务设计，能够生成分辨率为480P或720P、时长达5秒的视频。通过引入MoE架构，模型在保持推理成本几乎不变的情况下显著提升了整体容量。它包括一个高噪声专家，负责生成早期阶段的全局结构，以及一个低噪声专家，优化视频后期阶段的细节。此外，Wan2.2引入了精心策划的美学数据，涵盖光线、构图和色彩等维度的详细注释，从而实现更精确、可控的电影级视觉生成。与之前版本相比，该模型在更大规模数据集上训练，显著提升了在动作、语义和美学方面的泛化能力，并更好地处理复杂的动态效果。",
    "zh-TW": "Wan2.2-T2V-A14B是阿里巴巴首個採用專家混合架構（MoE）的開源影像生成模型，專為文字生成影像（T2V）任務設計，能生成長達5秒的影像，解析度為480P或720P。通過引入MoE架構，模型顯著提升了整體容量，同時推理成本幾乎保持不變。模型包括高噪音專家負責生成早期階段的全局結構，低噪音專家精細化影像後期細節。此外，Wan2.2整合了精心策劃的美學數據，涵蓋光線、構圖及色彩等維度的詳細標註，實現更精確可控的電影級視覺生成。與之前版本相比，該模型在更大數據集上進行訓練，顯著提升了動作、語義及美學的泛化能力，並更好地處理複雜動態效果。",
    "ja-JP": "Wan2.2-T2V-A14Bは、Alibabaによってリリースされた最初のオープンソースビデオ生成モデルで、エキスパートの混合(MoE)アーキテクチャを採用しています。このモデルはテキストからビデオへの(T2V)生成タスク用に設計されており、480Pまたは720Pの解像度で最大5秒間のビデオを生成することができます。MoEアーキテクチャを導入することで、推論コストをほぼ変えずにモデルの全体的な容量を大幅に増加させています。高ノイズエキスパートが生成の初期段階でグローバル構造を処理し、低ノイズエキスパートが後期段階で細かいディテールを洗練します。さらに、Wan2.2は照明、構図、色彩などの次元にわたる詳細な注釈付きの美的データを慎重に取り入れており、映画品質のビジュアルをより正確かつ制御可能に生成することができます。以前のバージョンと比較して、モデルはより大きなデータセットでトレーニングされており、動き、意味、美学の一般化が大幅に向上し、複雑な動的効果の処理が改善されています。",
    "ru-RU": "Wan2.2-T2V-A14B — первая модель генерации видео из текста с открытым исходным кодом, выпущенная Alibaba, использующая архитектуру Mixture of Experts (MoE). Модель предназначена для задач генерации видео из текста (T2V) и способна создавать видео длиной до 5 секунд с разрешением 480P или 720P. Внедрение архитектуры MoE значительно увеличивает общую емкость модели, сохраняя при этом почти неизменные затраты на интерпретацию. Она включает эксперта с высоким уровнем шума, который обрабатывает глобальную структуру на ранних этапах генерации, и эксперта с низким уровнем шума, который уточняет мелкие детали на поздних этапах видео. Кроме того, Wan2.2 включает тщательно подобранные эстетические данные с детализированными аннотациями по таким аспектам, как освещение, композиция и цвет. Это позволяет более точно и контролируемо создавать визуальные эффекты кинематографического качества. По сравнению с предыдущими версиями, модель обучена на большем наборе данных, что приводит к значительному улучшению обобщения в движении, семантике и эстетике, а также лучшей обработке сложных динамических эффектов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.2-T2V-A14B"
    }
   ]
  },
  {
   "slug": "other/wan2.2-i2v",
   "model_name": "wan2.2-i2v",
   "display_name": "wan2.2-i2v",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8.7"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "wan2.2-i2v"
    }
   ]
  },
  {
   "slug": "other/Wan2.2-I2V-A14B",
   "model_name": "Wan2.2-I2V-A14B",
   "display_name": "Wan-AI/Wan2.2-I2V-A14B",
   "vendor": "other",
   "pricing": [
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.294118"
      }
     },
     "provider_model_id": "Wan-AI/Wan2.2-I2V-A14B"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.31"
      }
     },
     "provider_model_id": "Wan-AI/Wan2.2-I2V-A14B"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "released_at": "2026-01-28",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Wan-AI/Wan2.2-I2V-A14B"
   ],
   "intro_i18n": {
    "zh-CN": "Wan2.2-I2V-A14B是阿里巴巴旗下AI项目Wan-AI发布的首批开源图像转视频（I2V）生成模型之一，采用专家混合（MoE）架构。该模型通过结合静态图像和文本提示生成平滑自然的动态视频序列。其核心创新在于MoE架构：高噪声专家负责视频生成早期阶段的粗略结构处理，而低噪声专家在后期阶段优化细节。这种设计在不增加推理成本的情况下提升了整体模型性能。与之前版本相比，Wan2.2在更大规模数据集上训练，显著提升了对复杂动作、美学风格和语义内容的理解能力，生成更稳定的视频并减少不真实的摄像机运动。",
    "zh-TW": "Wan2.2-I2V-A14B是阿里巴巴旗下AI計劃Wan-AI首批開源影像生成模型之一，採用專家混合架構（MoE）。該模型通過結合靜態影像與文字提示生成流暢自然的動態影像序列，其核心創新在於MoE架構：高噪音專家負責影像生成早期階段的粗略結構，而低噪音專家在後期階段精細化細節。此設計在不增加推理成本的情況下提升了整體模型性能。與之前版本相比，Wan2.2在更大數據集上進行訓練，顯著提升了對複雜動作、美學風格及語義內容的理解能力，生成更穩定的影像並減少不自然的相機運動。",
    "ja-JP": "Wan2.2-I2V-A14Bは、AlibabaのAIイニシアチブであるWan-AIによってリリースされた最初のオープンソース画像からビデオへの(I2V)生成モデルの1つで、エキスパートの混合(MoE)アーキテクチャを採用しています。このモデルは、静止画像とテキストプロンプトを組み合わせることで、滑らかで自然な動的ビデオシーケンスを生成することに焦点を当てています。コアとなる革新はMoEアーキテクチャにあり、高ノイズエキスパートがビデオ生成の初期段階で粗い構造を処理し、低ノイズエキスパートが後期段階で細かいディテールを洗練します。この設計により、推論コストを増加させることなく、モデル全体のパフォーマンスが向上します。以前のバージョンと比較して、Wan2.2は大幅に大きなデータセットでトレーニングされており、複雑な動き、美的スタイル、意味的内容の理解が著しく向上しています。より安定したビデオを生成し、非現実的なカメラ動作を減少させます。",
    "ru-RU": "Wan2.2-I2V-A14B — одна из первых моделей генерации видео из изображений с открытым исходным кодом, выпущенных Wan-AI, инициативой Alibaba в области ИИ, использующая архитектуру Mixture of Experts (MoE). Модель фокусируется на создании плавных и естественных динамических видеопоследовательностей, комбинируя статические изображения с текстовыми подсказками. Основное новшество заключается в архитектуре MoE: эксперт с высоким уровнем шума отвечает за обработку грубой структуры на ранних этапах генерации видео, а эксперт с низким уровнем шума уточняет мелкие детали на поздних этапах. Этот дизайн улучшает общую производительность модели без увеличения затрат на интерпретацию. По сравнению с предыдущими версиями, Wan2.2 обучена на значительно большем наборе данных, что приводит к заметным улучшениям в понимании сложных движений, эстетических стилей и семантического содержания. Она создает более стабильные видео и уменьшает нереалистичные движения камеры."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan-AI/Wan2.2-I2V-A14B"
    }
   ]
  },
  {
   "slug": "other/wan2.2-t2v",
   "model_name": "wan2.2-t2v",
   "display_name": "wan2.2-t2v",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8.7"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "wan2.2-t2v"
    }
   ]
  },
  {
   "slug": "other/wan2.5-i2v",
   "model_name": "wan2.5-i2v",
   "display_name": "wan2.5-i2v",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "18.66"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "wan2.5-i2v"
    }
   ]
  },
  {
   "slug": "other/wan2.5-t2v",
   "model_name": "wan2.5-t2v",
   "display_name": "wan2.5-t2v",
   "vendor": "other",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "18.66"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "wan2.5-t2v"
    }
   ]
  },
  {
   "slug": "other/Wan2.6-Image-Edit",
   "model_name": "Wan2.6-Image-Edit",
   "display_name": "Wan2.6-Image-Edit",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "Wan-AI/Wan2.6-Image-Edit"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Wan-AI/Wan2.6-Image-Edit"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.6-Image-Edit"
    }
   ]
  },
  {
   "slug": "other/Wan2.7-Image-Edit",
   "model_name": "Wan2.7-Image-Edit",
   "display_name": "Wan2.7-Image-Edit",
   "vendor": "other",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.03"
      }
     },
     "provider_model_id": "Wan-AI/Wan2.7-Image-Edit"
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Wan-AI/Wan2.7-Image-Edit"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Wan2.7-Image-Edit"
    }
   ]
  },
  {
   "slug": "other/weaver",
   "model_name": "weaver",
   "display_name": "Mancer: Weaver (alpha)",
   "vendor": "other",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "mancer/weaver"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "mancer/weaver"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2023-08-02",
   "max_input_tokens": 8000,
   "max_output_tokens": 2000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "structured_output": true
   },
   "knowledge_cutoff": "2023-06",
   "family": "alpha",
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_a",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mancer/weaver"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Mancer: Weaver (alpha)"
    }
   ]
  },
  {
   "slug": "other/xpersona-a-better-you",
   "model_name": "xpersona-a-better-you",
   "display_name": "xpersona-a-better-you",
   "vendor": "other",
   "pricing": [
    {
     "provider": "xpersona",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "18"
      }
     }
    }
   ],
   "released_at": "2026-05-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "xpersona-a-better-you"
    }
   ]
  },
  {
   "slug": "other/xpersona-frieren-coder",
   "model_name": "xpersona-frieren-coder",
   "display_name": "Xpersona Frieren 1",
   "vendor": "other",
   "pricing": [
    {
     "provider": "xpersona",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2026-05-01",
   "knowledge_cutoff": "2025-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 384000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Xpersona Frieren 1"
    }
   ]
  },
  {
   "slug": "other/xwin-lm-70b",
   "model_name": "xwin-lm-70b",
   "display_name": "xwin-lm-70b",
   "vendor": "other",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.75"
      }
     },
     "provider_model_id": "xwin-lm/xwin-lm-70b"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xwin-lm/xwin-lm-70b"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "xwin-lm-70b"
    }
   ]
  },
  {
   "slug": "other/yi-vl-plus",
   "model_name": "yi-vl-plus",
   "display_name": "yi-vl-plus",
   "vendor": "other",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.000852"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.000852"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "yi-vl-plus"
    }
   ]
  },
  {
   "slug": "other/youtu-vita",
   "model_name": "youtu-vita",
   "display_name": "YT-VITA",
   "vendor": "other",
   "pricing": [
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.514706"
      }
     }
    }
   ],
   "released_at": "2026-01-10",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "VITA 是一款多模态理解模型，支持视频与图像内容分析，可用于视频结构解析、图像目标检测等任务。",
    "zh-TW": "VITA 是一款多模態理解模型，支援影片與圖片內容分析，可用於影片結構解析、影像物件偵測等任務。",
    "ja-JP": "VITAは、動画および画像コンテンツの分析をサポートするマルチモーダル理解モデルです。動画構造解析や画像オブジェクト検出などのタスクに使用できます。",
    "ru-RU": "VITA — мультимодальная модель понимания, поддерживающая анализ видео и изображений. Может использоваться для структурного анализа видео и обнаружения объектов на изображениях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "YT-VITA"
    }
   ]
  },
  {
   "slug": "other/yt-video-2.0",
   "model_name": "yt-video-2.0",
   "display_name": "YT-Video-2.0",
   "vendor": "other",
   "pricing": [
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.735294"
      }
     }
    }
   ],
   "released_at": "2025-11-27",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "能够从图像生成时间一致性极高的视频，适用于广告、影视片段、产品展示等高要求场景。",
    "zh-TW": "可從圖像生成高度時間一致性的影片，適用於廣告、電影段落、產品展示等高要求場景。",
    "ja-JP": "画像から動画を生成し、広告、映画クリップ、製品紹介動画などの要求の厳しいアプリケーションに適した高い時間的一貫性を備えています。",
    "ru-RU": "Создаёт высококачественные и устойчивые по времени видеоролики на основе изображений. Подходит для рекламы, кино, демонстрации продуктов и других задач, требующих высокого качества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "YT-Video-2.0"
    }
   ]
  },
  {
   "slug": "other/z-code",
   "model_name": "z-code",
   "display_name": "Z-Code",
   "vendor": "other",
   "pricing": [
    {
     "provider": "zeldoc",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2026-04-15",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Z-Code"
    }
   ]
  },
  {
   "slug": "other/zdr",
   "model_name": "zdr",
   "display_name": "Zero Data Retention",
   "vendor": "other",
   "pricing": [],
   "intro": "TrustedRouter privacy routing alias that prefers zero data retention model endpoints.",
   "released_at": "2026-06-01",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Zero Data Retention"
    }
   ]
  },
  {
   "slug": "other/zephyr-7b-beta",
   "model_name": "zephyr-7b-beta",
   "display_name": "Zephyr 7B Beta",
   "vendor": "other",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "accounts/fireworks/models/zephyr-7b-beta"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/zephyr-7b-beta"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Zephyr 7B Beta"
    }
   ]
  },
  {
   "slug": "perplexity/codellama-34b-instruct",
   "model_name": "codellama-34b-instruct",
   "display_name": "codellama-34b-instruct",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "meta-llama/codellama-34b-instruct"
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/codellama-34b-instruct"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/codellama-70b-instruct",
   "model_name": "codellama-70b-instruct",
   "display_name": "codellama-70b-instruct",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "perplexity/llama-2-70b-chat",
   "model_name": "llama-2-70b-chat",
   "display_name": "llama-2-70b-chat",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "meta-llama/llama-2-70b-chat"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "meta-llama/llama-2-70b-chat"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/llama-3.1-70b-instruct",
   "model_name": "llama-3.1-70b-instruct",
   "display_name": "llama-3.1-70b-instruct",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-70b-instruct"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     }
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.1-70b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-70b-instruct"
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.360294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.414706"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-70b-instruct"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "hf:meta-llama/Llama-3.1-70B-Instruct"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.1-70B-Instruct"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2024-07-23",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "status": "beta",
   "knowledge_cutoff": "2023-12",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hf:meta-llama/Llama-3.1-70B-Instruct",
    "meta-llama/Llama-3.1-70B-Instruct",
    "meta-llama/llama-3.1-70b-instruct",
    "meta/llama-3.1-70b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Meta 最新的 Llama 3.1 系列，70B 指令微调版本，专为高质量对话优化。在行业评估中表现优异，超越领先闭源模型。（仅对企业认证用户开放）",
    "zh-TW": "Meta 最新的 Llama 3.1 系列，70B 指令微調版本，針對高品質對話進行優化。在業界評估中，表現優於多數封閉模型。（僅限企業驗證用戶使用）",
    "ja-JP": "Metaの最新Llama 3.1シリーズの70B命令調整バージョンで、高品質な対話に最適化されています。業界評価において、主要なクローズドモデルに対して優れた性能を示しています。（企業認証済みの組織のみ利用可能）",
    "ru-RU": "Последняя серия Meta Llama 3.1, вариант с 70 миллиардами параметров, обученный на инструкциях и оптимизированный для высококачественных диалогов. В отраслевых оценках показывает отличные результаты по сравнению с ведущими закрытыми моделями. (Доступна только для проверенных корпоративных клиентов.)"
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/llama-3.1-8b-instruct",
   "model_name": "llama-3.1-8b-instruct",
   "display_name": "llama-3.1-8b-instruct",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8299999999999998"
      }
     },
     "provider_model_id": "workers-ai/@cf/meta/llama-3.1-8b-instruct"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8299999999999998"
      }
     },
     "provider_model_id": "@cf/meta/llama-3.1-8b-instruct"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "friendli",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.1-8B-Instruct"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.049999999999999996"
      }
     }
    },
    {
     "provider": "inference",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "meta/llama-3.1-8b-instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0544"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0544"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "meta/llama-3.1-8b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "ovhcloud",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     }
    },
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      }
     },
     "provider_model_id": "meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "regolo-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "novita/meta-llama/llama-3.1-8b-instruct"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "hf:meta-llama/Llama-3.1-8B-Instruct"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "meta-llama/Llama-3.1-8B-Instruct"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding",
   "released_at": "2025-04-07",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "llama",
   "knowledge_cutoff": "2024-07",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/meta/llama-3.1-8b-instruct",
    "hf:meta-llama/Llama-3.1-8B-Instruct",
    "meta-llama/Llama-3.1-8B-Instruct",
    "meta-llama/llama-3.1-8b-instruct",
    "meta/llama-3.1-8b-instruct",
    "novita/meta-llama/llama-3.1-8b-instruct",
    "workers-ai/@cf/meta/llama-3.1-8b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Meta 最新的 Llama 3.1 系列，8B 指令微调版本，速度快、效率高。在行业评估中表现优异，超越众多领先闭源模型。（仅对企业认证用户开放）",
    "zh-TW": "Meta 最新的 Llama 3.1 系列，8B 指令微調版本，速度快且效率高。在業界評估中表現優異，超越多數封閉模型。（僅限企業驗證用戶使用）",
    "ja-JP": "Metaの最新Llama 3.1シリーズの8B命令調整バージョンで、特に高速かつ効率的です。業界評価において、多くの主要なクローズドモデルを上回る性能を発揮します。（企業認証済みの組織のみ利用可能）",
    "ru-RU": "Последняя серия Meta Llama 3.1, вариант с 8 миллиардами параметров, обученный на инструкциях, особенно быстр и эффективен. В отраслевых оценках демонстрирует отличные результаты, превосходя многие ведущие закрытые модели. (Доступна только для проверенных корпоративных клиентов.)"
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/llama-3.1-sonar-huge-128k-online",
   "model_name": "llama-3.1-sonar-huge-128k-online",
   "display_name": "llama-3.1-sonar-huge-128k-online",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.6"
      }
     }
    }
   ],
   "max_output_tokens": 127072,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.1-sonar-huge-128k-online"
    }
   ]
  },
  {
   "slug": "perplexity/llama-3.1-sonar-large-128k-chat",
   "model_name": "llama-3.1-sonar-large-128k-chat",
   "display_name": "llama-3.1-sonar-large-128k-chat",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.1-sonar-large-128k-chat"
    }
   ]
  },
  {
   "slug": "perplexity/llama-3.1-sonar-large-128k-online",
   "model_name": "llama-3.1-sonar-large-128k-online",
   "display_name": "llama-3.1-sonar-large-128k-online",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "perplexity/llama-3.1-sonar-large-128k-online"
    }
   ],
   "intro": "Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance.",
   "capabilities": {},
   "max_output_tokens": 127072,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/llama-3.1-sonar-large-128k-online"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.1-sonar-large-128k-online"
    }
   ]
  },
  {
   "slug": "perplexity/llama-3.1-sonar-small-128k-chat",
   "model_name": "llama-3.1-sonar-small-128k-chat",
   "display_name": "llama-3.1-sonar-small-128k-chat",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.1-sonar-small-128k-chat"
    }
   ]
  },
  {
   "slug": "perplexity/llama-3.1-sonar-small-128k-online",
   "model_name": "llama-3.1-sonar-small-128k-online",
   "display_name": "llama-3.1-sonar-small-128k-online",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "perplexity/llama-3.1-sonar-small-128k-online"
    }
   ],
   "intro": "Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance.",
   "capabilities": {},
   "max_output_tokens": 127072,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/llama-3.1-sonar-small-128k-online"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "llama-3.1-sonar-small-128k-online"
    }
   ]
  },
  {
   "slug": "perplexity/mistral-7b-instruct",
   "model_name": "mistral-7b-instruct",
   "display_name": "mistral-7b-instruct",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "mistral.mistral-7b-instruct-v0:2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.375",
        "completion": "0.384615"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.3125",
        "completion": "1.346154"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.375",
        "completion": "0.384615"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "mistral.mistral-7b-instruct-v0:2",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "mistral.mistral-7b-instruct-v0:2",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "mistral.mistral-7b-instruct-v0:2",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.16"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "mistral.mistral-7b-instruct-v0:2",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "mistral.mistral-7b-instruct-v0:2",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "mistral.mistral-7b-instruct-v0:2",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.34"
      }
     },
     "provider_model_id": "mistral.mistral-7b-instruct-v0:2",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistral.mistral-7b-instruct-v0:2",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistral.mistral-7b-instruct-v0:2",
     "region": "us-west-2"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "mistralai/mistral-7b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "mistralai/mistral-7b-instruct"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "stream": true,
    "open_weights": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-04-01",
   "family": "mistral",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mistral-7b-instruct:free",
    "mistral.mistral-7b-instruct-v0:2",
    "mistralai/mistral-7b-instruct",
    "mistralai/mistral-7b-instruct:free"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "open_weights: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/mixtral-8x7b-instruct",
   "model_name": "mixtral-8x7b-instruct",
   "display_name": "mixtral-8x7b-instruct",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "litellm+pydantic-prices+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.91"
      }
     },
     "provider_model_id": "mistral.mixtral-8x7b-instruct-v0:1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.381356",
        "completion": "0.384615"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.334746",
        "completion": "1.346154"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.381356",
        "completion": "0.384615"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.84"
      }
     },
     "provider_model_id": "mistral.mixtral-8x7b-instruct-v0:1",
     "region": "ap-south-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.91"
      }
     },
     "provider_model_id": "mistral.mixtral-8x7b-instruct-v0:1",
     "region": "ap-southeast-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.52"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.81"
      }
     },
     "provider_model_id": "mistral.mixtral-8x7b-instruct-v0:1",
     "region": "ca-central-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.49"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.76"
      }
     },
     "provider_model_id": "mistral.mixtral-8x7b-instruct-v0:1",
     "region": "eu-west-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.91"
      }
     },
     "provider_model_id": "mistral.mixtral-8x7b-instruct-v0:1",
     "region": "eu-west-2",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.59"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.91"
      }
     },
     "provider_model_id": "mistral.mixtral-8x7b-instruct-v0:1",
     "region": "eu-west-3",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry+portkey",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.76"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.18"
      }
     },
     "provider_model_id": "mistral.mixtral-8x7b-instruct-v0:1",
     "region": "sa-east-1",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "priority",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.75",
        "completion": "1.75"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^priority$"
        }
       ]
      },
      {
       "label": "flex",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "body_matches",
         "field": "service_tier",
         "pattern": "^flex$"
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "mistral.mixtral-8x7b-instruct-v0:1",
     "region": "us-east-1"
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "mistral.mixtral-8x7b-instruct-v0:1",
     "region": "us-west-2"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mixtral-8x7b-instruct"
    },
    {
     "provider": "fireworksai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "accounts/fireworks/models/mixtral-8x7b-instruct"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mistralai/mixtral-8x7b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "mistralai/mixtral-8x7b-instruct"
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
   "released_at": "2023-12-10",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "deprecated": true,
   "family": "mixtral",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/mixtral-8x7b-instruct",
    "mistral.mixtral-8x7b-instruct-v0:1",
    "mistralai/mixtral-8x7b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "Mixtral MoE 8x7B Instruct 是 Mixtral MoE 8x7B 的指令微调版本，启用了聊天补全 API。",
    "zh-TW": "Mixtral MoE 8x7B Instruct 是 Mixtral MoE 8x7B 的指令微調版本，已啟用聊天補全 API。",
    "ja-JP": "Mixtral MoE 8x7B Instructは、Mixtral MoE 8x7Bの命令調整済みバージョンで、チャット補完APIが有効化されています。",
    "ru-RU": "Mixtral MoE 8x7B Instruct — это дообученная на инструкциях версия модели Mixtral MoE 8x7B с включенной поддержкой API завершения чата."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/perplexity-sonar",
   "model_name": "perplexity-sonar",
   "display_name": "sonar",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    }
   ],
   "released_at": "2025-01-22",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sonar"
    }
   ]
  },
  {
   "slug": "perplexity/perplexity-sonar-deep-research",
   "model_name": "perplexity-sonar-deep-research",
   "display_name": "sonar-deep-research",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    }
   ],
   "released_at": "2025-01-22",
   "max_input_tokens": 127000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sonar-deep-research"
    }
   ]
  },
  {
   "slug": "perplexity/perplexity-sonar-pro",
   "model_name": "perplexity-sonar-pro",
   "display_name": "sonar-pro",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2025-01-22",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sonar-pro"
    }
   ]
  },
  {
   "slug": "perplexity/perplexity-sonar-reasoning",
   "model_name": "perplexity-sonar-reasoning",
   "display_name": "sonar-reasoning",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    }
   ],
   "released_at": "2025-01-22",
   "max_input_tokens": 127000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sonar-reasoning"
    }
   ]
  },
  {
   "slug": "perplexity/perplexity-sonar-reasoning-pro",
   "model_name": "perplexity-sonar-reasoning-pro",
   "display_name": "sonar-reasoning-pro",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    }
   ],
   "released_at": "2025-01-22",
   "max_input_tokens": 127000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sonar-reasoning-pro"
    }
   ]
  },
  {
   "slug": "perplexity/pplx-70b-chat",
   "model_name": "pplx-70b-chat",
   "display_name": "pplx-70b-chat",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "perplexity/pplx-70b-online",
   "model_name": "pplx-70b-online",
   "display_name": "pplx-70b-online",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.8"
      },
      "request": {
       "unit": "per_request",
       "price": "0.005"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "perplexity/pplx-7b-chat",
   "model_name": "pplx-7b-chat",
   "display_name": "pplx-7b-chat",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "perplexity/pplx-7b-online",
   "model_name": "pplx-7b-online",
   "display_name": "pplx-7b-online",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "request": {
       "unit": "per_request",
       "price": "0.005"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "perplexity/pplx-embed-v1-0.6b",
   "model_name": "pplx-embed-v1-0.6b",
   "display_name": "pplx-embed-v1-0.6b",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.004"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.004"
      }
     },
     "provider_model_id": "perplexity/pplx-embed-v1-0.6b"
    }
   ],
   "docs_url": "https://docs.perplexity.ai/docs/embeddings/quickstart",
   "max_input_tokens": 32768,
   "model_type": "text_embedding",
   "capabilities": {
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/pplx-embed-v1-0.6b"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "perplexity/pplx-embed-v1-4b",
   "model_name": "pplx-embed-v1-4b",
   "display_name": "pplx-embed-v1-4b",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "perplexity/pplx-embed-v1-4b"
    }
   ],
   "docs_url": "https://docs.perplexity.ai/docs/embeddings/quickstart",
   "max_input_tokens": 32768,
   "model_type": "text_embedding",
   "capabilities": {
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "embedding"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/pplx-embed-v1-4b"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "perplexity/r1-1776",
   "model_name": "r1-1776",
   "display_name": "R1 1776",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "pydantic-prices+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "perplexity/r1-1776"
    }
   ],
   "intro": "R1 1776 is a version of DeepSeek-R1 that has been post-trained to remove censorship constraints related to topics restricted by the Chinese government. The model retains its original reasoning capabilities while providing direct responses to a wider range of queries. R1 1776 is an offline chat model that does not use the perplexity search subsystem.",
   "capabilities": {
    "reasoning": true,
    "vision": true
   },
   "released_at": "2025-02-18",
   "max_input_tokens": 127072,
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/r1-1776"
   ],
   "intro_i18n": {
    "zh-CN": "R1-1776 是 DeepSeek R1 的后训练版本，旨在提供无审查、无偏见的真实信息。",
    "zh-TW": "R1-1776 是 DeepSeek R1 的後訓練版本，旨在提供未經審查、無偏見的事實資訊。",
    "ja-JP": "R1-1776は、DeepSeek R1のポストトレーニングバリアントで、検閲のない偏りのない事実情報を提供するよう設計されています。",
    "ru-RU": "R1-1776 — дообученный вариант DeepSeek R1, предназначенный для предоставления нецензурированной, объективной и достоверной информации."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "R1 1776"
    }
   ]
  },
  {
   "slug": "perplexity/sonar",
   "model_name": "sonar",
   "display_name": "Sonar",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "8"
      },
      "request": {
       "unit": "per_k_calls",
       "price": "12"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0625"
      }
     },
     "provider_model_id": "perplexity/sonar"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "perplexity/sonar"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "perplexity/sonar"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "perplexity/sonar"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.003"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "perplexity/sonar"
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0625"
      }
     },
     "provider_model_id": "perplexity/sonar"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "perplexity/sonar"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "perplexity/sonar"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "perplexity/sonar"
    }
   ],
   "intro": "Fast web-grounded Sonar for current answers, citations, and lightweight retrieval",
   "released_at": "2024-01-01",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "sonar",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "text_generation",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "response_format",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/sonar"
   ],
   "intro_i18n": {
    "zh-CN": "Perplexity 的轻量级产品，具备搜索支撑，速度更快、成本更低于 Sonar Pro。",
    "zh-TW": "Perplexity 的輕量產品，具備搜尋依據，速度更快、成本更低於 Sonar Pro。",
    "ja-JP": "Perplexityの軽量製品で、検索に基づいた応答を提供し、Sonar Proよりも高速かつ低コストです。",
    "ru-RU": "Легковесный продукт с привязкой к поиску, быстрее и дешевле, чем Sonar Pro."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/sonar-deep-research",
   "model_name": "sonar-deep-research",
   "display_name": "Perplexity Sonar Deep Research",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "perplexity/sonar-deep-research"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "perplexity/sonar-deep-research"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "perplexity/sonar-deep-research"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.6"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "perplexity/sonar-deep-research"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "internal_reasoning": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     }
    }
   ],
   "intro": "Sonar search model for current answers, retrieval, and citation-backed chat",
   "released_at": "2025-02-01",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "reasoning": true,
    "structured_output": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "family": "Sonar",
   "deprecated": true,
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/sonar-deep-research"
   ],
   "intro_i18n": {
    "zh-CN": "Deep Research 提供专家级的深度研究，并将其整合为易于理解和可操作的报告。",
    "zh-TW": "Deep Research 提供專業級的深入研究，並將其整合為易於理解與採取行動的報告。",
    "ja-JP": "Deep Research は、専門家レベルの包括的な調査を行い、それを分かりやすく実用的なレポートにまとめます。",
    "ru-RU": "Deep Research проводит всесторонние экспертные исследования и преобразует их в доступные и практичные отчеты."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/sonar-medium-chat",
   "model_name": "sonar-medium-chat",
   "display_name": "sonar-medium-chat",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "perplexity/sonar-medium-online",
   "model_name": "sonar-medium-online",
   "display_name": "sonar-medium-online",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "request": {
       "unit": "per_request",
       "price": "0.005"
      }
     }
    }
   ],
   "max_input_tokens": 12000,
   "max_output_tokens": 12000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "perplexity/sonar-pro",
   "model_name": "sonar-pro",
   "display_name": "Sonar Pro",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "request": {
       "unit": "per_k_calls",
       "price": "14"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "perplexity/sonar-pro"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "perplexity/sonar-pro"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "perplexity/sonar-pro"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.992"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "perplexity/sonar-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "perplexity/sonar-pro"
    },
    {
     "provider": "sap-ai-core",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "perplexity/sonar-pro"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "perplexity/sonar-pro"
    }
   ],
   "intro": "Deeper Sonar search model with broader retrieval and stronger synthesis",
   "released_at": "2024-01-01",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 200000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "sonar-pro",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "vision_understanding",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "response_format",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/sonar-pro"
   ],
   "intro_i18n": {
    "zh-CN": "Perplexity 的旗舰产品，具备搜索支撑，支持高级查询和追问。",
    "zh-TW": "Perplexity 的旗艦產品，具備搜尋依據，支援進階查詢與後續提問。",
    "ja-JP": "Perplexityの主力製品で、検索に基づいた高度なクエリやフォローアップに対応します。",
    "ru-RU": "Флагманский продукт Perplexity с привязкой к поиску, поддерживающий сложные запросы и уточнения."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/sonar-pro-search",
   "model_name": "sonar-pro-search",
   "display_name": "Perplexity: Sonar Pro Search",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "perplexity/sonar-pro-search"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "request": {
       "unit": "per_request",
       "price": "0.018"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "18"
      }
     },
     "provider_model_id": "perplexity/sonar-pro-search"
    }
   ],
   "intro": "Sonar Pro Search is Perplexity's advanced agentic search system for deeper reasoning and analysis.",
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "structured_output": true,
    "pdf_input": true
   },
   "released_at": "2025-10-31",
   "max_input_tokens": 200000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "sonar-pro",
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p",
     "web_search_options"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/sonar-pro-search"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Perplexity: Sonar Pro Search"
    }
   ]
  },
  {
   "slug": "perplexity/sonar-reasoning",
   "model_name": "sonar-reasoning",
   "display_name": "sonar-reasoning",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+pydantic-prices+helicone-registry+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "8"
      },
      "request": {
       "unit": "per_k_calls",
       "price": "12"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "perplexity/sonar-reasoning"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "perplexity/sonar-reasoning"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      }
     },
     "provider_model_id": "perplexity/sonar-reasoning"
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "web_search": true,
    "stream": true
   },
   "intro": "Sonar Reasoning is a reasoning model provided by Perplexity based on DeepSeek R1.",
   "knowledge_cutoff": "2025-01",
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "reasoning",
     "response_format",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "released_at": "2025-01-21",
   "family": "sonar-reasoning",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/sonar-reasoning"
   ],
   "intro_i18n": {
    "zh-CN": "专注推理的模型，输出详细的搜索支撑解释和思维链。",
    "zh-TW": "一款專注推理的模型，輸出具詳細搜尋依據的思考鏈（CoT）解釋。",
    "ja-JP": "詳細な検索に基づく説明を伴う思考の連鎖（CoT）を出力する推論特化モデルです。",
    "ru-RU": "Модель, ориентированная на рассуждение, выводящая цепочку мыслей с подробными объяснениями, основанными на поиске."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/sonar-reasoning-pro",
   "model_name": "sonar-reasoning-pro",
   "display_name": "Sonar Reasoning Pro",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      },
      "request": {
       "unit": "per_k_calls",
       "price": "14"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "perplexity/sonar-reasoning-pro"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "perplexity/sonar-reasoning-pro"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "perplexity/sonar-reasoning-pro"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.9985"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "perplexity/sonar-reasoning-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "perplexity/sonar-reasoning-pro"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "perplexity/sonar-reasoning-pro"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     },
     "provider_model_id": "perplexity/sonar-reasoning-pro"
    }
   ],
   "intro": "Web-grounded Sonar for multi-step research questions that need cited reasoning",
   "released_at": "2024-01-01",
   "knowledge_cutoff": "2025-09",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "sonar-reasoning",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "max_tokens",
     "reasoning",
     "response_format",
     "stop",
     "temperature",
     "top_p"
    ]
   },
   "deprecated": true,
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "perplexity/sonar-reasoning-pro"
   ],
   "intro_i18n": {
    "zh-CN": "专注推理的高级模型，输出带搜索增强的思维链，每次请求可包含多个搜索查询。",
    "zh-TW": "一款專注推理的進階模型，輸出包含增強搜尋的思考鏈（CoT），每次請求可包含多個搜尋查詢。",
    "ja-JP": "強化された検索機能を備えた高度な推論特化モデル。1リクエストあたり複数の検索クエリを含むCoT（思考の連鎖）を出力します。",
    "ru-RU": "Продвинутая модель, ориентированная на рассуждение, выводящая цепочку мыслей с расширенным поиском, включая несколько поисковых запросов на один запрос."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "perplexity/sonar-small-chat",
   "model_name": "sonar-small-chat",
   "display_name": "sonar-small-chat",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "perplexity/sonar-small-online",
   "model_name": "sonar-small-online",
   "display_name": "sonar-small-online",
   "vendor": "perplexity",
   "pricing": [
    {
     "provider": "perplexity",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      }
     }
    }
   ],
   "max_input_tokens": 12000,
   "max_output_tokens": 12000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "pixverse/Pixverse-6-T2V",
   "model_name": "Pixverse-6-T2V",
   "display_name": "Pixverse-6-T2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.045"
      }
     },
     "provider_model_id": "Pixverse/Pixverse-6-T2V"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video",
     "audio"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Pixverse/Pixverse-6-T2V"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pixverse-6-T2V"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-c1-it2v",
   "model_name": "pixverse-c1-it2v",
   "display_name": "PixVerse C1 IT2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.057353"
      }
     },
     "provider_model_id": "pixverse/pixverse-c1-it2v"
    }
   ],
   "released_at": "2026-04-07",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-c1-it2v"
   ],
   "intro_i18n": {
    "zh-CN": "C1 是 PixVerse 于 2026 年 3 月下旬推出的面向影视行业的大规模模型。其 it2v（image-to-video）能力不仅具备类似 t2v（text-to-video）的提示可控性，还能高保真还原参考图像的色彩、饱和度、场景与角色特征。相比 V6，具备更强的提示理解力与创造力，并能生成更接近专业电影水准的打斗动作与特效（如法术）。模型支持最长 15 秒视频生成，支持直接出音乐视频，且兼容多语言。特别适合单人特写、独白、定格或慢动作片段，以及转场类镜头等短时段画面生成。",
    "zh-TW": "C1 是 PixVerse 於 2026 年 3 月下旬面向影視行業推出的大規模模型。其 it2v（image-to-video）能力不僅具備類似 t2v（text-to-video）的提示可控性，還能高度還原參考圖的色彩、飽和度、場景與角色特徵。相較於 V6，其具備更佳的提示理解力與創造力，並能生成更接近專業電影水準的動作場面與視覺特效（如法術）。該模型可生成最長 15 秒影片，支援直接輸出搭配音樂的影片，並支援多語言。特別適合單人特寫、獨白、定格或慢動作片段、轉場銜接鏡頭等短時長鏡頭。",
    "ja-JP": "C1 は、PixVerse が 2026 年 3 月下旬に公開した、映画・映像業界向けの大規模モデルです。it2v（画像→動画）機能により、t2v（テキスト→動画）同様のプロンプト操作性を提供しつつ、参照画像の色彩・彩度・シーン・人物特徴を高精度に保持します。V6 と比べてプロンプト解釈力や創造性が向上し、アクション演出や魔法などの視覚効果もプロ水準に近づきました。最大 15 秒の動画生成、音楽付きの直接出力、多言語対応により、ワンショットのクローズアップ、モノローグ、フリーズフレーム、スローモーション、トランジションなどの短尺カットに特に適しています。",
    "ru-RU": "C1 — это крупномасштабная модель для кино- и телеиндустрии, представленная PixVerse в конце марта 2026 года. Возможности it2v (image-to-video) обеспечивают не только управляемость через промпты, схожую с t2v (text-to-video), но и высокую точность передачи цвета, насыщенности, сцен и характеристик персонажей из референсных изображений. По сравнению с V6 модель улучшает интерпретацию промптов, обладает большей креативностью и обеспечивает постановку боевых сцен и визуальные эффекты (например, магию) на уровне, близком к профессиональному кинопроизводству. Модель поддерживает генерацию видео длительностью до 15 секунд, включает музыку непосредственно в видеовывод и поддерживает несколько языков. Особенно хорошо подходит для коротких сцен, таких как крупные планы одного персонажа, монологи, замедленные или статичные фрагменты, а также переходные планы."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse C1 IT2V"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-c1-kf2v",
   "model_name": "pixverse-c1-kf2v",
   "display_name": "PixVerse C1 KF2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.057353"
      }
     },
     "provider_model_id": "pixverse/pixverse-c1-kf2v"
    }
   ],
   "released_at": "2026-04-07",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-c1-kf2v"
   ],
   "intro_i18n": {
    "zh-CN": "C1 是 PixVerse 于 2026 年 3 月下旬推出的面向影视行业的大规模模型。其 kf2v（keyframe-to-video）能力可在任意两张输入图像间生成平滑自然的衔接。模型支持最长 15 秒视频生成，可直接输出带音乐的视频，并支持多语言。",
    "zh-TW": "C1 是 PixVerse 於 2026 年 3 月下旬面向影視行業推出的大規模模型。其 kf2v（keyframe-to-video）能力可在任意兩張輸入影像之間生成自然流暢的過渡。該模型可生成最長 15 秒影片，支援直接輸出搭配音樂的影片，並支援多語言。",
    "ja-JP": "C1 は、PixVerse が 2026 年 3 月下旬に公開した、映画・映像業界向けの大規模モデルです。kf2v（キーフレーム→動画）機能により、任意の 2 枚の入力画像間で、自然かつ滑らかな遷移を実現します。最大 15 秒の動画生成、音楽付き直接出力、多言語対応を備えています。",
    "ru-RU": "C1 — это крупномасштабная модель для кино- и телеиндустрии, запущенная PixVerse в конце марта 2026 года. Возможности kf2v (keyframe-to-video) обеспечивают плавные и естественные переходы между двумя любыми входными изображениями. Модель поддерживает генерацию видео до 15 секунд, включает музыку непосредственно в видеовывод и поддерживает несколько языков."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse C1 KF2V"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-c1-r2v",
   "model_name": "pixverse-c1-r2v",
   "display_name": "PixVerse C1 R2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.057353"
      }
     },
     "provider_model_id": "pixverse/pixverse-c1-r2v"
    }
   ],
   "released_at": "2026-04-07",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-c1-r2v"
   ],
   "intro_i18n": {
    "zh-CN": "C1 是 PixVerse 于 2026 年 3 月下旬推出的面向影视行业的大规模模型。其 r2v（reference-to-video）能力支持输入 2–7 张图像，可在保留类似 t2v（text-to-video）的提示可控性和 it2v（image-to-video）的连贯性与创造力的基础上，智能融合多主体内容，生成更接近专业电影水准的打斗动作与特效（如法术与动作场面）。模型支持最长 15 秒视频生成，可直接输出带音乐的视频，并支持多语言。特别适合多角色群像、对话与互动等复杂场景，尤其擅长中景与大全景镜头。当输入单张多宫格分镜图（最多支持 9 宫格）时，可一键生成连续多镜头视频序列。",
    "zh-TW": "C1 是 PixVerse 於 2026 年 3 月下旬面向影視行業推出的大規模模型。其 r2v（reference-to-video）能力支援輸入 2–7 張影像，能智慧融合多個主體，同時保留類似 t2v（text-to-video）的提示可控性，以及 it2v（image-to-video）的連貫性與創造力。其生成的動作場面與視覺特效（例如法術與動作鏡頭）更接近專業電影水準。該模型可生成最長 15 秒影片，支援直接輸出搭配音樂的影片，並能處理多語言。特別適用於多人群像、對話與互動等複雜場景，尤其是中景與大全景鏡頭。若提供單張多分鏡頭故事版圖片（最多支援 9 宮格），還能一鍵生成連續多鏡頭影片序列。",
    "ja-JP": "C1 は、PixVerse が 2026 年 3 月下旬に公開した、映画・映像業界向けの大規模モデルです。r2v（リファレンス→動画）機能では 2〜7 枚の画像を入力でき、複数の被写体を知的に融合しながら、t2v（テキスト→動画）同様のプロンプト操作性と、it2v（画像→動画）の一貫性と創造性を兼ね備えています。アクション演出や魔法などの視覚効果をプロ映画レベルに近づけます。最大 15 秒の動画生成、音楽付き直接出力、多言語対応により、複数人物のグループショット、会話、インタラクションなどの複雑なシーン、とくにミディアム〜ワイドショットに適しています。1 枚のマルチパネル構図（最大 9 パネル）を入力した場合、マルチショット構成の連続動画をワンクリックで生成できます。",
    "ru-RU": "C1 — это крупномасштабная модель для кино- и телеиндустрии, выпущенная PixVerse в конце марта 2026 года. Возможности r2v (reference-to-video) позволяют вводить 2–7 изображений, интеллектуально объединяя несколько персонажей при сохранении управляемости промптом, аналогичной t2v, а также согласованности и креативности, присущих it2v. Модель обеспечивает постановку боевых сцен и визуальные эффекты (например, магию и экшн-сцены) на уровне, близком к профессиональному кино. Она поддерживает генерацию видео до 15 секунд, включает музыку в прямой видеовывод и работает с несколькими языками. Особенно подходит для сложных сцен, таких как групповые кадры, диалоги и взаимодействия, прежде всего в среднем и широком плане. При вводе одного многокадрового сториборда (до 9 кадров) модель может создать непрерывную многокадровую видеопоследовательность одним нажатием."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse C1 R2V"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-c1-t2v",
   "model_name": "pixverse-c1-t2v",
   "display_name": "PixVerse C1 T2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.057353"
      }
     },
     "provider_model_id": "pixverse/pixverse-c1-t2v"
    }
   ],
   "released_at": "2026-04-07",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-c1-t2v"
   ],
   "intro_i18n": {
    "zh-CN": "C1 是 PixVerse 于 2026 年 3 月下旬推出的面向影视行业的大规模模型。其 t2v（text-to-video）能力可通过提示词对视频生成进行精确控制，能够准确复现推、拉、摇、移、跟等多种电影语言技法，实现流畅的镜头运动与良好的视角切换。模型支持最长 15 秒视频生成，可直接输出带音乐的视频，并支持多语言。",
    "zh-TW": "C1 是 PixVerse 於 2026 年 3 月下旬面向影視行業推出的大規模模型。其 t2v（text-to-video）能力可透過文字提示精準控制影片生成，準確還原多種電影語言技巧，如推軌、拉鏡、平移、俯仰與移動鏡頭，呈現流暢的運鏡與穩定的視角轉換。該模型可生成最長 15 秒影片，支援直接輸出搭配音樂的影片，並支援多語言。",
    "ja-JP": "C1 は、PixVerse が 2026 年 3 月下旬に公開した、映画・映像業界向けの大規模モデルです。t2v（テキスト→動画）機能では、プロンプトによる動画生成の精密な制御が可能で、ドリーズーム、パン、チルト、トラッキングなど、多様な映画撮影技法を滑らかなカメラワークと適切な視点遷移で再現します。最大 15 秒の動画生成、音楽付き直接出力、多言語対応に対応しています。",
    "ru-RU": "C1 — это крупномасштабная модель для кино- и телеиндустрии, представленная PixVerse в конце марта 2026 года. Возможности t2v (text-to-video) обеспечивают точный контроль над генерацией видео с помощью промптов, точно воспроизводя различные кинематографические приемы, такие как наезды, отъезды, панорамы, наклоны и проходы камеры, обеспечивая плавные движения камеры и контролируемые переходы перспективы. Модель поддерживает генерацию видео до 15 секунд, включает музыку непосредственно в видеовывод и поддерживает множество языков."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse C1 T2V"
    }
   ]
  },
  {
   "slug": "pixverse/Pixverse-T2V",
   "model_name": "Pixverse-T2V",
   "display_name": "Pixverse-T2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.2"
      }
     },
     "provider_model_id": "Pixverse/Pixverse-T2V"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Pixverse/Pixverse-T2V"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pixverse-T2V"
    }
   ]
  },
  {
   "slug": "pixverse/Pixverse-T2V-HD",
   "model_name": "Pixverse-T2V-HD",
   "display_name": "Pixverse-T2V-HD",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.4"
      }
     },
     "provider_model_id": "Pixverse/Pixverse-T2V-HD"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Pixverse/Pixverse-T2V-HD"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pixverse-T2V-HD"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-v5.6",
   "model_name": "pixverse-v5.6",
   "display_name": "pixverse-v5.6",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.1326"
      }
     },
     "provider_model_id": "pixverse/pixverse-v5.6"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-v5.6"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "pixverse-v5.6"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-v5.6-it2v",
   "model_name": "pixverse-v5.6-it2v",
   "display_name": "PixVerse V5.6 IT2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.077941"
      }
     },
     "provider_model_id": "pixverse/pixverse-v5.6-it2v"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-v5.6-it2v"
   ],
   "intro_i18n": {
    "zh-CN": "上传任意图像，自由定制故事、节奏和风格，生成生动连贯的视频。PixVerse V5.6是爱视科技自主研发的视频生成大模型，在文本转视频和图像转视频能力上实现了全面升级。模型显著提升了图像清晰度、复杂动作的稳定性以及音视频同步性。在多角色对话场景中，唇形同步准确，情感表达自然。构图、光线和纹理一致性也得到了优化，进一步提升了整体生成质量。PixVerse V5.6在人工分析文本转视频和图像转视频排行榜上位居全球顶级。",
    "zh-TW": "上傳任意影像，自由定制故事、節奏及風格，生成生動且連貫的影像。PixVerse V5.6是愛視科技自研的影像生成大型模型，在文字生成影像及影像生成影像能力方面進行了全面升級。模型顯著提升影像清晰度、複雜動作穩定性及音視同步性。多角色對話場景中的唇同步準確性及自然情感表達得到改善。構圖、光線及紋理一致性也得到優化，進一步提升整體生成質量。PixVerse V5.6在人工分析文字生成影像及影像生成影像排行榜中排名全球頂級。",
    "ja-JP": "任意の画像をアップロードしてストーリー、ペース、スタイルを自由にカスタマイズし、生き生きとした一貫性のあるビデオを生成します。PixVerse V5.6は、Aishi Technologyが独自に開発したビデオ生成大型モデルで、テキストからビデオおよび画像からビデオの両方の能力において包括的なアップグレードを提供します。このモデルは、画像の明瞭さ、複雑な動きの安定性、音声とビジュアルの同期を大幅に向上させます。複数キャラクターの対話シーンでのリップシンク精度と自然な感情表現が改善され、構図、照明、テクスチャの一貫性も最適化され、全体的な生成品質がさらに向上します。PixVerse V5.6は、Artificial Analysisのテキストからビデオおよび画像からビデオのリーダーボードで世界トップクラスにランクインしています。",
    "ru-RU": "Загрузите любое изображение, чтобы свободно настроить сюжет, темп и стиль, создавая яркие и последовательные видео. PixVerse V5.6 — это крупная модель генерации видео, разработанная Aishi Technology, предлагающая комплексные улучшения как в преобразовании текста в видео, так и изображения в видео. Модель значительно улучшает четкость изображения, стабильность в сложных движениях и синхронизацию аудио и видео. Точность синхронизации губ и естественное выражение эмоций улучшены в сценах с диалогами нескольких персонажей. Композиция, освещение и согласованность текстур также оптимизированы, что еще больше повышает общее качество генерации. PixVerse V5.6 занимает лидирующие позиции в мировом рейтинге Artificial Analysis по преобразованию текста в видео и изображения в видео."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse V5.6 IT2V"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-v5.6-kf2v",
   "model_name": "pixverse-v5.6-kf2v",
   "display_name": "PixVerse V5.6 KF2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.077941"
      }
     },
     "provider_model_id": "pixverse/pixverse-v5.6-kf2v"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-v5.6-kf2v"
   ],
   "intro_i18n": {
    "zh-CN": "实现任意两张图像之间的无缝过渡，创造更平滑自然的场景变化和视觉效果。PixVerse V5.6是爱视科技自主研发的视频生成大模型，在文本转视频和图像转视频能力上实现了全面升级。模型显著提升了图像清晰度、复杂动作的稳定性以及音视频同步性。在多角色对话场景中，唇形同步准确，情感表达自然。构图、光线和纹理一致性也得到了优化，进一步提升了整体生成质量。PixVerse V5.6在人工分析文本转视频和图像转视频排行榜上位居全球顶级。",
    "zh-TW": "實現任意兩張影像之間的無縫過渡，創造更流暢且自然的場景變化，並具有視覺震撼效果。PixVerse V5.6是愛視科技自研的影像生成大型模型，在文字生成影像及影像生成影像能力方面進行了全面升級。模型顯著提升影像清晰度、複雜動作穩定性及音視同步性。多角色對話場景中的唇同步準確性及自然情感表達得到改善。構圖、光線及紋理一致性也得到優化，進一步提升整體生成質量。PixVerse V5.6在人工分析文字生成影像及影像生成影像排行榜中排名全球頂級。",
    "ja-JP": "任意の2つの画像間でシームレスな遷移を実現し、より滑らかで自然なシーン変更を視覚的に印象的な効果で作成します。PixVerse V5.6は、Aishi Technologyが独自に開発したビデオ生成大型モデルで、テキストからビデオおよび画像からビデオの両方の能力において包括的なアップグレードを提供します。このモデルは、画像の明瞭さ、複雑な動きの安定性、音声とビジュアルの同期を大幅に向上させます。複数キャラクターの対話シーンでのリップシンク精度と自然な感情表現が改善され、構図、照明、テクスチャの一貫性も最適化され、全体的な生成品質がさらに向上します。PixVerse V5.6は、Artificial Analysisのテキストからビデオおよび画像からビデオのリーダーボードで世界トップクラスにランクインしています。",
    "ru-RU": "Достигайте плавных переходов между любыми двумя изображениями, создавая более естественные изменения сцен с визуально впечатляющими эффектами. PixVerse V5.6 — это крупная модель генерации видео, разработанная Aishi Technology, предлагающая комплексные улучшения как в преобразовании текста в видео, так и изображения в видео. Модель значительно улучшает четкость изображения, стабильность в сложных движениях и синхронизацию аудио и видео. Точность синхронизации губ и естественное выражение эмоций улучшены в сценах с диалогами нескольких персонажей. Композиция, освещение и согласованность текстур также оптимизированы, что еще больше повышает общее качество генерации. PixVerse V5.6 занимает лидирующие позиции в мировом рейтинге Artificial Analysis по преобразованию текста в видео и изображения в видео."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse V5.6 KF2V"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-v5.6-r2v",
   "model_name": "pixverse-v5.6-r2v",
   "display_name": "PixVerse V5.6 R2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.077941"
      }
     },
     "provider_model_id": "pixverse/pixverse-v5.6-r2v"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-v5.6-r2v"
   ],
   "intro_i18n": {
    "zh-CN": "输入2-7张图像，智能融合不同主体，同时保持统一风格和协调动作，轻松构建丰富的叙事场景，增强内容可控性和创作自由度。PixVerse V5.6是爱视科技自主研发的视频生成大模型，在文本转视频和图像转视频能力上实现了全面升级。模型显著提升了图像清晰度、复杂动作的稳定性以及音视频同步性。在多角色对话场景中，唇形同步准确，情感表达自然。构图、光线和纹理一致性也得到了优化，进一步提升了整体生成质量。PixVerse V5.6在人工分析文本转视频和图像转视频排行榜上位居全球顶级。",
    "zh-TW": "輸入2至7張影像，智能融合不同主題，同時保持統一風格及協調動作，輕鬆構建豐富敘事場景，增強內容可控性及創意自由度。PixVerse V5.6是愛視科技自研的影像生成大型模型，在文字生成影像及影像生成影像能力方面進行了全面升級。模型顯著提升影像清晰度、複雜動作穩定性及音視同步性。多角色對話場景中的唇同步準確性及自然情感表達得到改善。構圖、光線及紋理一致性也得到優化，進一步提升整體生成質量。PixVerse V5.6在人工分析文字生成影像及影像生成影像排行榜中排名全球頂級。",
    "ja-JP": "2～7枚の画像を入力して異なる被写体をインテリジェントに統合し、統一されたスタイルと調和の取れた動きを維持しながら、豊かな物語シーンを簡単に構築し、コンテンツの制御性と創造的自由を向上させます。PixVerse V5.6は、Aishi Technologyが独自に開発したビデオ生成大型モデルで、テキストからビデオおよび画像からビデオの両方の能力において包括的なアップグレードを提供します。このモデルは、画像の明瞭さ、複雑な動きの安定性、音声とビジュアルの同期を大幅に向上させます。複数キャラクターの対話シーンでのリップシンク精度と自然な感情表現が改善され、構図、照明、テクスチャの一貫性も最適化され、全体的な生成品質がさらに向上します。PixVerse V5.6は、Artificial Analysisのテキストからビデオおよび画像からビデオのリーダーボードで世界トップクラスにランクインしています。",
    "ru-RU": "Введите 2–7 изображений, чтобы интеллектуально объединить разные объекты, сохраняя единый стиль и согласованное движение, легко создавая богатые повествовательные сцены и повышая управляемость контента и творческую свободу. PixVerse V5.6 — это крупная модель генерации видео, разработанная Aishi Technology, предлагающая комплексные улучшения как в преобразовании текста в видео, так и изображения в видео. Модель значительно улучшает четкость изображения, стабильность в сложных движениях и синхронизацию аудио и видео. Точность синхронизации губ и естественное выражение эмоций улучшены в сценах с диалогами нескольких персонажей. Композиция, освещение и согласованность текстур также оптимизированы, что еще больше повышает общее качество генерации. PixVerse V5.6 занимает лидирующие позиции в мировом рейтинге Artificial Analysis по преобразованию текста в видео и изображения в видео."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse V5.6 R2V"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-v5.6-t2v",
   "model_name": "pixverse-v5.6-t2v",
   "display_name": "PixVerse V5.6 T2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.077941"
      }
     },
     "provider_model_id": "pixverse/pixverse-v5.6-t2v"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-v5.6-t2v"
   ],
   "intro_i18n": {
    "zh-CN": "输入文本描述，以秒级速度生成高质量视频，并实现精确的语义对齐，支持多种风格。PixVerse V5.6是爱视科技自主研发的视频生成大模型，在文本转视频和图像转视频能力上实现了全面升级。模型显著提升了图像清晰度、复杂动作的稳定性以及音视频同步性。在多角色对话场景中，唇形同步准确，情感表达自然。构图、光线和纹理一致性也得到了优化，进一步提升了整体生成质量。PixVerse V5.6在人工分析文本转视频和图像转视频排行榜上位居全球顶级。",
    "zh-TW": "輸入文字描述即可生成高質量影像，支持多種風格，速度達秒級且語義對齊精確。PixVerse V5.6是愛視科技自研的影像生成大型模型，在文字生成影像及影像生成影像能力方面進行了全面升級。模型顯著提升影像清晰度、複雜動作穩定性及音視同步性。多角色對話場景中的唇同步準確性及自然情感表達得到改善。構圖、光線及紋理一致性也得到優化，進一步提升整體生成質量。PixVerse V5.6在人工分析文字生成影像及影像生成影像排行榜中排名全球頂級。",
    "ja-JP": "テキスト説明を入力して、高品質なビデオを秒単位の速度で生成し、正確な意味的整合性をサポートします。PixVerse V5.6は、Aishi Technologyが独自に開発したビデオ生成大型モデルで、テキストからビデオおよび画像からビデオの両方の能力において包括的なアップグレードを提供します。このモデルは、画像の明瞭さ、複雑な動きの安定性、音声とビジュアルの同期を大幅に向上させます。複数キャラクターの対話シーンでのリップシンク精度と自然な感情表現が改善され、構図、照明、テクスチャの一貫性も最適化され、全体的な生成品質がさらに向上します。PixVerse V5.6は、Artificial Analysisのテキストからビデオおよび画像からビデオのリーダーボードで世界トップクラスにランクインしています。",
    "ru-RU": "Введите текстовое описание, чтобы сгенерировать видео высокого качества с секундной скоростью и точным семантическим соответствием, поддерживающим несколько стилей. PixVerse V5.6 — это крупная модель генерации видео, разработанная Aishi Technology, предлагающая комплексные улучшения как в преобразовании текста в видео, так и изображения в видео. Модель значительно улучшает четкость изображения, стабильность в сложных движениях и синхронизацию аудио и видео. Точность синхронизации губ и естественное выражение эмоций улучшены в сценах с диалогами нескольких персонажей. Композиция, освещение и согласованность текстур также оптимизированы, что еще больше повышает общее качество генерации. PixVerse V5.6 занимает лидирующие позиции в мировом рейтинге Artificial Analysis по преобразованию текста в видео и изображения в видео."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse V5.6 T2V"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-v6",
   "model_name": "pixverse-v6",
   "display_name": "pixverse-v6",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.09"
      }
     },
     "provider_model_id": "pixverse/pixverse-v6"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-v6"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "pixverse-v6"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-v6-it2v",
   "model_name": "pixverse-v6-it2v",
   "display_name": "PixVerse V6 IT2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.052941"
      }
     },
     "provider_model_id": "pixverse/pixverse-v6-it2v"
    }
   ],
   "released_at": "2026-03-30",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-v6-it2v"
   ],
   "intro_i18n": {
    "zh-CN": "V6是PixVerse于2026年3月底推出的新模型，其it2v（图像转视频）模型全球排名第二。除了t2v（文本转视频）的提示控制能力外，it2v还能准确再现参考图像的颜色、饱和度、场景和角色特征，提供更强的角色情感和高速运动表现。支持最长15秒视频，直接输出音乐和视频，并支持多种语言。适用于电商产品特写、广告宣传片和模拟C4D建模等场景，一键直接输出。",
    "zh-TW": "V6是PixVerse於2026年3月底推出的新模型，其it2v（影像生成影像）模型全球排名第二。除了t2v（文字生成影像）的提示控制能力外，it2v能精確再現參考影像的色彩、飽和度、場景及角色特徵，提供更強的角色情感及高速動作性能。支持長達15秒影像，直接輸出音樂及影像，並支持多語言。非常適合電商產品特寫、廣告宣傳及模擬C4D建模展示產品結構等場景，一鍵直接輸出。",
    "ja-JP": "V6は、PixVerseが2026年3月末にリリースした新モデルです。そのit2v（画像からビデオ）モデルは世界第2位にランクインしています。t2v（テキストからビデオ）のプロンプト制御能力に加えて、it2vは参照画像の色、彩度、シーン、キャラクターの特徴を正確に再現し、より強力なキャラクターの感情と高速動作性能を提供します。最大15秒のビデオ、音楽とビデオの直接出力、複数言語をサポートします。eコマース製品のクローズアップ、広告プロモーション、C4Dモデリングのシミュレーションなどのシナリオに最適で、ワンクリックで直接出力が可能です。",
    "ru-RU": "V6 — новая модель PixVerse, запущенная в конце марта 2026 года. Ее модель it2v (изображение в видео) занимает второе место в мире. Помимо возможностей управления подсказками t2v (текст в видео), it2v может точно воспроизводить цвета, насыщенность, сцены и особенности персонажей эталонных изображений, обеспечивая более сильные эмоции персонажей и производительность в высокоскоростных движениях. Поддерживает видео длиной до 15 секунд, прямой вывод музыки и видео, а также несколько языков. Идеально подходит для таких сценариев, как крупные планы товаров для электронной коммерции, рекламные ролики и моделирование C4D для демонстрации структуры продуктов с прямым выводом в один клик."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse V6 IT2V"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-v6-kf2v",
   "model_name": "pixverse-v6-kf2v",
   "display_name": "PixVerse V6 KF2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.052941"
      }
     },
     "provider_model_id": "pixverse/pixverse-v6-kf2v"
    }
   ],
   "released_at": "2026-03-30",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-v6-kf2v"
   ],
   "intro_i18n": {
    "zh-CN": "V6是PixVerse于2026年3月底推出的新模型，其kf2v（关键帧转视频）模型可无缝连接任意两张图像，生成更平滑自然的视频过渡。支持最长15秒视频，直接输出音乐和视频，并支持多种语言。",
    "zh-TW": "V6是PixVerse於2026年3月底推出的新模型，其kf2v（關鍵影格生成影像）模型能無縫連接任意兩張影像，生成更流暢且自然的影像過渡。支持長達15秒影像，直接輸出音樂及影像，並支持多語言。",
    "ja-JP": "V6は、PixVerseが2026年3月末にリリースした新モデルです。そのkf2v（キーフレームからビデオ）モデルは、任意の2つの画像をシームレスに接続し、より滑らかで自然なビデオ遷移を生成します。最大15秒のビデオ、音楽とビデオの直接出力、複数言語をサポートします。",
    "ru-RU": "V6 — новая модель PixVerse, запущенная в конце марта 2026 года. Ее модель kf2v (ключевые кадры в видео) может бесшовно соединять любые два изображения, создавая более плавные и естественные переходы видео. Поддерживает видео длиной до 15 секунд, прямой вывод музыки и видео, а также несколько языков."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse V6 KF2V"
    }
   ]
  },
  {
   "slug": "pixverse/pixverse-v6-t2v",
   "model_name": "pixverse-v6-t2v",
   "display_name": "PixVerse V6 T2V",
   "vendor": "pixverse",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.052941"
      }
     },
     "provider_model_id": "pixverse/pixverse-v6-t2v"
    }
   ],
   "released_at": "2026-03-30",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pixverse/pixverse-v6-t2v"
   ],
   "intro_i18n": {
    "zh-CN": "V6是PixVerse于2026年3月底推出的新模型，其t2v（文本转视频）模型通过提示精确控制视频视觉效果，准确再现各种电影技术。推拉、平移、倾斜、跟踪和跟随等摄像机运动平滑自然，视角切换精确可控。支持最长15秒视频，直接输出音乐和视频，并支持多种语言。",
    "zh-TW": "V6是PixVerse於2026年3月底推出的新模型，其t2v（文字生成影像）模型通過提示精確控制影像視覺效果，精確再現各種電影技術。推、拉、平移、傾斜、跟蹤及跟隨等相機運動流暢自然，視角切換精確可控。支持長達15秒影像，直接輸出音樂及影像，並支持多語言。",
    "ja-JP": "V6は、PixVerseが2026年3月末にリリースした新モデルです。そのt2v（テキストからビデオ）モデルは、プロンプトを通じてビデオビジュアルを正確に制御し、さまざまな映画技法を正確に再現します。プッシュ、プル、パン、チルト、トラッキング、フォローなどのカメラ動作が滑らかで自然であり、視点の切り替えも正確かつ制御可能です。最大15秒のビデオ、音楽とビデオの直接出力、複数言語をサポートします。",
    "ru-RU": "V6 — новая модель PixVerse, запущенная в конце марта 2026 года. Ее модель t2v (текст в видео) позволяет точно управлять визуальными эффектами видео через подсказки, точно воспроизводя различные кинематографические техники. Движения камеры, такие как приближение, отдаление, панорамирование, наклон, слежение и следование, плавные и естественные, с точным и управляемым переключением перспективы. Поддерживает видео длиной до 15 секунд, прямой вывод музыки и видео, а также несколько языков."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "PixVerse V6 T2V"
    }
   ]
  },
  {
   "slug": "recraft/recraft-v2",
   "model_name": "recraft-v2",
   "display_name": "Recraft V2",
   "vendor": "recraft",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.022"
      },
      "image_output_vector_illustration": {
       "unit": "per_image",
       "price": "0.044"
      }
     },
     "provider_model_id": "recraft/recraft-v2"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-03-13",
   "max_input_tokens": 512,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "recraft",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "recraft/recraft-v2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Recraft V2"
    }
   ]
  },
  {
   "slug": "recraft/recraft-v3",
   "model_name": "recraft-v3",
   "display_name": "Recraft V3",
   "vendor": "recraft",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      },
      "image_output_vector_illustration": {
       "unit": "per_image",
       "price": "0.08"
      }
     },
     "provider_model_id": "recraft/recraft-v3"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2024-10-30",
   "max_input_tokens": 512,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "recraft",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "recraft/recraft-v3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Recraft V3"
    }
   ]
  },
  {
   "slug": "recraft/recraft-v4",
   "model_name": "recraft-v4",
   "display_name": "Recraft V4",
   "vendor": "recraft",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      },
      "image_output_vector_illustration": {
       "unit": "per_image",
       "price": "0.08"
      }
     },
     "provider_model_id": "recraft/recraft-v4"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-02-17",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "recraft",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "recraft/recraft-v4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Recraft V4"
    }
   ]
  },
  {
   "slug": "recraft/recraft-v4-pro",
   "model_name": "recraft-v4-pro",
   "display_name": "Recraft V4 Pro",
   "vendor": "recraft",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.25"
      },
      "image_output_vector_illustration": {
       "unit": "per_image",
       "price": "0.3"
      }
     },
     "provider_model_id": "recraft/recraft-v4-pro"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-02-17",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "recraft",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "recraft/recraft-v4-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Recraft V4 Pro"
    }
   ]
  },
  {
   "slug": "recraft/recraft-v4.1",
   "model_name": "recraft-v4.1",
   "display_name": "Recraft V4.1",
   "vendor": "recraft",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.035"
      },
      "image_output_vector_illustration": {
       "unit": "per_image",
       "price": "0.08"
      }
     },
     "provider_model_id": "recraft/recraft-v4.1"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-05-14",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "recraft",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "recraft/recraft-v4.1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Recraft V4.1"
    }
   ]
  },
  {
   "slug": "recraft/recraft-v4.1-pro",
   "model_name": "recraft-v4.1-pro",
   "display_name": "Recraft V4.1 Pro",
   "vendor": "recraft",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.21"
      },
      "image_output_vector_illustration": {
       "unit": "per_image",
       "price": "0.3"
      }
     },
     "provider_model_id": "recraft/recraft-v4.1-pro"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-05-14",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "recraft",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "recraft/recraft-v4.1-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Recraft V4.1 Pro"
    }
   ]
  },
  {
   "slug": "recraft/recraft-v4.1-utility",
   "model_name": "recraft-v4.1-utility",
   "display_name": "Recraft V4.1 Utility",
   "vendor": "recraft",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.035"
      },
      "image_output_vector_illustration": {
       "unit": "per_image",
       "price": "0.08"
      }
     },
     "provider_model_id": "recraft/recraft-v4.1-utility"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-05-14",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "recraft",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "recraft/recraft-v4.1-utility"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Recraft V4.1 Utility"
    }
   ]
  },
  {
   "slug": "recraft/recraft-v4.1-utility-pro",
   "model_name": "recraft-v4.1-utility-pro",
   "display_name": "Recraft V4.1 Utility Pro",
   "vendor": "recraft",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.21"
      },
      "image_output_vector_illustration": {
       "unit": "per_image",
       "price": "0.3"
      }
     },
     "provider_model_id": "recraft/recraft-v4.1-utility-pro"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-05-14",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "family": "recraft",
   "capabilities": {
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "recraft/recraft-v4.1-utility-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Recraft V4.1 Utility Pro"
    }
   ]
  },
  {
   "slug": "reka/reka-edge",
   "model_name": "reka-edge",
   "display_name": "Reka Edge",
   "vendor": "reka",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "rekaai/reka-edge"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "rekaai/reka-edge"
    }
   ],
   "intro": "Multimodal model for analyzing text, images, documents, and rich media",
   "released_at": "2026-03-20",
   "max_input_tokens": 16384,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "image",
     "text",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "family": "reka",
   "deprecated": true,
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "reka/reka-edge",
    "rekaai/reka-edge"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Reka Edge"
    }
   ]
  },
  {
   "slug": "reka/reka-flash-3",
   "model_name": "reka-flash-3",
   "display_name": "Reka Flash 3",
   "vendor": "reka",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "rekaai/reka-flash-3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.01"
      }
     },
     "provider_model_id": "rekaai/reka-flash-3"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-03-12",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "knowledge_cutoff": "2025-01",
   "family": "reka",
   "deprecated": true,
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "reka-flash-3:free",
    "rekaai/reka-flash-3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Reka Flash 3"
    }
   ]
  },
  {
   "slug": "runway/runway",
   "model_name": "runway",
   "display_name": "Runway",
   "vendor": "runway",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2024-10-11",
   "max_input_tokens": 256,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "runway",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "runwayml/runway"
   ],
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Runway"
    }
   ]
  },
  {
   "slug": "runway/runway-gen-4-turbo",
   "model_name": "runway-gen-4-turbo",
   "display_name": "Runway-Gen-4-Turbo",
   "vendor": "runway",
   "pricing": [],
   "intro": "Video model for prompt-guided generation, editing, and motion workflows",
   "released_at": "2025-05-09",
   "max_input_tokens": 256,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "family": "runway",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "runwayml/runway-gen-4-turbo"
   ],
   "model_type": "video_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Runway-Gen-4-Turbo"
    }
   ]
  },
  {
   "slug": "sensenova/sensenova-6.7-flash-lite",
   "model_name": "sensenova-6.7-flash-lite",
   "display_name": "SenseNova 6.7 Flash Lite",
   "vendor": "sensenova",
   "pricing": [
    {
     "provider": "sensenova",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2026-05-08",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "一款为真实工作流设计的轻量级多模态代理模型，支持基于文本的对话和图像理解。轻量高效，平衡性能、成本和可部署性。原生多模态架构，支持图像理解，包括OCR和图表解析。针对办公和生产力场景进行了增强，稳定支持复杂的长链任务。改进了令牌效率，为复杂工作负载提供更好的成本控制。上下文长度为256K令牌（最大输入：252K，最大输出：64K）。",
    "zh-TW": "一款為現實工作流程設計的輕量級多模態代理模型，支持基於文本的對話和圖像理解。輕量高效，平衡性能、成本和可部署性。原生多模態架構，支持圖像理解，包括 OCR 和圖表解讀。針對辦公和生產力場景進行增強，穩定支持複雜的長鏈任務。改進的令牌效率，實現對複雜工作負載的更好成本控制。上下文長度為 256K 令牌（最大輸入：252K，最大輸出：64K）。",
    "ja-JP": "現実世界のワークフロー向けに設計された軽量マルチモーダルエージェントモデルで、テキストベースの会話と画像理解の両方をサポートします。軽量かつ効率的で、性能、コスト、展開性のバランスを実現しています。画像理解を含むネイティブマルチモーダルアーキテクチャで、OCRやチャート解釈をサポートします。オフィスや生産性シナリオ向けに強化されており、複雑な長鎖タスクを安定してサポートします。トークン効率が向上し、複雑なワークロードのコスト管理が可能です。コンテキスト長は256Kトークン（最大入力: 252K、最大出力: 64K）。",
    "ru-RU": "Легковесная мультимодальная модель-агент, разработанная для рабочих процессов в реальном мире, поддерживающая как текстовые беседы, так и понимание изображений. Легкая и эффективная, сбалансированная по производительности, стоимости и возможностям развертывания. Родная мультимодальная архитектура с поддержкой понимания изображений, включая OCR и интерпретацию диаграмм. Улучшена для офисных и производственных сценариев, со стабильной поддержкой сложных задач с длинной цепочкой. Повышена эффективность токенов, что позволяет лучше контролировать затраты на сложные рабочие нагрузки. Контекстная длина составляет 256K токенов (максимальный ввод: 252K, максимальный вывод: 64K)."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "SenseNova 6.7 Flash Lite"
    }
   ]
  },
  {
   "slug": "sensenova/sensenova-u1-fast",
   "model_name": "sensenova-u1-fast",
   "display_name": "SenseNova U1 Fast",
   "vendor": "sensenova",
   "pricing": [
    {
     "provider": "sensenova",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2026-05-08",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "基于SenseNova U1的加速版本，专为信息图生成进行了优化。",
    "zh-TW": "基於 SenseNova U1 的加速版本，專為信息圖生成進行了優化。",
    "ja-JP": "SenseNova U1をベースにした高速版で、特にインフォグラフィック生成に最適化されています。",
    "ru-RU": "Ускоренная версия на основе SenseNova U1, специально оптимизированная для генерации инфографики."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "SenseNova U1 Fast"
    }
   ]
  },
  {
   "slug": "skywork/r1v4-lite",
   "model_name": "r1v4-lite",
   "display_name": "Skywork R1V4-Lite",
   "vendor": "skywork",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "skywork/r1v4-lite"
    }
   ],
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "structured_output": true,
    "pdf_input": true,
    "open_weights": true
   },
   "released_at": "2025-11-18",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "skywork",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "skywork/r1v4-lite"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Skywork R1V4-Lite"
    }
   ]
  },
  {
   "slug": "stability/sdxl-turbo",
   "model_name": "sdxl-turbo",
   "display_name": "sdxl-turbo",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.0002"
      }
     },
     "provider_model_id": "stabilityai/sdxl-turbo"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "stabilityai/sdxl-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sdxl-turbo"
    }
   ]
  },
  {
   "slug": "stability/stability.sd3-5-large-v1",
   "model_name": "stability.sd3-5-large-v1",
   "display_name": "stability.sd3-5-large-v1",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.08"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "stability.sd3-5-large-v1"
    }
   ]
  },
  {
   "slug": "stability/stability.stable-diffusion-xl-v0::premium",
   "model_name": "stability.stable-diffusion-xl-v0::premium",
   "display_name": "stability.stable-diffusion-xl-v0::premium",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.08"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "stability.stable-diffusion-xl-v0::premium"
    }
   ]
  },
  {
   "slug": "stability/stability.stable-diffusion-xl-v1::premium",
   "model_name": "stability.stable-diffusion-xl-v1::premium",
   "display_name": "stability.stable-diffusion-xl-v1::premium",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.08"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "stability.stable-diffusion-xl-v1::premium"
    }
   ]
  },
  {
   "slug": "stability/stability.stable-image-core-v1",
   "model_name": "stability.stable-image-core-v1",
   "display_name": "stability.stable-image-core-v1",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.04"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "stability.stable-image-core-v1"
    }
   ]
  },
  {
   "slug": "stability/stability.stable-image-ultra-v1",
   "model_name": "stability.stable-image-ultra-v1",
   "display_name": "stability.stable-image-ultra-v1",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "portkey",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.14"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "stability.stable-image-ultra-v1"
    }
   ]
  },
  {
   "slug": "stability/stable-diffusion-3-medium",
   "model_name": "stable-diffusion-3-medium",
   "display_name": "stable-diffusion-3-medium",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.0019"
      }
     },
     "provider_model_id": "stabilityai/stable-diffusion-3-medium"
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "stabilityai/stable-diffusion-3-medium"
   ],
   "intro_i18n": {
    "zh-CN": "Stability AI 最新的文本生成图像模型。该版本显著提升图像质量、文本理解与风格多样性，能更准确地解析复杂自然语言提示并生成更精确多样的图像。",
    "zh-TW": "Stability AI 最新的文字轉圖像模型。本版本大幅提升圖像品質、文字理解與風格多樣性，能更準確地解析複雜自然語言提示並生成精緻多樣的圖像。",
    "ja-JP": "Stability AI による最新のテキストから画像への変換モデルです。画像品質、テキスト理解、スタイルの多様性が大幅に向上し、複雑な自然言語プロンプトをより正確に解釈し、多様で精密な画像を生成します。",
    "ru-RU": "Последняя модель преобразования текста в изображение от Stability AI. Эта версия значительно улучшает качество изображений, понимание текста и разнообразие стилей, точнее интерпретирует сложные текстовые запросы и генерирует более точные и разнообразные изображения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "stable-diffusion-3-medium"
    }
   ]
  },
  {
   "slug": "stability/stablediffusionxl",
   "model_name": "stablediffusionxl",
   "display_name": "StableDiffusionXL",
   "vendor": "stability",
   "pricing": [],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2023-07-09",
   "max_input_tokens": 200,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "family": "stable-diffusion",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "stabilityai/stablediffusionxl"
   ],
   "model_type": "image_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "StableDiffusionXL"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-conservative-upscale-v1:0",
   "model_name": "us.stability.stable-conservative-upscale-v1:0",
   "display_name": "us.stability.stable-conservative-upscale-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.4"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-conservative-upscale-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-creative-upscale-v1:0",
   "model_name": "us.stability.stable-creative-upscale-v1:0",
   "display_name": "us.stability.stable-creative-upscale-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.6"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-creative-upscale-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-fast-upscale-v1:0",
   "model_name": "us.stability.stable-fast-upscale-v1:0",
   "display_name": "us.stability.stable-fast-upscale-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.03"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-fast-upscale-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-image-control-sketch-v1:0",
   "model_name": "us.stability.stable-image-control-sketch-v1:0",
   "display_name": "us.stability.stable-image-control-sketch-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-image-control-sketch-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-image-control-structure-v1:0",
   "model_name": "us.stability.stable-image-control-structure-v1:0",
   "display_name": "us.stability.stable-image-control-structure-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-image-control-structure-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-image-erase-object-v1:0",
   "model_name": "us.stability.stable-image-erase-object-v1:0",
   "display_name": "us.stability.stable-image-erase-object-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-image-erase-object-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-image-inpaint-v1:0",
   "model_name": "us.stability.stable-image-inpaint-v1:0",
   "display_name": "us.stability.stable-image-inpaint-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-image-inpaint-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-image-remove-background-v1:0",
   "model_name": "us.stability.stable-image-remove-background-v1:0",
   "display_name": "us.stability.stable-image-remove-background-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-image-remove-background-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-image-search-recolor-v1:0",
   "model_name": "us.stability.stable-image-search-recolor-v1:0",
   "display_name": "us.stability.stable-image-search-recolor-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-image-search-recolor-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-image-search-replace-v1:0",
   "model_name": "us.stability.stable-image-search-replace-v1:0",
   "display_name": "us.stability.stable-image-search-replace-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-image-search-replace-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-image-style-guide-v1:0",
   "model_name": "us.stability.stable-image-style-guide-v1:0",
   "display_name": "us.stability.stable-image-style-guide-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-image-style-guide-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-outpaint-v1:0",
   "model_name": "us.stability.stable-outpaint-v1:0",
   "display_name": "us.stability.stable-outpaint-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.06"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-outpaint-v1:0"
    }
   ]
  },
  {
   "slug": "stability/us.stability.stable-style-transfer-v1:0",
   "model_name": "us.stability.stable-style-transfer-v1:0",
   "display_name": "us.stability.stable-style-transfer-v1:0",
   "vendor": "stability",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.08"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "us.stability.stable-style-transfer-v1:0"
    }
   ]
  },
  {
   "slug": "stepfun/fireworks/models/step-3p7-flash-nvfp4",
   "model_name": "fireworks/models/step-3p7-flash-nvfp4",
   "display_name": "Step-3.7-Flash-NVFP4",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/step-3p7-flash-nvfp4"
    }
   ],
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/step-3p7-flash-nvfp4"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step-3.7-Flash-NVFP4"
    }
   ]
  },
  {
   "slug": "stepfun/gelab-zero-4b-preview",
   "model_name": "gelab-zero-4b-preview",
   "display_name": "Stepfun-Ai/Gelab Zero 4b Preview",
   "vendor": "stepfun",
   "pricing": [],
   "intro": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
   "released_at": "2025-12-23",
   "max_input_tokens": 8192,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "stepfun-ai/gelab-zero-4b-preview"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Stepfun-Ai/Gelab Zero 4b Preview"
    }
   ]
  },
  {
   "slug": "stepfun/step-1-128k",
   "model_name": "step-1-128k",
   "display_name": "Step 1 128K",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.882353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "29.411765"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "在性能与成本之间取得平衡，适用于通用场景。",
    "zh-TW": "在效能與成本之間取得平衡，適用於一般場景。",
    "ja-JP": "一般的なシナリオにおいて、性能とコストのバランスを実現します。",
    "ru-RU": "Оптимальный баланс между производительностью и стоимостью для общих сценариев."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1 128K"
    }
   ]
  },
  {
   "slug": "stepfun/step-1-256k",
   "model_name": "step-1-256k",
   "display_name": "Step 1 256K",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2.794118"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13.970588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "44.117647"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "13.970588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "44.117647"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "支持超长上下文，适合长文档分析。",
    "zh-TW": "支援超長上下文，適合長文檔分析。",
    "ja-JP": "超長文コンテキスト処理に対応し、長文ドキュメントの分析に最適です。",
    "ru-RU": "Обработка сверхдлинного контекста, идеально подходит для анализа длинных документов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1 256K"
    }
   ]
  },
  {
   "slug": "stepfun/step-1-32k",
   "model_name": "step-1-32k",
   "display_name": "Step 1 (32K)",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.59"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.294118"
      }
     }
    },
    {
     "provider": "stepfun-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.59"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.41"
      }
     }
    }
   ],
   "intro": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "web_search": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "支持中等长度对话，适用于多种场景。",
    "zh-TW": "支援中等長度對話，適用於多種場景。",
    "ja-JP": "中程度の長さの会話を幅広いシナリオでサポートします。",
    "ru-RU": "Поддержка диалогов средней длины для широкого круга задач."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "stepfun/step-1-8k",
   "model_name": "step-1-8k",
   "display_name": "Step 1 8K",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "小型模型，适合轻量级任务。",
    "zh-TW": "小型模型，適合輕量任務。",
    "ja-JP": "軽量なタスクに適した小型モデルです。",
    "ru-RU": "Небольшая модель, подходящая для легких задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1 8K"
    }
   ]
  },
  {
   "slug": "stepfun/step-1-flash",
   "model_name": "step-1-flash",
   "display_name": "Step 1 Flash",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "高速模型，适用于实时聊天场景。",
    "zh-TW": "高速模型，適合即時聊天應用。",
    "ja-JP": "リアルタイムチャットに適した高速モデルです。",
    "ru-RU": "Высокоскоростная модель, подходящая для общения в реальном времени."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1 Flash"
    }
   ]
  },
  {
   "slug": "stepfun/step-1.5v-mini",
   "model_name": "step-1.5v-mini",
   "display_name": "Step 1.5V Mini",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.147059"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "具备强大视频理解能力。",
    "zh-TW": "具備強大影片理解能力。",
    "ja-JP": "高度な動画理解能力を備えています。",
    "ru-RU": "Мощные возможности понимания видео."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1.5V Mini"
    }
   ]
  },
  {
   "slug": "stepfun/step-1o-turbo-vision",
   "model_name": "step-1o-turbo-vision",
   "display_name": "Step 1o Turbo Vision",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "released_at": "2025-02-14",
   "max_input_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "video_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "图像理解能力强，在数学与编程方面优于 1o。体积更小，输出更快。",
    "zh-TW": "具備強大圖像理解能力，在數學與程式碼任務上超越 1o。體積更小，輸出更快。",
    "ja-JP": "画像理解に優れ、数学やコーディングで 1o を上回る性能を発揮します。1o より小型で出力も高速です。",
    "ru-RU": "Продвинутое понимание изображений, превосходит 1o в математике и программировании. Меньше по размеру и быстрее по скорости вывода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1o Turbo Vision"
    }
   ]
  },
  {
   "slug": "stepfun/step-1o-vision-32k",
   "model_name": "step-1o-vision-32k",
   "display_name": "Step 1o Vision 32K",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      }
     }
    }
   ],
   "released_at": "2025-01-22",
   "max_input_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "图像理解能力强，视觉表现优于 Step-1V 系列。",
    "zh-TW": "具備強大圖像理解能力，視覺表現優於 Step-1V 系列。",
    "ja-JP": "Step-1V シリーズよりも優れた視覚性能を持つ画像理解モデルです。",
    "ru-RU": "Продвинутое понимание изображений с лучшей визуальной производительностью, чем серия Step-1V."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1o Vision 32K"
    }
   ]
  },
  {
   "slug": "stepfun/step-1v-32k",
   "model_name": "step-1v-32k",
   "display_name": "Step 1V 32K",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.294118"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "web_search": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "支持视觉输入，实现更丰富的多模态交互。",
    "zh-TW": "支援視覺輸入，實現更豐富的多模態互動。",
    "ja-JP": "視覚入力に対応し、より豊かなマルチモーダル対話を実現します。",
    "ru-RU": "Поддержка визуального ввода для более насыщенного мультимодального взаимодействия."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1V 32K"
    }
   ]
  },
  {
   "slug": "stepfun/step-1v-8k",
   "model_name": "step-1v-8k",
   "display_name": "Step 1V 8K",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.941176"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "web_search": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "小型视觉模型，适用于基础图文任务。",
    "zh-TW": "小型視覺模型，適用於基本圖文任務。",
    "ja-JP": "基本的な画像とテキストのタスクに対応する小型ビジョンモデルです。",
    "ru-RU": "Небольшая визуальная модель для базовых задач с изображениями и текстом."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1V 8K"
    }
   ]
  },
  {
   "slug": "stepfun/step-1x-edit",
   "model_name": "step-1x-edit",
   "display_name": "Step 1X Edit",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2025-03-04",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "专注于图像编辑的模型，可根据用户提供的图像与文本进行修改与增强。支持多种输入格式，包括文本描述与示例图像，生成符合用户意图的编辑结果。",
    "zh-TW": "此模型專注於圖像編輯，可根據使用者提供的圖像與文字進行修改與增強。支援多種輸入格式，包括文字描述與範例圖像，並生成符合使用者意圖的編輯結果。",
    "ja-JP": "このモデルは画像編集に特化しており、ユーザーが提供した画像やテキストに基づいて画像を修正・強化します。テキスト説明や例示画像など複数の入力形式に対応し、ユーザーの意図に沿った編集を生成します。",
    "ru-RU": "Модель для редактирования изображений, модифицирует и улучшает изображения на основе текста и примеров. Поддерживает различные форматы ввода и генерирует правки в соответствии с намерением пользователя."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1X Edit"
    }
   ]
  },
  {
   "slug": "stepfun/step-1x-medium",
   "model_name": "step-1x-medium",
   "display_name": "Step 1X Medium",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.014706"
      }
     }
    }
   ],
   "released_at": "2025-07-15",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "具备强大图像生成能力，支持中文提示输入，能更好理解中文语义并转化为视觉特征，实现高分辨率、高质量图像生成，并支持一定程度的风格迁移。",
    "zh-TW": "此模型具備強大的文字提示圖像生成能力。原生支援中文，能更好理解中文描述並轉化為視覺特徵，實現更準確的生成。可產出高解析度、高品質圖像，並支援一定程度的風格轉換。",
    "ja-JP": "このモデルはテキストプロンプトによる強力な画像生成を提供します。中国語にネイティブ対応しており、中国語の記述をより正確に理解し、意味を視覚的特徴に変換して高解像度・高品質な画像を生成します。スタイル変換にも一定の対応があります。",
    "ru-RU": "Модель с мощной генерацией изображений по текстовому описанию. Благодаря поддержке китайского языка, лучше понимает и визуализирует китайские описания. Генерирует изображения высокого разрешения и качества, поддерживает перенос стиля."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 1X Medium"
    }
   ]
  },
  {
   "slug": "stepfun/step-2-16k",
   "model_name": "step-2-16k",
   "display_name": "Step 2 (16K)",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.44"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.04"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17.647059"
      }
     }
    },
    {
     "provider": "stepfun-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.44"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.04"
      }
     }
    }
   ],
   "intro": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
   "released_at": "2025-01-01",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 16384,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "web_search": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "支持大上下文交互，适用于复杂对话。",
    "zh-TW": "支援大上下文互動，適合複雜對話場景。",
    "ja-JP": "複雑な対話に対応する大規模コンテキスト処理をサポートします。",
    "ru-RU": "Поддержка взаимодействия с большим контекстом для сложных диалогов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "stepfun/step-2-16k-exp",
   "model_name": "step-2-16k-exp",
   "display_name": "Step 2 16K Exp",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.117647"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17.647059"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.004"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "19.992"
      }
     }
    }
   ],
   "released_at": "2025-01-15",
   "max_input_tokens": 16000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Step-2 实验版本，包含最新功能与持续更新。不建议用于生产环境。",
    "zh-TW": "Step-2 實驗版本，具備最新功能與持續更新。不建議用於生產環境。",
    "ja-JP": "最新機能と継続的なアップデートを備えた Step-2 の実験的ビルドです。本番環境での使用は推奨されません。",
    "ru-RU": "Экспериментальная сборка Step-2 с новейшими функциями и обновлениями. Не рекомендуется для продакшена."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 2 16K Exp"
    }
   ]
  },
  {
   "slug": "stepfun/step-2-mini",
   "model_name": "step-2-mini",
   "display_name": "Step 2 Mini",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.408"
      }
     }
    }
   ],
   "released_at": "2025-01-14",
   "max_input_tokens": 8000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "基于下一代自研 MFA 注意力架构构建，在大幅降低成本的同时实现 Step-1 级别效果，具备更高吞吐与更低延迟，适用于通用任务，编程能力强。",
    "zh-TW": "基於新一代自研 MFA 注意力架構，提供類似 Step-1 的效能，成本更低、吞吐更高、延遲更低。具備強大程式能力，適用於通用任務。",
    "ja-JP": "次世代の社内開発 MFA アテンションアーキテクチャに基づき、Step-1 に近い性能を大幅に低コストで実現し、高スループットと低レイテンシを達成します。一般的なタスクに対応し、コーディング能力にも優れています。",
    "ru-RU": "Построена на архитектуре MFA следующего поколения, обеспечивает производительность уровня Step-1 при значительно меньших затратах, с высокой пропускной способностью и низкой задержкой. Отлично справляется с общими задачами и программированием."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 2 Mini"
    }
   ]
  },
  {
   "slug": "stepfun/step-2x-large",
   "model_name": "step-2x-large",
   "display_name": "Step 2X Large",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2024-08-07",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "新一代 StepFun 图像模型，专注于图像生成，可根据文本提示生成高质量图像，具备更真实的纹理与更强的中英文文本渲染能力。",
    "zh-TW": "新一代 StepFun 圖像模型，專注於文字提示圖像生成，能產出高品質圖像，具備更真實的質感與更強的中英文文字渲染能力。",
    "ja-JP": "StepFun による次世代画像生成モデルで、テキストプロンプトから高品質な画像を生成します。よりリアルな質感と強力な中英テキスト描画能力を備えています。",
    "ru-RU": "Модель нового поколения StepFun для генерации изображений, создает изображения высокого качества по текстовому описанию. Обеспечивает реалистичную текстуру и качественную отрисовку текста на китайском и английском языках."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 2X Large"
    }
   ]
  },
  {
   "slug": "stepfun/step-3",
   "model_name": "step-3",
   "display_name": "Step 3",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     },
     "tracks": [
      {
       "label": ">4000000K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2.666667",
        "prompt": "2.666667",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 4000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2499"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6494"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "stepfun/step-3",
     "tracks": [
      {
       "label": ">4K context",
       "factor": "1",
       "charge_factors": {
        "completion": "2.491228",
        "prompt": "2.714286"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 4000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 64000,
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true,
    "stream": true
   },
   "intro": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
   "released_at": "2025-07-31",
   "knowledge_cutoff": "2025-01",
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "stepfun/step-3"
   ],
   "intro_i18n": {
    "zh-CN": "该模型具备强大的视觉感知与复杂推理能力，能准确处理跨领域知识理解、数学与视觉交叉分析及多种日常视觉分析任务。",
    "zh-TW": "此模型具備強大的視覺感知與複雜推理能力，能準確處理跨領域知識理解、數學與視覺交叉分析，以及多種日常視覺分析任務。",
    "ja-JP": "このモデルは優れた視覚認識と複雑な推論能力を持ち、分野横断的な知識理解、数学と視覚の複合分析、日常的な視覚分析タスクに正確に対応します。",
    "ru-RU": "Модель с мощным визуальным восприятием и сложным логическим выводом, точно обрабатывает знания из разных областей, анализ математики и изображений, а также широкий спектр повседневных визуальных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step 3"
    }
   ]
  },
  {
   "slug": "stepfun/step-3.5-flash",
   "model_name": "step-3.5-flash",
   "display_name": "Step 3.5 Flash",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.33"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+computeprices",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "stepfun-ai/Step-3.5-Flash"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "stepfun-ai/Step-3.5-Flash"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "stepfun/step-3.5-flash"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "stepfun/step-3.5-flash"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "stepfun-ai/step-3.5-flash"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "stepfun-ai/step-3.5-flash"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "stepfun/step-3.5-flash"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.096"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.288"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.019"
      }
     },
     "provider_model_id": "route/step-3.5-flash"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "stepfun-ai/Step-3.5-Flash"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "stepfun-ai/Step-3.5-Flash"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "stepfun-ai/Step-3.5-Flash"
    },
    {
     "provider": "stepfun-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29999999999999993"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.019999999999999997"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "stepfun/step-3.5-flash"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "stepfun/step-3.5-flash"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "stepfun/step-3.5-flash"
    }
   ],
   "intro": "StepFun flash lane for quick multimodal reasoning and coding assistance",
   "released_at": "2026-01-29",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "family": "step",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "route/step-3.5-flash",
    "step-3-5-flash",
    "stepfun-ai/Step-3.5-Flash",
    "stepfun-ai/step-3.5-flash",
    "stepfun/step-3.5-flash",
    "stepfun/step-3.5-flash:free"
   ],
   "intro_i18n": {
    "zh-CN": "Stepfun 的旗舰语言推理模型。该模型具备顶级的推理能力和快速可靠的执行能力。能够分解和规划复杂任务，快速可靠地调用工具执行任务，并胜任逻辑推理、数学、软件工程和深入研究等各种复杂任务。",
    "zh-TW": "Stepfun 的旗艦語言推理模型。該模型具備頂級推理能力及快速可靠的執行能力。能分解並規劃複雜任務，快速可靠地調用工具執行任務，並勝任邏輯推理、數學、軟件工程及深入研究等各種複雜任務。",
    "ja-JP": "Stepfunのフラッグシップ言語推論モデル。このモデルは、トップクラスの推論能力と迅速かつ信頼性の高い実行能力を備えています。複雑なタスクを分解して計画し、ツールを迅速かつ確実に呼び出してタスクを実行し、論理推論、数学、ソフトウェアエンジニアリング、深い研究などのさまざまな複雑なタスクに対応できます。",
    "ru-RU": "Флагманская модель языкового рассуждения от Stepfun. Эта модель обладает первоклассными возможностями рассуждения и быстрой и надёжной способностью выполнения задач. Она способна разбирать и планировать сложные задачи, быстро и надёжно вызывать инструменты для выполнения задач, а также справляться с различными сложными задачами, такими как логическое рассуждение, математика, разработка программного обеспечения и углублённые исследования."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "stepfun/step-3.5-flash-2603",
   "model_name": "step-3.5-flash-2603",
   "display_name": "Step 3.5 Flash 2603",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "stepfun/step-3.5-flash-2603"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "stepfun-ai/step-3.5-flash-2603"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "route/step-3.5-flash-2603"
    },
    {
     "provider": "stepfun-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    }
   ],
   "intro": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
   "released_at": "2026-04-02",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "web_search": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "route/step-3.5-flash-2603",
    "stepfun-ai/step-3.5-flash-2603",
    "stepfun/step-3.5-flash-2603"
   ],
   "intro_i18n": {
    "zh-CN": "基于 Step 3.5 Flash 打造，并针对高频 Agent 场景优化，进一步提升 token 效率与推理速度，同时保留旗舰级推理与工具调用能力。支持切换至低推理模式以降低资源消耗，并对编码任务与 Agent 框架进行专项优化。",
    "zh-TW": "基於 Step 3.5 Flash 打造並針對高頻代理場景優化，進一步提升 token 效率與推理速度，同時保留旗艦級推理與工具調用能力。也支援切換至低推理模式以降低資源消耗，並針對程式任務與代理框架進行相容性優化。",
    "ja-JP": "Step 3.5 Flashを基盤とし、高頻度エージェントシナリオ向けに最適化されており、トークン効率と推論速度をさらに向上させています。フラッグシップレベルの推論とツール呼び出し能力を維持しながら、リソース消費を削減するために低推論モードへの切り替えをサポートします。また、コーディングタスクとエージェントフレームワークとの互換性を向上させるためのターゲット最適化が行われています。",
    "ru-RU": "Создана на базе Step 3.5 Flash и оптимизирована для высокочастотных агентных сценариев. Улучшает эффективность токенов и скорость инференции, сохраняя флагманский уровень рассуждений и вызова инструментов. Поддерживает переключение в режим с низким уровнем рассуждений для снижения расходов. Также добавлены оптимизации для повышения совместимости с задачами программирования и агентными фреймворками."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "stepfun/step-3.7-flash",
   "model_name": "step-3.7-flash",
   "display_name": "Step 3.7 Flash",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.32"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.044"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "stepfun-ai/Step-3.7-Flash"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "stepfun-ai/Step-3.7-Flash"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "stepfun/step-3.7-flash"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "stepfun/step-3.7-flash"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "stepfun/step-3.7-flash:thinking"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     },
     "provider_model_id": "stepfun/step-3.7-flash"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "stepfun-ai/step-3.7-flash"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "stepfun/step-3.7-flash"
    },
    {
     "provider": "stepfun-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1499999999999997"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.039999999999999994"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "stepfun/step-3.7-flash"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "provider_model_id": "stepfun/step-3.7-flash"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02700708"
      }
     },
     "provider_model_id": "stepfun/step-3.7-flash"
    }
   ],
   "intro": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
   "released_at": "2026-05-29",
   "knowledge_cutoff": "2026-01",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "family": "step",
   "benchmarks": {
    "intelligence_index": 29.7,
    "coding_index": 37.3,
    "agentic_index": 21.5
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "step-3-7-flash",
    "stepfun-ai/Step-3.7-Flash",
    "stepfun-ai/step-3.7-flash",
    "stepfun/step-3.7-flash",
    "stepfun/step-3.7-flash-free",
    "stepfun/step-3.7-flash:thinking"
   ],
   "intro_i18n": {
    "zh-CN": "StepFun的旗舰多模态推理模型。基于step-3.5-flash的高速推理和工具调用能力，增加了原生多模态输入支持，能够直接理解图像和视频内容，无需依赖视觉MCP或额外的视觉模型。该模型支持三种推理级别（低/中/高），是代理工作流、编码任务和多模态应用的快速可靠选择。",
    "zh-TW": "StepFun 的旗艦多模態推理模型。基於 step-3.5-flash 的高速推理和工具調用能力，增加了原生多模態輸入支持，能直接理解影像和視頻內容，而無需依賴視覺 MCP 或額外的視覺模型。該模型支持三種推理級別（低/中/高），是代理工作流、編程任務和多模態應用的快速可靠選擇。",
    "ja-JP": "StepFunのフラッグシップマルチモーダル推論モデルです。step-3.5-flashの高速推論およびツール呼び出し機能を基盤に、ネイティブなマルチモーダル入力サポートを追加し、視覚MCPや追加のビジョンモデルに依存せずに画像や動画コンテンツを直接理解できます。このモデルは3つの推論レベル（低/中/高）をサポートし、エージェントワークフロー、コーディングタスク、マルチモーダルアプリケーションにおいて迅速かつ信頼性の高い選択肢です。",
    "ru-RU": "Флагманская мультимодальная модель рассуждений от StepFun. Основываясь на высокоскоростных возможностях рассуждений и вызова инструментов step-3.5-flash, она добавляет поддержку нативного мультимодального ввода, позволяя напрямую понимать изображения и видео без использования визуальных MCP или дополнительных моделей визуализации. Модель поддерживает три уровня рассуждений (низкий / средний / высокий), что делает её быстрым и надёжным выбором для агентных рабочих процессов, задач кодирования и мультимодальных приложений."
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "aihubmix",
     "charge": "cache_read",
     "old": "0.0044",
     "new": "0.044"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "aihubmix",
     "charge": "completion",
     "old": "0.132",
     "new": "1.32"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "aihubmix",
     "charge": "prompt",
     "old": "0.022",
     "new": "0.22"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "stepfun/step-image-edit-2",
   "model_name": "step-image-edit-2",
   "display_name": "Step Image Edit 2",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.002941"
      }
     }
    }
   ],
   "released_at": "2026-04-28",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Stepfun 最新迭代的轻量级编辑模型，支持文本生成图像和图像编辑于一体。尽管参数少于 60 亿，但在其规模内实现了最先进的性能，可与 120 亿至 200 亿参数范围的开源模型相媲美。每个编辑任务仅需 1-2 秒，重新定义了实时交互式图像编辑体验。",
    "zh-TW": "Stepfun 最新迭代推出的輕量級編輯模型，支持文本生成圖像和圖像編輯，集成於單一模型中。儘管參數少於 60 億，但在其規模內實現了最先進的性能，與 12B–20B 參數範圍的開源模型相媲美。每個編輯任務僅需 1–2 秒，重新定義了實時交互式圖像編輯的體驗。",
    "ja-JP": "Stepfunの最新バージョンからの軽量編集モデルで、単一モデル内でテキストから画像生成と画像編集の両方をサポートします。6億未満のパラメータでありながら、12B〜20Bパラメータ範囲のオープンソースモデルに匹敵する性能を達成し、各編集タスクはわずか1〜2秒で完了します。リアルタイムのインタラクティブ画像編集体験を再定義します。",
    "ru-RU": "Легковесная модель редактирования от последней итерации Stepfun, поддерживающая как генерацию изображений по тексту, так и редактирование изображений в рамках одной модели. Несмотря на менее чем 6 миллиардов параметров, она достигает передовых результатов на своем уровне, соперничая с открытыми моделями в диапазоне 12–20 миллиардов параметров. Каждая задача редактирования занимает всего 1–2 секунды, переопределяя опыт интерактивного редактирования изображений в реальном времени."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step Image Edit 2"
    }
   ]
  },
  {
   "slug": "stepfun/step-r1-v-mini",
   "model_name": "step-r1-v-mini",
   "display_name": "Step R1 V Mini",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "stepfun",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.367647"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "11"
      }
     }
    }
   ],
   "max_input_tokens": 100000,
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true,
    "vision": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-04-08",
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "具备强图像理解能力的推理模型，可处理图像与文本，并在深度推理后生成文本。擅长视觉推理，在数学、编程与文本推理方面表现出色，支持 100K 上下文窗口。",
    "zh-TW": "具備強大圖像理解能力的推理模型，能處理圖像與文字，並在深度推理後生成文字。擅長視覺推理，在數學、程式碼與文字推理方面表現頂尖，支援 100K 上下文。",
    "ja-JP": "画像理解に優れた推論モデルで、画像とテキストを処理し、深い推論を経てテキストを生成します。視覚的推論に強く、数学、コーディング、テキスト推論において最高水準の性能を発揮し、100K のコンテキストウィンドウに対応します。",
    "ru-RU": "Модель логического вывода с продвинутым пониманием изображений, способна обрабатывать изображения и текст, а затем генерировать текст после глубокого анализа. Отлично справляется с визуальной логикой, математикой, программированием и текстовыми задачами, поддерживает контекст до 100K."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Step R1 V Mini"
    }
   ]
  },
  {
   "slug": "stepfun/step3",
   "model_name": "step3",
   "display_name": "stepfun-ai/step3",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     },
     "provider_model_id": "stepfun-ai/step3"
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "stepfun-ai/step3"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "stepfun-ai/step3"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-3.5-flash",
   "model_name": "stepfun-3.5-flash",
   "display_name": "StepFun 3.5 Flash",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.096"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.288"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.019"
      }
     },
     "provider_model_id": "route/stepfun-3.5-flash"
    }
   ],
   "intro": "StepFun flash lane for quick multimodal reasoning and coding assistance",
   "released_at": "2026-01-29",
   "knowledge_cutoff": "2025-01",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "route/stepfun-3.5-flash"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "StepFun 3.5 Flash"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-step-1o-vision-32k",
   "model_name": "stepfun-step-1o-vision-32k",
   "display_name": "step-1o-vision-32k",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2025-01-22",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "step-1o-vision-32k"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-step-1v-32k",
   "model_name": "stepfun-step-1v-32k",
   "display_name": "step-1v-32k",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2025-08-08",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "step-1v-32k"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-step-1v-8k",
   "model_name": "stepfun-step-1v-8k",
   "display_name": "step-1v-8k",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.86"
      }
     }
    }
   ],
   "released_at": "2024-03-01",
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "step-1v-8k"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-step-2-16k",
   "model_name": "stepfun-step-2-16k",
   "display_name": "step-2-16k",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17"
      }
     }
    }
   ],
   "released_at": "2024-07-01",
   "max_input_tokens": 16000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "step-2-16k"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-step-2-16k-exp",
   "model_name": "stepfun-step-2-16k-exp",
   "display_name": "step-2-16k-exp",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "17"
      }
     }
    }
   ],
   "released_at": "2025-01-16",
   "max_input_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "step-2-16k-exp"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-step-2-mini",
   "model_name": "stepfun-step-2-mini",
   "display_name": "step-2-mini",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     }
    }
   ],
   "released_at": "2025-01-16",
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "step-2-mini"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-step-3",
   "model_name": "stepfun-step-3",
   "display_name": "step-3",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2142"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5715"
      }
     }
    }
   ],
   "released_at": "2025-07-31",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "step-3"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-step-3-5-flash",
   "model_name": "stepfun-step-3-5-flash",
   "display_name": "step-3.5-flash",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2026-02-02",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "step-3.5-flash"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-step-3-7-flash",
   "model_name": "stepfun-step-3-7-flash",
   "display_name": "step-3.7-flash",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.15"
      }
     }
    }
   ],
   "released_at": "2026-05-30",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "step-3.7-flash"
    }
   ]
  },
  {
   "slug": "stepfun/stepfun-step-r1-v-mini",
   "model_name": "stepfun-step-r1-v-mini",
   "display_name": "step-r1-v-mini",
   "vendor": "stepfun",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2025-04-08",
   "max_input_tokens": 100000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "step-r1-v-mini"
    }
   ]
  },
  {
   "slug": "suno/suno-v4.5",
   "model_name": "suno-v4.5",
   "display_name": "suno-v4.5",
   "vendor": "suno",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "music_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "suno-v4.5"
    }
   ]
  },
  {
   "slug": "suno/suno-v5",
   "model_name": "suno-v5",
   "display_name": "suno-v5",
   "vendor": "suno",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "music_generation",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "suno-v5"
    }
   ]
  },
  {
   "slug": "suno/suno-v5.5",
   "model_name": "suno-v5.5",
   "display_name": "suno-v5.5",
   "vendor": "suno",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "music_generation",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "listed",
     "note": "suno-v5.5"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-2.0-instruct-20251111",
   "model_name": "hunyuan-2.0-instruct-20251111",
   "display_name": "Tencent HY 2.0 Instruct",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.467647"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.6625"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "1.169118"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.636765"
      }
     }
    },
    {
     "provider": "tencent-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "hunyuan-2.0-instruct"
    }
   ],
   "intro": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
   "released_at": "2026-03-08",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "hunyuan",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "web_search": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hunyuan-2.0-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "模型基础全面升级，核心能力更加稳健。在知识、数学、写作和推理方面达到顶尖水平，并在指令跟随、多轮对话和长上下文理解方面表现出色。",
    "zh-TW": "模型底座全面升級，核心能力更強。在知識、數學、寫作與推理方面達到頂尖水準，並在指令遵循、多輪互動與長上下文理解上展現卓越表現。",
    "ja-JP": "モデル基盤が包括的にアップグレードされ、より堅牢なコア能力を備えています。知識、数学、執筆、推論においてトップクラスの性能を達成しています。また、指示の追従、マルチターンの対話、長いコンテキストの理解において優れた性能を示しています。",
    "ru-RU": "Основа модели была всесторонне обновлена, обеспечивая более устойчивые базовые способности. Достигнут высочайший уровень в областях знаний, математики, письма и рассуждений. Модель также демонстрирует отличные результаты в следовании инструкциям, многотуровом взаимодействии и понимании длинного контекста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Tencent HY 2.0 Instruct"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-2.0-thinking-20251109",
   "model_name": "hunyuan-2.0-thinking-20251109",
   "display_name": "Tencent HY 2.0 Think",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.584559"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.779412"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.338235"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "3.117647"
      }
     }
    },
    {
     "provider": "tencent-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "hunyuan-2.0-thinking"
    }
   ],
   "intro": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
   "released_at": "2026-03-08",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "hunyuan",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hunyuan-2.0-thinking"
   ],
   "intro_i18n": {
    "zh-CN": "专注生成创意内容、多轮交互与实用指令跟随任务。在数学、编码与 Agent 任务上有显著提升。",
    "zh-TW": "專精創意內容、多輪互動與實用指令場景，在數學、程式與代理任務方面有顯著提升。",
    "ja-JP": "創造的なコンテンツ、マルチターンの対話、実用的な指示追従シナリオに特化しています。数学、コーディング、エージェントベースのタスクにおいて能力が大幅に向上しています。",
    "ru-RU": "Специализирована для творческого контента, многотуровых диалогов и практических сценариев следования инструкциям. Значительно улучшены способности в математике, программировании и агентных задачах."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Tencent HY 2.0 Think"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-a13b",
   "model_name": "hunyuan-a13b",
   "display_name": "Hunyuan A13B",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "family": "Hunyuan",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan A13B"
    }
   ]
  },
  {
   "slug": "tencent/Hunyuan-A13B-Instruct",
   "model_name": "Hunyuan-A13B-Instruct",
   "display_name": "tencent/Hunyuan-A13B-Instruct",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      }
     },
     "provider_model_id": "tencent/Hunyuan-A13B-Instruct"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "tencent/hunyuan-a13b-instruct"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "tencent/hunyuan-a13b-instruct"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "tencent/Hunyuan-A13B-Instruct"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     },
     "provider_model_id": "tencent/Hunyuan-A13B-Instruct"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "tencent/Hunyuan-A13B-Instruct"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "tencent/Hunyuan-A13B-Instruct"
    }
   ],
   "intro": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
   "released_at": "2025-06-30",
   "max_input_tokens": 131000,
   "max_output_tokens": 131000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "hunyuan",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "knowledge_cutoff": "2025-03",
   "deprecated": true,
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "structured_outputs",
     "temperature",
     "top_k",
     "top_p"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hunyuan-a13b-instruct",
    "hunyuan-a13b-instruct:free",
    "tencent/Hunyuan-A13B-Instruct",
    "tencent/hunyuan-a13b-instruct"
   ],
   "intro_i18n": {
    "zh-CN": "混元-A13B-Instruct 总参数 80B，激活参数 13B，性能媲美更大模型。支持快慢混合推理、稳定长文本理解，在 BFCL-v3 与 τ-Bench 上具备领先代理能力。支持 GQA 与多量化格式，推理高效。",
    "zh-TW": "Hunyuan-A13B-Instruct 採用總參數量 80B、啟用參數 13B 的架構，媲美更大型模型。支援快慢混合推理、穩定的長文本理解，並在 BFCL-v3 與 τ-Bench 上展現領先代理能力。GQA 與多量化格式實現高效推理。",
    "ja-JP": "Hunyuan-A13B-Instruct は、総パラメータ数 80B、アクティブパラメータ数 13B で大型モデルに匹敵する性能を発揮します。高速・低速のハイブリッド推論、安定した長文理解、BFCL-v3 や τ-Bench における先進的なエージェント能力を備えています。GQA とマルチ量子化形式により効率的な推論が可能です。",
    "ru-RU": "Hunyuan-A13B-Instruct использует 80 миллиардов параметров, из которых активно 13 миллиардов, обеспечивая производительность, сопоставимую с более крупными моделями. Поддерживает гибридное быстрое/медленное рассуждение, стабильное понимание длинных текстов и лидирующие возможности агентов на BFCL-v3 и τ-Bench. Поддержка GQA и мульти-квантованных форматов обеспечивает эффективный вывод."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "tencent/Hunyuan-A13B-Instruct"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-code",
   "model_name": "hunyuan-code",
   "display_name": "Hunyuan Code",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2024-04-24",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "混元最新代码模型，基于200B高质量代码数据和六个月的SFT数据训练，支持8K上下文。在自动代码基准测试和五种语言的专家人工评估中排名靠前。",
    "zh-TW": "Hunyuan 最新的代碼模型，基於 200B 高質量代碼數據和六個月的 SFT 數據訓練，支持 8K 上下文。在自動化代碼基準測試和五種語言的專家人工評估中排名靠前。",
    "ja-JP": "Hunyuanの最新コードモデルは、200Bの高品質コードデータと6か月のSFTデータでトレーニングされ、8Kコンテキストを備えています。自動コードベンチマークおよび5つの言語における専門家の人間評価で上位にランクされています。",
    "ru-RU": "Последняя модель кода Hunyuan, обученная на 200B высококачественных данных кода плюс шесть месяцев данных SFT, с контекстом 8K. Она занимает лидирующие позиции в автоматизированных тестах кода и экспертных оценках на пяти языках."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan Code"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-functioncall",
   "model_name": "hunyuan-functioncall",
   "display_name": "Hunyuan FunctionCall",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "released_at": "2025-08-08",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "混元最新专家混合工具调用模型，基于高质量工具调用数据训练，支持32K上下文窗口，在各维度基准测试中表现领先。",
    "zh-TW": "Hunyuan 最新的 MoE FunctionCall 模型，基於高質量工具調用數據訓練，支持 32K 上下文窗口，在多維度基準測試中表現領先。",
    "ja-JP": "Hunyuanの最新MoE FunctionCallモデルは、高品質なツール呼び出しデータでトレーニングされ、32Kコンテキストウィンドウを備え、さまざまな次元でのベンチマークでリードしています。",
    "ru-RU": "Последняя модель MoE FunctionCall от Hunyuan, обученная на высококачественных данных вызова инструментов, с окном контекста 32K и ведущими показателями по различным измерениям."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan FunctionCall"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-lite",
   "model_name": "hunyuan-lite",
   "display_name": "Hunyuan Lite",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 6000,
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2024-04-24",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "升级为 MoE 架构，具备 256K 上下文窗口，在 NLP、代码、数学及各类领域基准上领先众多开源模型。",
    "zh-TW": "升級為 MoE 架構並具備 256K 上下文，在 NLP、程式、數學與多領域基準中領先多款開源模型。",
    "ja-JP": "256Kコンテキストウィンドウを備えたMoEアーキテクチャにアップグレードされ、NLP、コード、数学、ドメインベンチマークで多くのオープンソースモデルをリードしています。",
    "ru-RU": "Обновлена до архитектуры MoE с контекстом 256K, превосходя многие открытые модели в областях NLP, программирования, математики и специализированных бенчмарков."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan Lite"
    }
   ]
  },
  {
   "slug": "tencent/Hunyuan-MT-7B",
   "model_name": "Hunyuan-MT-7B",
   "display_name": "Hunyuan MT 7B",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "tencent/Hunyuan-MT-7B"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "20"
      }
     },
     "provider_model_id": "tencent/Hunyuan-MT-7B"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "tencent/Hunyuan-MT-7B"
    }
   ],
   "intro": "Translation model for multilingual conversion, localization, and cross-language workflows",
   "released_at": "2025-09-18",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "hunyuan",
   "capabilities": {},
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "tencent/Hunyuan-MT-7B"
   ],
   "intro_i18n": {
    "zh-CN": "混元翻译模型包括 Hunyuan-MT-7B 与集成模型 Hunyuan-MT-Chimera。Hunyuan-MT-7B 是一款支持 33 种语言及 5 种中国少数民族语言的 7B 轻量翻译模型，在 WMT25 中 31 个语对中获得 30 个第一。腾讯混元采用从预训练到 SFT、翻译 RL 与集成 RL 的完整训练流程，在同等规模下实现领先性能，部署高效便捷。",
    "zh-TW": "混元翻譯模型包含 Hunyuan-MT-7B 與集成模型 Hunyuan-MT-Chimera。Hunyuan-MT-7B 是一款輕量級 7B 翻譯模型，支援 33 種語言及 5 種中國少數民族語言。在 WMT25 中於 31 組語言對中獲得 30 項第一名。騰訊混元採用完整訓練流程，從預訓練到 SFT、翻譯強化學習與集成強化學習，在同級模型中表現領先，部署高效便捷。",
    "ja-JP": "Hunyuan 翻訳モデルには Hunyuan-MT-7B とアンサンブルモデル Hunyuan-MT-Chimera が含まれます。Hunyuan-MT-7B は 7B の軽量翻訳モデルで、33 言語と中国の少数民族言語 5 言語に対応します。WMT25 では 31 言語ペア中 30 件で 1 位を獲得しました。Tencent Hunyuan は、事前学習から SFT、翻訳 RL、アンサンブル RL までの完全なトレーニングパイプラインを採用し、同規模で最高水準の性能と効率的なデプロイを実現しています。",
    "ru-RU": "Модель перевода Hunyuan включает Hunyuan-MT-7B и ансамбль Hunyuan-MT-Chimera. Hunyuan-MT-7B — это легковесная модель на 7 миллиардов параметров, поддерживающая 33 языка и 5 языков китайских меньшинств. На WMT25 заняла первое место в 30 из 31 языковой пары. Tencent Hunyuan использует полный цикл обучения от предобучения до SFT, RL для перевода и ансамблевого RL, достигая выдающейся производительности при компактных размерах и легкости развертывания."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan MT 7B"
    }
   ]
  },
  {
   "slug": "tencent/Hunyuan-MT-Chimera-7B",
   "model_name": "Hunyuan-MT-Chimera-7B",
   "display_name": "Hunyuan-MT-Chimera-7B",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044139396"
      }
     }
    }
   ],
   "released_at": "2025-09-03",
   "max_input_tokens": 32000,
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044160504",
     "new": "0.044139396"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044191182",
     "new": "0.044160504"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044237766",
     "new": "0.044191182"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044246799",
     "new": "0.044237766"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044231136",
     "new": "0.044246799"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044153685",
     "new": "0.044231136"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan-MT-Chimera-7B"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-pro",
   "model_name": "hunyuan-pro",
   "display_name": "Hunyuan Pro",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.3"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "4.411765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "released_at": "2024-04-24",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "万亿参数的 MOE-32K 长上下文模型，在复杂指令与推理、高级数学、函数调用等方面表现强劲，针对多语言翻译、金融、法律和医疗等领域进行了优化。",
    "zh-TW": "兆級參數 MOE-32K 長上下文模型，在複雜指令與推理、高階數學、函數調用方面表現優異，並針對多語翻譯、金融、法律與醫療領域進行優化。",
    "ja-JP": "1 兆パラメータの MOE-32K 長文コンテキストモデルで、ベンチマークをリードし、複雑な指示や推論、高度な数学、関数呼び出しに強く、多言語翻訳、金融、法律、医療分野に最適化されています。",
    "ru-RU": "Модель MoE с триллионом параметров и контекстом 32K, лидирующая в тестах, сильна в сложных инструкциях и рассуждениях, продвинутой математике, вызове функций и оптимизирована для перевода, финансов, права и медицины."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan Pro"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-role",
   "model_name": "hunyuan-role",
   "display_name": "Hunyuan Role",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2025-08-08",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "混元最新角色扮演模型，经过角色扮演数据的正式微调，在角色扮演场景中表现更强。",
    "zh-TW": "Hunyuan 最新的角色扮演模型，經過角色扮演數據的正式微調，在角色扮演場景中提供更強的基礎性能。",
    "ja-JP": "Hunyuanの最新ロールプレイモデルは、ロールプレイデータで正式にファインチューニングされ、ロールプレイシナリオでの基本性能が強化されています。",
    "ru-RU": "Последняя модель ролевой игры Hunyuan, официально дообученная на данных ролевой игры, обеспечивающая более сильную базовую производительность в сценариях ролевой игры."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan Role"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-role-latest",
   "model_name": "hunyuan-role-latest",
   "display_name": "Hunyuan-role",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.352941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.411765"
      }
     }
    }
   ],
   "released_at": "2026-03-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 32000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "专为角色扮演场景打造，角色一致性极高，具备自然逼真的人类式表达，故事推进丰富，提供情绪陪伴与互动体验。",
    "zh-TW": "專為角色扮演場景設計，具備高度一致的角色設定與極自然的人類化對話風格，並提供沉浸式敘事推進與情感陪伴體驗。",
    "ja-JP": "ロールプレイングシナリオ向けに設計されており、高度に一貫したキャラクターの整合性と非常に自然で人間らしい会話スタイルを提供します。魅力的な物語の展開と進行、感情的な伴侶性と充足感を提供します。",
    "ru-RU": "Для ролевых сценариев обеспечивает высокую стабильность характера и естественный, человечный стиль общения. Предлагает увлекательное развитие сюжета и эмоциональную сопричастность."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan-role"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-standard",
   "model_name": "hunyuan-standard",
   "display_name": "Hunyuan Standard",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.64"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.72"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.661765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 2000,
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2024-04-24",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "采用改进路由以缓解负载均衡与专家坍缩问题。“大海捞针”长文本任务准确率达 99.9%。MOE-32K 在保持质量与价格平衡的同时，为长文本提供更高性价比。",
    "zh-TW": "採用改良後的路由技術，減輕負載不均與專家塌陷問題。長文本「大海撈針」表現達到 99.9%。MOE-32K 在品質與成本之間取得良好平衡，適合長文本輸入。",
    "ja-JP": "負荷分散とエキスパート崩壊を軽減するために改良されたルーティングを使用しています。長文の「干し草の中の針」は99.9%に達します。MOE-32Kは、長文入力の品質と価格のバランスを取りながら、より良い価値を提供します。",
    "ru-RU": "Использует улучшенную маршрутизацию для предотвращения дисбаланса нагрузки и деградации экспертов. В задаче «иголка в стоге сена» для длинных текстов достигает 99.9%. MOE-32K предлагает оптимальный баланс между качеством и стоимостью для длинных текстов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan Standard"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-standard-256K",
   "model_name": "hunyuan-standard-256K",
   "display_name": "Hunyuan Standard 256K",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.6"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.823529"
      }
     }
    }
   ],
   "max_input_tokens": 256000,
   "max_output_tokens": 6000,
   "model_type": "text_generation",
   "capabilities": {},
   "released_at": "2025-08-08",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "采用改进路由以缓解负载均衡与专家坍缩问题。“大海捞针”长文本任务准确率达 99.9%。MOE-256K 在长度与质量上进一步增强，大幅扩展输入能力。",
    "zh-TW": "採用改良後的路由技術，減輕負載不均與專家塌陷問題。長文本「大海撈針」表現達到 99.9%。MOE-256K 在長度與品質上更進一步，大幅提升輸入上限。",
    "ja-JP": "負荷分散とエキスパート崩壊を軽減するために改良されたルーティングを使用しています。長文の「干し草の中の針」は99.9%に達します。MOE-256Kは、長さと品質をさらに拡張し、入力の長さを大幅に拡大します。",
    "ru-RU": "Использует улучшенную маршрутизацию для предотвращения дисбаланса нагрузки и деградации экспертов. В задаче «иголка в стоге сена» для длинных текстов достигает 99.9%. MOE-256K расширяет предельную длину и качество ввода."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan Standard 256K"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-t1",
   "model_name": "hunyuan-t1",
   "display_name": "Hunyuan-T1",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "hunyuan-t1-20250321"
    },
    {
     "provider": "tencent-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
   "released_at": "2026-03-08",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "hunyuan",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hunyuan-t1-20250321",
    "hunyuan-t1-20250711"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan-T1"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-t1-latest",
   "model_name": "hunyuan-t1-latest",
   "display_name": "hunyuan-t1-latest",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2025-03-22",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "hunyuan-t1-latest"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-turbo",
   "model_name": "hunyuan-turbo",
   "display_name": "Hunyuan Turbo",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.352941"
      }
     }
    }
   ],
   "max_input_tokens": 32000,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "混元下一代大模型预览版，采用全新 MoE 架构，推理速度更快，性能超越 hunyuan-pro。",
    "zh-TW": "混元下一代大型語言模型預覽版，採用全新 MoE 架構，推理速度更快，整體表現超越 hunyuan-pro。",
    "ja-JP": "Hunyuanの次世代LLMのプレビュー版で、新しいMoEアーキテクチャを採用し、hunyuan-proよりも高速な推論と強力な成果を提供します。",
    "ru-RU": "Предварительная версия LLM нового поколения от Hunyuan с новой архитектурой MoE, обеспечивающая более быстрое рассуждение и лучшие результаты, чем hunyuan-pro."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan Turbo"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-turbos",
   "model_name": "hunyuan-turbos",
   "display_name": "Hunyuan-TurboS",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "hunyuan-turbos-20250226"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.187"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.374"
      }
     },
     "provider_model_id": "hunyuan-turbos-20250226"
    },
    {
     "provider": "tencent-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
   "released_at": "2026-03-08",
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "hunyuan",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hunyuan-turbos-20250226",
    "hunyuan-turbos-20250716"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan-TurboS"
    }
   ]
  },
  {
   "slug": "tencent/hunyuan-vision",
   "model_name": "hunyuan-vision",
   "display_name": "Hunyuan Vision",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "26"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      }
     }
    }
   ],
   "max_input_tokens": 8000,
   "max_output_tokens": 4000,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "image_output": true,
    "pdf_input": true
   },
   "released_at": "2024-04-24",
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "混元最新多模态模型，支持图像+文本输入以生成文本。",
    "zh-TW": "Hunyuan 最新的多模態模型，支持圖像+文本輸入以生成文本。",
    "ja-JP": "Hunyuanの最新マルチモーダルモデルは、画像+テキスト入力をサポートし、テキストを生成します。",
    "ru-RU": "Последняя мультимодальная модель Hunyuan, поддерживающая ввод изображения + текста для генерации текста."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hunyuan Vision"
    }
   ]
  },
  {
   "slug": "tencent/hy-image-lite",
   "model_name": "hy-image-lite",
   "display_name": "HY-Image-Lite",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.014559"
      }
     }
    }
   ],
   "released_at": "2025-09-12",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "采用超高压缩编码器，实现快速图像生成并保持高质量输出。支持电商商品图增强、设计素材生成及游戏场景迭代等场景。",
    "zh-TW": "採用超高壓縮編碼技術，在維持高品質輸出的同時，實現高速影像生成。適用於電商商品圖優化、創意工具的設計素材生成、遊戲場景迭代等場景。",
    "ja-JP": "超高圧縮コーデックを採用し、高品質な出力を維持しながら高速な画像生成を可能にします。eコマース製品画像の強化、クリエイティブツールのデザイン資産生成、ゲームシーンの反復開発などのユースケースをサポートします。",
    "ru-RU": "Использует ультравысокий коэффициент сжатия для быстрой генерации изображений при сохранении высокого качества. Поддерживает создание улучшенных изображений для e‑commerce, генерацию дизайна и разработку игровых сцен."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HY-Image-Lite"
    }
   ]
  },
  {
   "slug": "tencent/hy-image-v3.0",
   "model_name": "hy-image-v3.0",
   "display_name": "HY-Image-V3.0",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.029412"
      }
     }
    }
   ],
   "released_at": "2026-03-10",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "基于混元大模型，能够理解图像布局、构图、笔触等视觉逻辑，结合世界知识推理常识性视觉场景。可解析复杂长文本语义、生成长篇图文、复杂漫画与表情包，并能创作生动的教育插画。",
    "zh-TW": "基於鴻源大模型，具備影像布局、構圖與筆觸推理能力，能運用世界知識推斷常識性視覺場景。可理解上千字的複雜語意，生成長文本內容、複雜漫畫、迷因，並創作生動的教育插圖。",
    "ja-JP": "Hunyuan大規模モデルに基づいており、画像のレイアウト、構成、筆遣いを推論する能力を備えています。世界知識を使用して常識的な視覚シーンを推測し、数千文字規模の複雑なセマンティクスを解釈し、長文テキストコンテンツ、複雑な漫画、ミーム、教育的なイラストを生成します。",
    "ru-RU": "Основана на большой модели Hunyuan и способна рассуждать о композиции, расположении объектов и стиле изображения, используя мировые знания для понимания естественных визуальных сцен. Также понимает сложные семантические описания объёмом до нескольких тысяч символов, создаёт длинные тексты, комиксы, мемы и наглядные учебные иллюстрации."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HY-Image-V3.0"
    }
   ]
  },
  {
   "slug": "tencent/HY-MT1.5-7B",
   "model_name": "HY-MT1.5-7B",
   "display_name": "HY-MT1.5-7B",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044139396"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 32000,
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044160504",
     "new": "0.044139396"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044191182",
     "new": "0.044160504"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044237766",
     "new": "0.044191182"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044246799",
     "new": "0.044237766"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044231136",
     "new": "0.044246799"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044153685",
     "new": "0.044231136"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HY-MT1.5-7B"
    }
   ]
  },
  {
   "slug": "tencent/Hy-MT2-30B-A3B",
   "model_name": "Hy-MT2-30B-A3B",
   "display_name": "Hy-MT2-30B-A3B",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102991924"
      }
     }
    }
   ],
   "released_at": "2026-05-27",
   "max_input_tokens": 32000,
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103041176",
     "new": "0.102991924"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103112758",
     "new": "0.103041176"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103221454",
     "new": "0.103112758"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103242531",
     "new": "0.103221454"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103205984",
     "new": "0.103242531"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.103025265",
     "new": "0.103205984"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hy-MT2-30B-A3B"
    }
   ]
  },
  {
   "slug": "tencent/HY-MT2-7B",
   "model_name": "HY-MT2-7B",
   "display_name": "HY-MT2-7B",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.044139396"
      }
     }
    }
   ],
   "released_at": "2026-05-27",
   "max_input_tokens": 32000,
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044160504",
     "new": "0.044139396"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044191182",
     "new": "0.044160504"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044237766",
     "new": "0.044191182"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044246799",
     "new": "0.044237766"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044231136",
     "new": "0.044246799"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.044153685",
     "new": "0.044231136"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HY-MT2-7B"
    }
   ]
  },
  {
   "slug": "tencent/hy-video-1.5",
   "model_name": "hy-video-1.5",
   "display_name": "HY-Video-1.5",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.220588"
      }
     }
    }
   ],
   "released_at": "2026-01-06",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "支持文本与图像输入，生成高质量视频，具备镜头切换与多角色互动能力。显著提升内容生产效率并降低成本，适用于企业广告、营销及个人创作。",
    "zh-TW": "支援文本與圖像等多模態輸入，生成高品質影片，可實現場景轉換與多角色互動。能簡化製作流程並降低成本，適用於企業廣告、行銷與個人創作應用。",
    "ja-JP": "テキストや画像を含むマルチモーダル入力をサポートし、高品質な動画を生成します。シーンの切り替えや複数キャラクターの相互作用を可能にします。制作ワークフローを簡素化し、コストを削減し、企業広告、マーケティング、個人の創造的なアプリケーションに適しています。",
    "ru-RU": "Поддерживает мультимодальные входы, включая текст и изображения, и создаёт высококачественные видеоролики с переходами между сценами и взаимодействием нескольких персонажей. Упрощает производственные процессы и снижает затраты, подходит для рекламы, маркетинга и творческих задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "HY-Video-1.5"
    }
   ]
  },
  {
   "slug": "tencent/Hy3",
   "model_name": "Hy3",
   "display_name": "Hy3",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1562"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6248"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03905"
      }
     },
     "provider_model_id": "hy3"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035"
      }
     },
     "provider_model_id": "tencent/Hy3"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035"
      }
     },
     "provider_model_id": "tencent/hy3"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.066"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.25999999999999995"
      }
     },
     "provider_model_id": "tencent/hy3"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "hy3-free"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035"
      }
     },
     "provider_model_id": "tencent/hy3"
    },
    {
     "provider": "tencent-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "hy3"
    },
    {
     "provider": "tencent-tokenhub",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "hy3"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux+ai-model-directory",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5301"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0333"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1323"
      }
     },
     "provider_model_id": "tencent/hy3"
    }
   ],
   "intro": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
   "released_at": "2026-07-06",
   "max_input_tokens": 256000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "Hy",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.9,
     "top_p": 1
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hy3",
    "hy3-free",
    "tencent/Hy3",
    "tencent/hy3",
    "tencent/hy3:free"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "kilo",
     "charge": "cache_read",
     "old": "0.5",
     "new": "0.035"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "kilo",
     "charge": "completion",
     "old": "0.8",
     "new": "0.58"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "kilo",
     "charge": "prompt",
     "old": "0.2",
     "new": "0.14"
    },
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "Hy3"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "cache_read",
     "old": "0.5",
     "new": "0.035"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "completion",
     "old": "0.8",
     "new": "0.58"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "0.2",
     "new": "0.14"
    }
   ]
  },
  {
   "slug": "tencent/Hy3-preview",
   "model_name": "Hy3-preview",
   "display_name": "Hy3 preview",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.566661"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.051"
      }
     },
     "provider_model_id": "hy3-preview"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035"
      }
     },
     "provider_model_id": "hy3-preview"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_016": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "cache_read_0_016_0_032": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_0_016": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "prompt_0_016_0_032": {
       "unit": "per_M_tokens",
       "price": "0.235294"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion_0_0_016": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_016_0_032": {
       "unit": "per_M_tokens",
       "price": "0.941176"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     },
     "provider_model_id": "hy3-preview"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.066"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029"
      }
     },
     "provider_model_id": "tencent/hy3-preview"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.066"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029"
      }
     },
     "provider_model_id": "tencent/hy3-preview"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "hy3-preview-free"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.063"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.021"
      }
     },
     "provider_model_id": "tencent/hy3-preview"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.17390999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05797"
      }
     },
     "provider_model_id": "tencent/hy3-preview"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.066"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029"
      }
     },
     "provider_model_id": "tencent/Hy3-preview"
    },
    {
     "provider": "tencent-tokenhub",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "hy3-preview"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.066"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.260000004"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.029000003999999996"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.066"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.066"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.066"
      }
     },
     "provider_model_id": "tencent/hy3-preview"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.172"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.058"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "tencent/hy3-preview",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.607022",
        "cache_read": "1.579315",
        "prompt": "1.336071"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": ">16K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.286741",
        "cache_read": "1.191413",
        "prompt": "1.069791"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 16000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
   "released_at": "2026-04-20",
   "max_input_tokens": 256000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "Hy",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "knowledge_cutoff": "2025-06",
   "deprecated": true,
   "status": "deprecated",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.9,
     "top_p": 1
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "hy3-preview",
    "hy3-preview-free",
    "tencent/Hy3-preview",
    "tencent/hy3-preview",
    "tencent/hy3-preview:free"
   ],
   "intro_i18n": {
    "zh-CN": "混元 Hy3 Preview 专为 Agent 工作负载设计，采用 295B 总参数、21B 激活参数的 MoE 架构。模型具备三种模式：no_think（极速响应）、think_low（快速推理）、think_high（深度推理），可适应从高频交互到复杂工程的不同需求。在 SWE-bench Verified 等编码基准上接近 SOTA，同时支持 256K 上下文，用于跨文件代码重构与长文档分析。非常适合需要可靠任务完成且对推理成本敏感的开发者。",
    "zh-TW": "鴻源 Hy3 Preview 專為代理工作負載設計，採用 295B 參數、21B 啟動參數的 MoE 架構。單一模型提供 **no_think**（極速回應）、**think_low**（快速推理）與 **think_high**（深度推理）三種模式，以滿足從高頻互動到複雜工程任務的不同需求。在 SWE-bench Verified 等程式基準中接近 SOTA，並支援 256K 上下文，可用於跨文件程式重構與長文分析。非常適合重視成本與可靠性的開發者。",
    "ja-JP": "Hunyuan Hy3 Previewは、エージェントワークロード向けに設計されており、295Bの総パラメータと21Bのアクティブパラメータを備えたMixture-of-Experts (MoE)アーキテクチャを採用しています。**no_think**（超高速応答）、**think_low**（迅速な推論）、**think_high**（深い推論）の3つのモードを単一モデル内で提供し、高頻度の対話から複雑なエンジニアリングタスクまで、さまざまなレイテンシーと深度の要件に対応します。SWE-bench Verifiedなどのコーディングベンチマークでほぼ最先端の性能を達成し、256Kコンテキストウィンドウをサポートしてクロスファイルコードリファクタリングや長文ドキュメント分析を可能にします。このモデルは、推論コストに敏感でありながら信頼性の高いタスク完了を必要とする開発者に適しています。",
    "ru-RU": "Hunyuan Hy3 Preview создан для агентных нагрузок и использует архитектуру MoE с 295B общих параметров и 21B активных. Поддерживает три режима в одной модели: no_think (сверхбыстрый ответ), think_low (быстрое рассуждение) и think_high (глубокое рассуждение), удовлетворяя требованиям от высокочастотных запросов до сложных инженерных задач. Демонстрирует показатели, близкие к передовым результатам, в бенчмарках программирования вроде SWE-bench Verified, и поддерживает контекст 256K для рефакторинга кода и анализа длинных документов. Подходит для разработчиков, которым важны надёжность и экономичность вычислений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Hy3 preview"
    }
   ]
  },
  {
   "slug": "tencent/siliconflow-tencent-hunyuan-a13b-instruct",
   "model_name": "siliconflow-tencent-hunyuan-a13b-instruct",
   "display_name": "tencent/Hunyuan-A13B-Instruct",
   "vendor": "tencent",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     }
    }
   ],
   "released_at": "2025-07-02",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "tencent/Hunyuan-A13B-Instruct"
    }
   ]
  },
  {
   "slug": "upstage/solar-10_7b-instruct",
   "model_name": "solar-10_7b-instruct",
   "display_name": "solar-10.7b-instruct",
   "vendor": "upstage",
   "pricing": [
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "upstage/solar-10_7b-instruct"
    }
   ],
   "intro": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
   "released_at": "2024-06-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "upstage/solar-10_7b-instruct"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "solar-10.7b-instruct"
    }
   ]
  },
  {
   "slug": "upstage/SOLAR-10.7B-Instruct-v1.0",
   "model_name": "SOLAR-10.7B-Instruct-v1.0",
   "display_name": "SOLAR-10.7B-Instruct-v1.0",
   "vendor": "upstage",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "upstage/SOLAR-10.7B-Instruct-v1.0"
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "upstage/SOLAR-10.7B-Instruct-v1.0"
   ],
   "intro_i18n": {
    "zh-CN": "Upstage SOLAR Instruct v1（11B）专为精准指令任务调优，具备强大的语言能力。",
    "zh-TW": "Upstage SOLAR Instruct v1（11B）針對精準指令任務進行調校，語言表現強勁。",
    "ja-JP": "Upstage SOLAR Instruct v1（11B）は、精密な指示タスクに対応するよう調整され、優れた言語性能を発揮します。",
    "ru-RU": "Upstage SOLAR Instruct v1 (11B) настроена для точного выполнения инструкций с высокой языковой производительностью."
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "SOLAR-10.7B-Instruct-v1.0"
    }
   ]
  },
  {
   "slug": "upstage/solar-pro-3",
   "model_name": "solar-pro-3",
   "display_name": "Upstage: Solar Pro 3",
   "vendor": "upstage",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "upstage/solar-pro-3"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "upstage/solar-pro-3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.015"
      }
     },
     "provider_model_id": "upstage/solar-pro-3"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2026-01-27",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true
   },
   "family": "solar-pro",
   "model_type": "deep_thinking",
   "benchmarks": {
    "intelligence_index": 14.1,
    "coding_index": 16.2,
    "agentic_index": 2.7
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "upstage/solar-pro-3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Upstage: Solar Pro 3"
    }
   ]
  },
  {
   "slug": "vidu/vidu-2.0",
   "model_name": "vidu-2.0",
   "display_name": "vidu-2.0",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.28"
      }
     },
     "provider_model_id": "vidu/vidu-2.0"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/vidu-2.0"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vidu-2.0"
    }
   ]
  },
  {
   "slug": "vidu/vidu-q3",
   "model_name": "vidu-q3",
   "display_name": "vidu-q3",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.0975"
      }
     },
     "provider_model_id": "vidu/vidu-q3"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video",
     "audio"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/vidu-q3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vidu-q3"
    }
   ]
  },
  {
   "slug": "vidu/vidu-q3-turbo",
   "model_name": "vidu-q3-turbo",
   "display_name": "vidu-q3-turbo",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "request": {
       "unit": "per_request",
       "price": "0.195"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "vidu/vidu-q3-turbo"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/vidu-q3-turbo"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "vidu-q3-turbo"
    }
   ]
  },
  {
   "slug": "vidu/vidu2-image",
   "model_name": "vidu2-image",
   "display_name": "Vidu 2 Image",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.183824"
      }
     }
    }
   ],
   "released_at": "2025-06-18",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Vidu 2是一个平衡速度和质量的视频生成基础模型。专注于图像转视频生成和首尾帧控制，支持4秒720P视频。生成速度显著提升，同时成本大幅降低。图像转视频生成修复了之前的颜色偏移问题，提供稳定可控的视觉效果，适用于电商等应用。此外，首尾帧的语义理解和多参考图像的一致性得到了增强，使其成为一般娱乐、互联网媒体、动画短剧和广告等大规模内容生产的高效工具。",
    "zh-TW": "Vidu 2是一款平衡速度及質量的影像生成基礎模型。專注於影像生成影像及首尾影格控制，支持4秒720P影像。生成速度顯著提升，同時成本大幅降低。影像生成影像修復了之前的色彩偏移問題，提供穩定且可控的視覺效果，適用於電商及類似應用。此外，首尾影格的語義理解及多參考影像的一致性得到增強，使其成為一般娛樂、互聯網媒體、動畫短劇及廣告等大規模內容製作的高效工具。",
    "ja-JP": "Vidu 2は、速度と品質のバランスを取るために設計されたビデオ生成基盤モデルです。画像からビデオへの生成と開始–終了フレーム制御に焦点を当て、4秒間の720Pビデオをサポートします。生成速度が大幅に向上し、コストが大幅に削減されました。画像からビデオへの生成は、以前の色シフト問題を修正し、安定した制御可能なビジュアルを提供し、eコマースや類似のアプリケーションに適しています。さらに、開始および終了フレームの意味理解と複数の参照画像間の一貫性が向上し、一般的なエンターテインメント、インターネットメディア、アニメ短編ドラマ、広告などの大規模なコンテンツ制作に効率的なツールとなっています。",
    "ru-RU": "Vidu 2 — базовая модель генерации видео, разработанная для баланса между скоростью и качеством. Она фокусируется на генерации видео из изображений и управлении начальными и конечными кадрами, поддерживая видео длиной 4 секунды в разрешении 720P. Скорость генерации значительно улучшена, а затраты существенно снижены. Генерация видео из изображений устраняет предыдущие проблемы с изменением цвета, обеспечивая стабильные и управляемые визуальные эффекты, подходящие для электронной коммерции и аналогичных приложений. Кроме того, улучшено семантическое понимание начальных и конечных кадров, а также согласованность между несколькими эталонными изображениями, что делает ее эффективным инструментом для массового производства контента в сфере развлечений, интернет-медиа, анимационных коротких драм и рекламы."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu 2 Image"
    }
   ]
  },
  {
   "slug": "vidu/vidu2-reference",
   "model_name": "vidu2-reference",
   "display_name": "Vidu 2 Reference",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.183824"
      }
     }
    }
   ],
   "released_at": "2025-06-18",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Vidu 2是一个平衡速度和质量的视频生成基础模型。专注于图像转视频生成和首尾帧控制，支持4秒720P视频。生成速度显著提升，同时成本大幅降低。图像转视频生成修复了之前的颜色偏移问题，提供稳定可控的视觉效果，适用于电商等应用。此外，首尾帧的语义理解和多参考图像的一致性得到了增强，使其成为一般娱乐、互联网媒体、动画短剧和广告等大规模内容生产的高效工具。",
    "zh-TW": "Vidu 2是一款平衡速度及質量的影像生成基礎模型。專注於影像生成影像及首尾影格控制，支持4秒720P影像。生成速度顯著提升，同時成本大幅降低。影像生成影像修復了之前的色彩偏移問題，提供穩定且可控的視覺效果，適用於電商及類似應用。此外，首尾影格的語義理解及多參考影像的一致性得到增強，使其成為一般娛樂、互聯網媒體、動畫短劇及廣告等大規模內容製作的高效工具。",
    "ja-JP": "Vidu 2は、速度と品質のバランスを取るために設計されたビデオ生成基盤モデルです。画像からビデオへの生成と開始–終了フレーム制御に焦点を当て、4秒間の720Pビデオをサポートします。生成速度が大幅に向上し、コストが大幅に削減されました。画像からビデオへの生成は、以前の色シフト問題を修正し、安定した制御可能なビジュアルを提供し、eコマースや類似のアプリケーションに適しています。さらに、開始および終了フレームの意味理解と複数の参照画像間の一貫性が向上し、一般的なエンターテインメント、インターネットメディア、アニメ短編ドラマ、広告などの大規模なコンテンツ制作に効率的なツールとなっています。",
    "ru-RU": "Vidu 2 — базовая модель генерации видео, разработанная для баланса между скоростью и качеством. Она фокусируется на генерации видео из изображений и управлении начальными и конечными кадрами, поддерживая видео длиной 4 секунды в разрешении 720P. Скорость генерации значительно улучшена, а затраты существенно снижены. Генерация видео из изображений устраняет предыдущие проблемы с изменением цвета, обеспечивая стабильные и управляемые визуальные эффекты, подходящие для электронной коммерции и аналогичных приложений. Кроме того, улучшено семантическое понимание начальных и конечных кадров, а также согласованность между несколькими эталонными изображениями, что делает ее эффективным инструментом для массового производства контента в сфере развлечений, интернет-медиа, анимационных коротких драм и рекламы."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu 2 Reference"
    }
   ]
  },
  {
   "slug": "vidu/vidu2-start-end",
   "model_name": "vidu2-start-end",
   "display_name": "Vidu 2 Start End",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.183824"
      }
     }
    }
   ],
   "released_at": "2025-06-18",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Vidu 2是一个平衡速度和质量的视频生成基础模型。专注于图像转视频生成和首尾帧控制，支持4秒720P视频。生成速度显著提升，同时成本大幅降低。图像转视频生成修复了之前的颜色偏移问题，提供稳定可控的视觉效果，适用于电商等应用。此外，首尾帧的语义理解和多参考图像的一致性得到了增强，使其成为一般娱乐、互联网媒体、动画短剧和广告等大规模内容生产的高效工具。",
    "zh-TW": "Vidu 2是一款平衡速度及質量的影像生成基礎模型。專注於影像生成影像及首尾影格控制，支持4秒720P影像。生成速度顯著提升，同時成本大幅降低。影像生成影像修復了之前的色彩偏移問題，提供穩定且可控的視覺效果，適用於電商及類似應用。此外，首尾影格的語義理解及多參考影像的一致性得到增強，使其成為一般娛樂、互聯網媒體、動畫短劇及廣告等大規模內容製作的高效工具。",
    "ja-JP": "Vidu 2は、速度と品質のバランスを取るために設計されたビデオ生成基盤モデルです。画像からビデオへの生成と開始–終了フレーム制御に焦点を当て、4秒間の720Pビデオをサポートします。生成速度が大幅に向上し、コストが大幅に削減されました。画像からビデオへの生成は、以前の色シフト問題を修正し、安定した制御可能なビジュアルを提供し、eコマースや類似のアプリケーションに適しています。さらに、開始および終了フレームの意味理解と複数の参照画像間の一貫性が向上し、一般的なエンターテインメント、インターネットメディア、アニメ短編ドラマ、広告などの大規模なコンテンツ制作に効率的なツールとなっています。",
    "ru-RU": "Vidu 2 — базовая модель генерации видео, разработанная для баланса между скоростью и качеством. Она фокусируется на генерации видео из изображений и управлении начальными и конечными кадрами, поддерживая видео длиной 4 секунды в разрешении 720P. Скорость генерации значительно улучшена, а затраты существенно снижены. Генерация видео из изображений устраняет предыдущие проблемы с изменением цвета, обеспечивая стабильные и управляемые визуальные эффекты, подходящие для электронной коммерции и аналогичных приложений. Кроме того, улучшено семантическое понимание начальных и конечных кадров, а также согласованность между несколькими эталонными изображениями, что делает ее эффективным инструментом для массового производства контента в сфере развлечений, интернет-медиа, анимационных коротких драм и рекламы."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu 2 Start End"
    }
   ]
  },
  {
   "slug": "vidu/vidu2.0",
   "model_name": "vidu2.0",
   "display_name": "vidu2.0",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "vidu2.0"
    }
   ]
  },
  {
   "slug": "vidu/viduq1",
   "model_name": "viduq1",
   "display_name": "viduq1",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "viduq1"
    }
   ]
  },
  {
   "slug": "vidu/viduq1-image",
   "model_name": "viduq1-image",
   "display_name": "Vidu Q1 Image",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.367647"
      }
     }
    }
   ],
   "released_at": "2025-06-18",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Vidu Q1是Vidu的下一代视频生成基础模型，专注于高质量视频创作。生成固定规格为5秒、24帧/秒、1080P分辨率的内容。通过对视觉清晰度的深度优化，整体图像质量和纹理显著提升，同时大幅减少了手部变形和帧抖动等问题。真实风格接近现实场景，2D动画风格以高保真度保留。首尾帧之间的过渡更加平滑，非常适合电影制作、广告和动画短剧等高需求创意场景。",
    "zh-TW": "Vidu Q1是Vidu的下一代影像生成基礎模型，專注於高質量影像創作。生成內容規格固定為5秒、24FPS及1080P解析度。通過深度優化視覺清晰度，整體影像質量及紋理顯著提升，同時大幅減少手部變形及影格抖動等問題。真實風格接近現實場景，2D動畫風格以高保真度保留。首尾影格之間的過渡更流暢，非常適合電影製作、廣告及動畫短劇等高需求創意場景。",
    "ja-JP": "Vidu Q1は、高品質なビデオ作成に焦点を当てたViduの次世代ビデオ生成基盤モデルです。5秒間、24FPS、1080P解像度の固定仕様でコンテンツを生成します。視覚的明瞭性の深い最適化により、全体的な画像品質とテクスチャが大幅に向上し、手の変形やフレームの揺れなどの問題が大幅に減少しました。リアルなスタイルは現実世界のシーンに近づき、2Dアニメーションスタイルは高い忠実度で保持されます。開始フレームと終了フレーム間の遷移が滑らかになり、映画制作、広告、アニメ短編ドラマなどの高需要なクリエイティブシナリオに適しています。",
    "ru-RU": "Vidu Q1 — модель следующего поколения для генерации видео от Vidu, ориентированная на создание высококачественного видео. Она производит контент с фиксированными характеристиками: 5 секунд, 24 FPS и разрешение 1080P. Благодаря глубокой оптимизации визуальной четкости, общее качество изображения и текстуры значительно улучшены, а такие проблемы, как деформация рук и дрожание кадров, значительно уменьшены. Реалистичный стиль максимально приближен к реальным сценам, а 2D-анимационные стили сохраняются с высокой точностью. Переходы между начальным и конечным кадрами стали более плавными, что делает ее подходящей для творческих сценариев с высокими требованиями, таких как кинопроизводство, реклама и анимационные короткие драмы."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q1 Image"
    }
   ]
  },
  {
   "slug": "vidu/viduq1-start-end",
   "model_name": "viduq1-start-end",
   "display_name": "Vidu Q1 Start End",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.367647"
      }
     }
    }
   ],
   "released_at": "2025-06-18",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Vidu Q1是Vidu的下一代视频生成基础模型，专注于高质量视频创作。生成固定规格为5秒、24帧/秒、1080P分辨率的内容。通过对视觉清晰度的深度优化，整体图像质量和纹理显著提升，同时大幅减少了手部变形和帧抖动等问题。真实风格接近现实场景，2D动画风格以高保真度保留。首尾帧之间的过渡更加平滑，非常适合电影制作、广告和动画短剧等高需求创意场景。",
    "zh-TW": "Vidu Q1是Vidu的下一代影像生成基礎模型，專注於高質量影像創作。生成內容規格固定為5秒、24FPS及1080P解析度。通過深度優化視覺清晰度，整體影像質量及紋理顯著提升，同時大幅減少手部變形及影格抖動等問題。真實風格接近現實場景，2D動畫風格以高保真度保留。首尾影格之間的過渡更流暢，非常適合電影製作、廣告及動畫短劇等高需求創意場景。",
    "ja-JP": "Vidu Q1は、高品質なビデオ作成に焦点を当てたViduの次世代ビデオ生成基盤モデルです。5秒間、24FPS、1080P解像度の固定仕様でコンテンツを生成します。視覚的明瞭性の深い最適化により、全体的な画像品質とテクスチャが大幅に向上し、手の変形やフレームの揺れなどの問題が大幅に減少しました。リアルなスタイルは現実世界のシーンに近づき、2Dアニメーションスタイルは高い忠実度で保持されます。開始フレームと終了フレーム間の遷移が滑らかになり、映画制作、広告、アニメ短編ドラマなどの高需要なクリエイティブシナリオに適しています。",
    "ru-RU": "Vidu Q1 — модель следующего поколения для генерации видео от Vidu, ориентированная на создание высококачественного видео. Она производит контент с фиксированными характеристиками: 5 секунд, 24 FPS и разрешение 1080P. Благодаря глубокой оптимизации визуальной четкости, общее качество изображения и текстуры значительно улучшены, а такие проблемы, как деформация рук и дрожание кадров, значительно уменьшены. Реалистичный стиль максимально приближен к реальным сценам, а 2D-анимационные стили сохраняются с высокой точностью. Переходы между начальным и конечным кадрами стали более плавными, что делает ее подходящей для творческих сценариев с высокими требованиями, таких как кинопроизводство, реклама и анимационные короткие драмы."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q1 Start End"
    }
   ]
  },
  {
   "slug": "vidu/viduq1-text",
   "model_name": "viduq1-text",
   "display_name": "Vidu Q1 Text",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.367647"
      }
     }
    }
   ],
   "released_at": "2025-06-18",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Vidu Q1是Vidu的下一代视频生成基础模型，专注于高质量视频创作。生成固定规格为5秒、24帧/秒、1080P分辨率的内容。通过对视觉清晰度的深度优化，整体图像质量和纹理显著提升，同时大幅减少了手部变形和帧抖动等问题。真实风格接近现实场景，2D动画风格以高保真度保留。首尾帧之间的过渡更加平滑，非常适合电影制作、广告和动画短剧等高需求创意场景。",
    "zh-TW": "Vidu Q1是Vidu的下一代影像生成基礎模型，專注於高質量影像創作。生成內容規格固定為5秒、24FPS及1080P解析度。通過深度優化視覺清晰度，整體影像質量及紋理顯著提升，同時大幅減少手部變形及影格抖動等問題。真實風格接近現實場景，2D動畫風格以高保真度保留。首尾影格之間的過渡更流暢，非常適合電影製作、廣告及動畫短劇等高需求創意場景。",
    "ja-JP": "Vidu Q1は、高品質なビデオ作成に焦点を当てたViduの次世代ビデオ生成基盤モデルです。5秒間、24FPS、1080P解像度の固定仕様でコンテンツを生成します。視覚的明瞭性の深い最適化により、全体的な画像品質とテクスチャが大幅に向上し、手の変形やフレームの揺れなどの問題が大幅に減少しました。リアルなスタイルは現実世界のシーンに近づき、2Dアニメーションスタイルは高い忠実度で保持されます。開始フレームと終了フレーム間の遷移が滑らかになり、映画制作、広告、アニメ短編ドラマなどの高需要なクリエイティブシナリオに適しています。",
    "ru-RU": "Vidu Q1 — модель следующего поколения для генерации видео от Vidu, ориентированная на создание высококачественного видео. Она производит контент с фиксированными характеристиками: 5 секунд, 24 FPS и разрешение 1080P. Благодаря глубокой оптимизации визуальной четкости, общее качество изображения и текстуры значительно улучшены, а такие проблемы, как деформация рук и дрожание кадров, значительно уменьшены. Реалистичный стиль максимально приближен к реальным сценам, а 2D-анимационные стили сохраняются с высокой точностью. Переходы между начальным и конечным кадрами стали более плавными, что делает ее подходящей для творческих сценариев с высокими требованиями, таких как кинопроизводство, реклама и анимационные короткие драмы."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q1 Text"
    }
   ]
  },
  {
   "slug": "vidu/viduq2",
   "model_name": "viduq2",
   "display_name": "viduq2",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "viduq2"
    }
   ]
  },
  {
   "slug": "vidu/viduq2_reference2video",
   "model_name": "viduq2_reference2video",
   "display_name": "Vidu Q2 Reference-to-Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.04136"
      }
     },
     "provider_model_id": "vidu/viduq2_reference2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq2_reference2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入参考图像和文本描述生成视频。ViduQ2参考转视频是一款专为精确指令遵循和细腻情感捕捉设计的模型。提供卓越的叙事控制，准确解读和表达微表情变化；具有丰富的电影语言、流畅的摄像机运动和强烈的视觉张力。广泛适用于电影和动画、广告和电商、短剧以及文旅行业。",
    "zh-TW": "輸入參考影像及文字描述生成影像。ViduQ2參考生成影像是一款專為精確指令遵循及細膩情感捕捉設計的模型。提供卓越的敘事控制，精確解釋及表達微表情變化；特性包括豐富的電影語言、流暢的相機運動及強烈的視覺張力。廣泛應用於電影及動畫、廣告及電商、短劇及文化旅遊行業。",
    "ja-JP": "参照画像とテキスト説明を入力してビデオを生成します。ViduQ2参照からビデオは、正確な指示遵守と微妙な感情キャプチャのために設計されたモデルです。優れた物語制御を提供し、微表情の変化を正確に解釈して表現します。豊かな映画的言語、滑らかなカメラ動作、強い視覚的緊張感を特徴とします。映画やアニメーション、広告やeコマース、短編ドラマ、文化観光産業に広く適用可能です。",
    "ru-RU": "Введите эталонные изображения вместе с текстовым описанием, чтобы сгенерировать видео. ViduQ2 reference-to-video — модель, разработанная для точного следования инструкциям и захвата нюансов эмоций. Она предлагает выдающийся контроль повествования, точно интерпретируя и выражая изменения микроэмоций; обладает богатым кинематографическим языком, плавными движениями камеры и сильным визуальным напряжением. Широко применяется в кино и анимации, рекламе и электронной коммерции, коротких драмах и индустрии культурного туризма."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q2 Reference-to-Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq2_text2video",
   "model_name": "viduq2_text2video",
   "display_name": "Vidu Q2 Turbo Text-to-Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.032169"
      }
     },
     "provider_model_id": "vidu/viduq2_text2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq2_text2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入文本提示生成视频。ViduQ2文本转视频是一款专为精确指令遵循和细腻情感捕捉设计的模型。提供卓越的叙事控制，准确解读和表达微表情变化；具有丰富的电影语言、流畅的摄像机运动和强烈的视觉张力。广泛适用于电影和动画、广告和电商、短剧以及文旅行业。",
    "zh-TW": "輸入文字提示生成影像。ViduQ2文字生成影像是一款專為精確指令遵循及細膩情感捕捉設計的模型。提供卓越的敘事控制，精確解釋及表達微表情變化；特性包括豐富的電影語言、流暢的相機運動及強烈的視覺張力。廣泛應用於電影及動畫、廣告及電商、短劇及文化旅遊行業。",
    "ja-JP": "テキストプロンプトを入力してビデオを生成します。ViduQ2テキストからビデオは、正確な指示遵守と微妙な感情キャプチャのために設計されたモデルです。優れた物語制御を提供し、微表情の変化を正確に解釈して表現します。豊かな映画的言語、滑らかなカメラ動作、強い視覚的緊張感を特徴とします。映画やアニメーション、広告やeコマース、短編ドラマ、文化観光産業に広く適用可能です。",
    "ru-RU": "Введите текстовую подсказку, чтобы сгенерировать видео. ViduQ2 text-to-video — модель, разработанная для точного следования инструкциям и захвата нюансов эмоций. Она предлагает выдающийся контроль повествования, точно интерпретируя и выражая изменения микроэмоций; обладает богатым кинематографическим языком, плавными движениями камеры и сильным визуальным напряжением. Широко применяется в кино и анимации, рекламе и электронной коммерции, коротких драмах и индустрии культурного туризма."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q2 Turbo Text-to-Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq2-pro_img2video",
   "model_name": "viduq2-pro_img2video",
   "display_name": "Vidu Q2 Pro Image-to-Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.050551"
      }
     },
     "provider_model_id": "vidu/viduq2-pro_img2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq2-pro_img2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入图像和文本描述生成视频。ViduQ2-Pro图像转视频是全球首个“万物皆可参考”视频模型。支持六个参考维度——效果、表情、纹理、动作、角色和场景，实现全面进化的视频编辑。通过可控的添加、删除和修改，达到细粒度的视频编辑，设计为动画系列、短剧和电影制作的生产级创作引擎。",
    "zh-TW": "輸入影像及文字描述生成影像。ViduQ2-Pro影像生成影像是全球首款“萬物皆可參考”影像模型。支持六個參考維度——效果、表情、紋理、動作、角色及場景——實現全面進化的影像編輯。通過可控的添加、刪除及修改，實現細粒度影像編輯，設計為動畫系列、短劇及電影製作的生產級創作引擎。",
    "ja-JP": "画像とテキスト説明を入力してビデオを生成します。ViduQ2-Pro画像からビデオは、世界初の「すべてが参照可能」なビデオモデルです。エフェクト、表情、テクスチャ、アクション、キャラクター、シーンの6つの参照次元をサポートし、完全に進化したビデオ編集を可能にします。追加、削除、変更を制御可能にすることで、細かい粒度のビデオ編集を実現し、アニメシリーズ、短編ドラマ、映画制作のためのプロダクショングレードの作成エンジンとして設計されています。",
    "ru-RU": "Введите изображение и текстовое описание, чтобы сгенерировать видео. ViduQ2-Pro image-to-video — первая в мире модель видео «Все может быть ссылкой». Она поддерживает шесть измерений ссылок — эффекты, выражения, текстуры, действия, персонажи и сцены — обеспечивая полностью развитое редактирование видео. Через управляемое добавление, удаление и модификацию достигается тонкое редактирование видео, разработанное как производственный движок для создания анимационных сериалов, коротких драм и кинопроизводства."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q2 Pro Image-to-Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq2-pro_reference2video",
   "model_name": "viduq2-pro_reference2video",
   "display_name": "Vidu Q2 Pro Reference-to-Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.045956"
      }
     },
     "provider_model_id": "vidu/viduq2-pro_reference2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq2-pro_reference2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入参考视频、图像和文本描述生成视频。ViduQ2-Pro参考转视频是全球首个“万物皆可参考”视频模型。支持六个参考维度——效果、表情、纹理、动作、角色和场景，实现全面进化的视频编辑。通过可控的添加、删除和修改，达到细粒度的视频编辑，设计为动画系列、短剧和电影制作的生产级创作引擎。",
    "zh-TW": "輸入參考影像、影像及文字描述生成影像。ViduQ2-Pro參考生成影像是全球首款“萬物皆可參考”影像模型。支持六個參考維度——效果、表情、紋理、動作、角色及場景——實現全面進化的影像編輯。通過可控的添加、刪除及修改，實現細粒度影像編輯，設計為動畫系列、短劇及電影製作的生產級創作引擎。",
    "ja-JP": "参照ビデオ、画像、およびテキスト説明を入力してビデオを生成します。ViduQ2-Pro参照からビデオは、世界初の「すべてが参照可能」なビデオモデルです。エフェクト、表情、テクスチャ、アクション、キャラクター、シーンの6つの参照次元をサポートし、完全に進化したビデオ編集を可能にします。追加、削除、変更を制御可能にすることで、細かい粒度のビデオ編集を実現し、アニメシリーズ、短編ドラマ、映画制作のためのプロダクショングレードの作成エンジンとして設計されています。",
    "ru-RU": "Введите эталонные видео, изображения и текстовое описание, чтобы сгенерировать видео. ViduQ2-Pro reference-to-video — первая в мире модель видео «Все может быть ссылкой». Она поддерживает шесть измерений ссылок — эффекты, выражения, текстуры, действия, персонажи и сцены — обеспечивая полностью развитое редактирование видео. Через управляемое добавление, удаление и модификацию достигается тонкое редактирование видео, разработанное как производственный движок для создания анимационных сериалов, коротких драм и кинопроизводства."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q2 Pro Reference-to-Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq2-pro_start-end2video",
   "model_name": "viduq2-pro_start-end2video",
   "display_name": "Vidu Q2 Pro Start-to-End Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.050551"
      }
     },
     "provider_model_id": "vidu/viduq2-pro_start-end2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq2-pro_start-end2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入首帧和尾帧图像以及文本描述生成视频。ViduQ2-Pro关键帧转视频是全球首个“万物皆可参考”视频模型。支持六个参考维度——效果、表情、纹理、动作、角色和场景，实现全面进化的视频编辑。通过可控的添加、删除和修改，达到细粒度的视频编辑，设计为动画系列、短剧和电影制作的生产级创作引擎。",
    "zh-TW": "輸入首影格及尾影格影像以及文字描述生成影像。ViduQ2-Pro關鍵影格生成影像是全球首款“萬物皆可參考”影像模型。支持六個參考維度——效果、表情、紋理、動作、角色及場景——實現全面進化的影像編輯。通過可控的添加、刪除及修改，實現細粒度影像編輯，設計為動畫系列、短劇及電影製作的生產級創作引擎。",
    "ja-JP": "最初と最後のフレーム画像とテキスト説明を入力してビデオを生成します。ViduQ2-Proキーフレームからビデオは、世界初の「すべてが参照可能」なビデオモデルです。エフェクト、表情、テクスチャ、アクション、キャラクター、シーンの6つの参照次元をサポートし、完全に進化したビデオ編集を可能にします。追加、削除、変更を制御可能にすることで、細かい粒度のビデオ編集を実現し、アニメシリーズ、短編ドラマ、映画制作のためのプロダクショングレードの作成エンジンとして設計されています。",
    "ru-RU": "Введите изображения первого и последнего кадров вместе с текстовым описанием, чтобы сгенерировать видео. ViduQ2-Pro keyframe-to-video — первая в мире модель видео «Все может быть ссылкой». Она поддерживает шесть измерений ссылок — эффекты, выражения, текстуры, действия, персонажи и сцены — обеспечивая полностью развитое редактирование видео. Через управляемое добавление, удаление и модификацию достигается тонкое редактирование видео, разработанное как производственный движок для создания анимационных сериалов, коротких драм и кинопроизводства."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q2 Pro Start-to-End Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq2-turbo_img2video",
   "model_name": "viduq2-turbo_img2video",
   "display_name": "Vidu Q2 Turbo Image-to-Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.036765"
      }
     },
     "provider_model_id": "vidu/viduq2-turbo_img2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq2-turbo_img2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入图像和文本描述生成视频。ViduQ2-Turbo图像转视频是一个超快速生成引擎。5秒720P视频可在19秒内生成，5秒1080P视频约需27秒。角色动作和表情自然逼真，在动作场景等高动态场景中表现出色，具有强大的真实性和卓越的性能。",
    "zh-TW": "輸入影像及文字描述生成影像。ViduQ2-Turbo影像生成影像是一款超高速生成引擎。5秒720P影像生成僅需19秒，5秒1080P影像約需27秒。角色動作及表情自然逼真，提供強烈的真實感及卓越性能，適用於動作場景等高動態場景。",
    "ja-JP": "画像とテキスト説明を入力してビデオを生成します。ViduQ2-Turbo画像からビデオは、超高速生成エンジンです。5秒間の720Pビデオはわずか19秒で生成でき、5秒間の1080Pビデオは約27秒で生成できます。キャラクターの動作や表情は自然でリアルであり、アクションシーンのような高動的なシーンで強いリアリズムと優れたパフォーマンスを発揮します。",
    "ru-RU": "Введите изображение и текстовое описание, чтобы сгенерировать видео. ViduQ2-Turbo image-to-video — ультрабыстрый движок генерации. 5-секундное видео в разрешении 720P может быть сгенерировано всего за 19 секунд, а 5-секундное видео в разрешении 1080P — примерно за 27 секунд. Действия и выражения персонажей естественны и реалистичны, обеспечивая сильную аутентичность и отличную производительность в высокодинамичных сценах, таких как экшн-сцены, с широким диапазоном движений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q2 Turbo Image-to-Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq2-turbo_start-end2video",
   "model_name": "viduq2-turbo_start-end2video",
   "display_name": "Vidu Q2 Turbo Start-to-End Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.036765"
      }
     },
     "provider_model_id": "vidu/viduq2-turbo_start-end2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq2-turbo_start-end2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入首帧和尾帧图像以及文本描述生成视频。ViduQ2-Turbo关键帧转视频是一个超快速生成引擎。5秒720P视频可在19秒内生成，5秒1080P视频约需27秒。角色动作和表情自然逼真，在动作场景等高动态场景中表现出色，支持广泛的运动。",
    "zh-TW": "輸入首影格及尾影格影像以及文字描述生成影像。ViduQ2-Turbo關鍵影格生成影像是一款超高速生成引擎。5秒720P影像生成僅需19秒，5秒1080P影像約需27秒。角色動作及表情自然逼真，提供強烈的真實感及卓越性能，適用於動作場景等高動態場景。",
    "ja-JP": "最初と最後のフレーム画像とテキスト説明を入力してビデオを生成します。ViduQ2-Turboキーフレームからビデオは、超高速生成エンジンです。5秒間の720Pビデオはわずか19秒で生成でき、5秒間の1080Pビデオは約27秒で生成できます。キャラクターの動作や表情は自然でリアルであり、アクションシーンのような高動的なシーンで強いリアリズムと優れたパフォーマンスを発揮します。",
    "ru-RU": "Введите изображения первого и последнего кадров вместе с текстовым описанием, чтобы сгенерировать видео. ViduQ2-Turbo keyframe-to-video — ультрабыстрый движок генерации. 5-секундное видео в разрешении 720P может быть сгенерировано всего за 19 секунд, а 5-секундное видео в разрешении 1080P — примерно за 27 секунд. Действия и выражения персонажей естественны и реалистичны, обеспечивая сильную аутентичность и отличную производительность в высокодинамичных сценах, таких как экшн-сцены, с поддержкой широкого диапазона движений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q2 Turbo Start-to-End Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq3",
   "model_name": "viduq3",
   "display_name": "viduq3",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.42"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "viduq3"
    }
   ]
  },
  {
   "slug": "vidu/viduq3-pro_img2video",
   "model_name": "viduq3-pro_img2video",
   "display_name": "Vidu Q3 Pro Image-to-Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.11489"
      }
     },
     "provider_model_id": "vidu/viduq3-pro_img2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq3-pro_img2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入图像和文本描述生成视频。ViduQ3-Pro图像转视频是旗舰级视听原生模型。支持最长16秒的音视频同步生成，实现自由的多镜头切换，同时精确控制节奏、情感和叙事连贯性。凭借领先的参数规模，提供卓越的图像质量、角色一致性和情感表达，达到电影级标准。适用于广告（电商、TVC、活动宣传）、动画系列、真人剧和游戏等专业制作场景。",
    "zh-TW": "輸入影像及文字描述生成影像。ViduQ3-Pro影像生成影像是一款旗艦級音視原生模型。支持長達16秒的音視同步生成，實現自由多鏡頭切換，同時精確控制節奏、情感及敘事連貫性。憑藉領先的參數規模，提供卓越的影像質量、角色一致性及情感表達，達到電影標準。非常適合廣告（電商、TVC、活動宣傳）、動畫系列、真人劇及遊戲等專業製作場景。",
    "ja-JP": "画像とテキスト説明を入力してビデオを生成します。ViduQ3-Pro画像からビデオは、フラッグシップレベルの視聴覚ネイティブモデルです。最大16秒の音声とビジュアルが同期した生成をサポートし、自由なマルチショット切り替えを可能にしながら、ペース、感情、物語の連続性を正確に制御します。先進的なパラメータスケールを備え、卓越した画像品質、キャラクターの一貫性、感情表現を提供し、映画基準を満たします。広告（eコマース、TVC、パフォーマンスキャンペーン）、アニメシリーズ、実写ドラマ、ゲームなどのプロフェッショナルな制作シナリオに最適です。",
    "ru-RU": "Введите изображение и текстовое описание, чтобы сгенерировать видео. ViduQ3-Pro image-to-video — флагманская модель с нативной аудиовизуальной поддержкой. Поддерживает до 16 секунд синхронизированной аудиовизуальной генерации, позволяя свободное переключение между кадрами при точном контроле темпа, эмоций и повествовательной непрерывности. С ведущим масштабом параметров она обеспечивает исключительное качество изображения, согласованность персонажей и выражение эмоций, соответствуя кинематографическим стандартам. Идеально подходит для профессиональных производственных сценариев, таких как реклама (электронная коммерция, ТВ-ролики, кампании), анимационные сериалы, игровые драмы и игры."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q3 Pro Image-to-Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq3-pro_start-end2video",
   "model_name": "viduq3-pro_start-end2video",
   "display_name": "Vidu Q3 Pro Start-to-End Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.11489"
      }
     },
     "provider_model_id": "vidu/viduq3-pro_start-end2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq3-pro_start-end2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入首帧和尾帧图像以及文本描述生成视频。ViduQ3-Pro关键帧转视频是旗舰级视听原生模型。支持最长16秒的音视频同步生成，实现自由的多镜头切换，同时精确控制节奏、情感和叙事连贯性。凭借领先的参数规模，提供卓越的图像质量、角色一致性和情感表达，达到电影级标准。适用于广告（电商、TVC、活动宣传）、动画系列、真人剧和游戏等专业制作场景。",
    "zh-TW": "輸入首影格及尾影格影像以及文字描述生成影像。ViduQ3-Pro關鍵影格生成影像是一款旗艦級音視原生模型。支持長達16秒的音視同步生成，實現自由多鏡頭切換，同時精確控制節奏、情感及敘事連貫性。憑藉領先的參數規模，提供卓越的影像質量、角色一致性及情感表達，達到電影標準。非常適合廣告（電商、TVC、活動宣傳）、動畫系列、真人劇及遊戲等專業製作場景。",
    "ja-JP": "最初と最後のフレーム画像とテキスト説明を入力してビデオを生成します。ViduQ3-Proキーフレームからビデオは、フラッグシップレベルの視聴覚ネイティブモデルです。最大16秒の音声とビジュアルが同期した生成をサポートし、自由なマルチショット切り替えを可能にしながら、ペース、感情、物語の連続性を正確に制御します。先進的なパラメータスケールを備え、卓越した画像品質、キャラクターの一貫性、感情表現を提供し、映画基準を満たします。広告（eコマース、TVC、パフォーマンスキャンペーン）、アニメシリーズ、実写ドラマ、ゲームなどのプロフェッショナルな制作シナリオに最適です。",
    "ru-RU": "Введите изображения первого и последнего кадров вместе с текстовым описанием, чтобы сгенерировать видео. ViduQ3-Pro keyframe-to-video — флагманская модель с нативной аудиовизуальной поддержкой. Поддерживает до 16 секунд синхронизированной аудиовизуальной генерации, позволяя свободное переключение между кадрами при точном контроле темпа, эмоций и повествовательной непрерывности. С ведущим масштабом параметров она обеспечивает исключительное качество изображения, согласованность персонажей и выражение эмоций, соответствуя кинематографическим стандартам. Идеально подходит для профессиональных производственных сценариев, таких как реклама (электронная коммерция, ТВ-ролики, кампании), анимационные сериалы, игровые драмы и игры."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q3 Pro Start-to-End Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq3-pro_text2video",
   "model_name": "viduq3-pro_text2video",
   "display_name": "Vidu Q3 Pro Text-to-Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.11489"
      }
     },
     "provider_model_id": "vidu/viduq3-pro_text2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq3-pro_text2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入文本提示生成视频。ViduQ3-Pro文本转视频是旗舰级视听原生模型。支持最长16秒的音视频同步生成，实现自由的多镜头切换，同时精确控制节奏、情感和叙事连贯性。凭借领先的参数规模，提供卓越的图像质量、角色一致性和情感表达，达到电影级标准。适用于广告（电商、TVC、活动宣传）、动画系列、真人剧和游戏等专业制作场景。",
    "zh-TW": "輸入文字提示生成影像。ViduQ3-Pro文字生成影像是一款旗艦級音視原生模型。支持長達16秒的音視同步生成，實現自由多鏡頭切換，同時精確控制節奏、情感及敘事連貫性。憑藉領先的參數規模，提供卓越的影像質量、角色一致性及情感表達，達到電影標準。非常適合廣告（電商、TVC、活動宣傳）、動畫系列、真人劇及遊戲等專業製作場景。",
    "ja-JP": "テキストプロンプトを入力してビデオを生成します。ViduQ3-Proテキストからビデオは、フラッグシップレベルの視聴覚ネイティブモデルです。最大16秒の音声とビジュアルが同期した生成をサポートし、自由なマルチショット切り替えを可能にしながら、ペース、感情、物語の連続性を正確に制御します。先進的なパラメータスケールを備え、卓越した画像品質、キャラクターの一貫性、感情表現を提供し、映画基準を満たします。広告（eコマース、TVC、パフォーマンスキャンペーン）、アニメシリーズ、実写ドラマ、ゲームなどのプロフェッショナルな制作シナリオに最適です。",
    "ru-RU": "Введите текстовую подсказку, чтобы сгенерировать видео. ViduQ3-Pro text-to-video — флагманская модель с нативной аудиовизуальной поддержкой. Поддерживает до 16 секунд синхронизированной аудиовизуальной генерации, позволяя свободное переключение между кадрами при точном контроле темпа, эмоций и повествовательной непрерывности. С ведущим масштабом параметров она обеспечивает исключительное качество изображения, согласованность персонажей и выражение эмоций, соответствуя кинематографическим стандартам. Идеально подходит для профессиональных производственных сценариев, таких как реклама (электронная коммерция, ТВ-ролики, кампании), анимационные сериалы, игровые драмы и игры."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q3 Pro Text-to-Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq3-turbo_img2video",
   "model_name": "viduq3-turbo_img2video",
   "display_name": "Vidu Q3 Turbo Image-to-Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.055147"
      }
     },
     "provider_model_id": "vidu/viduq3-turbo_img2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq3-turbo_img2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入图像和文本描述生成视频。ViduQ3-Turbo图像转视频是高性能加速模型。提供极快的生成速度，同时保持高质量的视觉效果和动态表现，在动作场景、情感渲染和语义理解方面表现出色。性价比高，适合社交媒体图片、AI伴侣和特效素材等休闲娱乐场景。",
    "zh-TW": "輸入影像及文字描述生成影像。ViduQ3-Turbo影像生成影像是一款高性能加速模型。提供極快的生成速度，同時保持高質量視覺效果及動態表現，擅長動作場景、情感渲染及語義理解。性價比高，非常適合社交媒體影像、AI伴侶及特效資產等休閒娛樂場景。",
    "ja-JP": "画像とテキスト説明を入力してビデオを生成します。ViduQ3-Turbo画像からビデオは、高性能な加速モデルです。非常に高速な生成を提供しながら、高品質なビジュアルと動的表現を維持し、アクションシーン、感情表現、意味理解に優れています。コスト効率が高く、ソーシャルメディア画像、AIコンパニオン、特殊効果アセットなどのカジュアルなエンターテインメントシナリオに最適です。",
    "ru-RU": "Введите изображение и текстовое описание, чтобы сгенерировать видео. ViduQ3-Turbo image-to-video — высокопроизводительная ускоренная модель. Она предлагает чрезвычайно быструю генерацию, сохраняя высокое качество визуальных эффектов и динамическое выражение, превосходя в экшн-сценах, эмоциональном рендеринге и семантическом понимании. Экономична и идеально подходит для развлекательных сценариев, таких как изображения для социальных сетей, AI-компаньоны и активы для спецэффектов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q3 Turbo Image-to-Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq3-turbo_start-end2video",
   "model_name": "viduq3-turbo_start-end2video",
   "display_name": "Vidu Q3 Turbo Start-to-End Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.055147"
      }
     },
     "provider_model_id": "vidu/viduq3-turbo_start-end2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq3-turbo_start-end2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入首帧和尾帧图像以及文本描述生成视频。ViduQ3-Turbo关键帧转视频是高性能加速模型。提供极快的生成速度，同时保持高质量的视觉效果和动态表现，在动作场景、情感渲染和语义理解方面表现出色。性价比高，适合社交媒体图片、AI伴侣和特效素材等休闲娱乐场景。",
    "zh-TW": "輸入首影格及尾影格影像以及文字描述生成影像。ViduQ3-Turbo關鍵影格生成影像是一款高性能加速模型。提供極快的生成速度，同時保持高質量視覺效果及動態表現，擅長動作場景、情感渲染及語義理解。性價比高，非常適合社交媒體影像、AI伴侶及特效資產等休閒娛樂場景。",
    "ja-JP": "最初と最後のフレーム画像とテキスト説明を入力してビデオを生成します。ViduQ3-Turboキーフレームからビデオは、高性能な加速モデルです。非常に高速な生成を提供しながら、高品質なビジュアルと動的表現を維持し、アクションシーン、感情表現、意味理解に優れています。コスト効率が高く、ソーシャルメディア画像、AIコンパニオン、特殊効果アセットなどのカジュアルなエンターテインメントシナリオに最適です。",
    "ru-RU": "Введите изображения первого и последнего кадров вместе с текстовым описанием, чтобы сгенерировать видео. ViduQ3-Turbo keyframe-to-video — высокопроизводительная ускоренная модель. Она предлагает чрезвычайно быструю генерацию, сохраняя высокое качество визуальных эффектов и динамическое выражение, превосходя в экшн-сценах, эмоциональном рендеринге и семантическом понимании. Экономична и идеально подходит для развлекательных сценариев, таких как изображения для социальных сетей, AI-компаньоны и активы для спецэффектов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q3 Turbo Start-to-End Video"
    }
   ]
  },
  {
   "slug": "vidu/viduq3-turbo_text2video",
   "model_name": "viduq3-turbo_text2video",
   "display_name": "Vidu Q3 Turbo Text-to-Video",
   "vendor": "vidu",
   "pricing": [
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_second",
       "price": "0.055147"
      }
     },
     "provider_model_id": "vidu/viduq3-turbo_text2video"
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "vidu/viduq3-turbo_text2video"
   ],
   "intro_i18n": {
    "zh-CN": "输入文本提示生成视频。ViduQ3-Turbo文本转视频是高性能加速模型。提供极快的生成速度，同时保持高质量的视觉效果和动态表现，在动作场景、情感渲染和语义理解方面表现出色。性价比高，非常适合社交媒体图片、AI伴侣和特效素材等休闲娱乐场景。",
    "zh-TW": "輸入文字提示生成影像。ViduQ3-Turbo文字生成影像是一款高性能加速模型。提供極快的生成速度，同時保持高質量視覺效果及動態表現，擅長動作場景、情感渲染及語義理解。性價比高，非常適合社交媒體影像、AI伴侶及特效資產等休閒娛樂場景。",
    "ja-JP": "テキストプロンプトを入力してビデオを生成します。ViduQ3-Turboテキストからビデオは、高性能な加速モデルです。非常に高速な生成を提供しながら、高品質なビジュアルと動的表現を維持し、アクションシーン、感情表現、意味理解に優れています。コスト効率が高く、ソーシャルメディア画像、AIコンパニオン、特殊効果アセットなどのカジュアルなエンターテインメントシナリオに最適です。",
    "ru-RU": "Введите текстовую подсказку, чтобы сгенерировать видео. ViduQ3-Turbo text-to-video — высокопроизводительная ускоренная модель. Она предлагает чрезвычайно быструю генерацию, сохраняя высокое качество визуальных эффектов и динамическое выражение, превосходя в экшн-сценах, эмоциональном рендеринге и семантическом понимании. Экономична и идеально подходит для развлекательных сценариев, таких как изображения для социальных сетей, AI-компаньоны и активы для спецэффектов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Vidu Q3 Turbo Text-to-Video"
    }
   ]
  },
  {
   "slug": "voyage/fireworks/models/voyage-4-nano",
   "model_name": "fireworks/models/voyage-4-nano",
   "display_name": "Voyage 4 Nano",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "accounts/fireworks/models/voyage-4-nano"
    }
   ],
   "max_input_tokens": 40960,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/voyage-4-nano"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Voyage 4 Nano"
    }
   ]
  },
  {
   "slug": "voyage/fireworks/models/voyage-multimodal-3-5",
   "model_name": "fireworks/models/voyage-multimodal-3-5",
   "display_name": "Voyage Multimodal 3.5",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "accounts/fireworks/models/voyage-multimodal-3-5"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/voyage-multimodal-3-5"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Voyage Multimodal 3.5"
    }
   ]
  },
  {
   "slug": "voyage/fireworks/models/voyage-rerank-2-5",
   "model_name": "fireworks/models/voyage-rerank-2-5",
   "display_name": "Voyage ReRank 2.5",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "accounts/fireworks/models/voyage-rerank-2-5"
    }
   ],
   "max_input_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/voyage-rerank-2-5"
   ],
   "model_type": "text_rerank",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Voyage ReRank 2.5"
    }
   ]
  },
  {
   "slug": "voyage/rerank-2.5",
   "model_name": "rerank-2.5",
   "display_name": "Voyage Rerank 2.5",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "voyage/rerank-2.5"
    }
   ],
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2025-08-11",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {},
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "voyage/rerank-2.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Voyage Rerank 2.5"
    }
   ]
  },
  {
   "slug": "voyage/rerank-2.5-lite",
   "model_name": "rerank-2.5-lite",
   "display_name": "Voyage Rerank 2.5 Lite",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "voyage/rerank-2.5-lite"
    }
   ],
   "intro": "Reranking model for improving retrieval quality in search and recommendation systems",
   "released_at": "2025-08-11",
   "max_input_tokens": 32000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {},
   "model_type": "text_rerank",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "voyage/rerank-2.5-lite"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Voyage Rerank 2.5 Lite"
    }
   ]
  },
  {
   "slug": "voyage/voyage-3-large",
   "model_name": "voyage-3-large",
   "display_name": "voyage-3-large",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "voyage/voyage-3-large"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2025-01-07",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {},
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "voyage/voyage-3-large"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voyage-3-large"
    }
   ]
  },
  {
   "slug": "voyage/voyage-3.5",
   "model_name": "voyage-3.5",
   "display_name": "voyage-3.5",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "voyage/voyage-3.5"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2025-05-20",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {},
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "voyage/voyage-3.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voyage-3.5"
    }
   ]
  },
  {
   "slug": "voyage/voyage-3.5-lite",
   "model_name": "voyage-3.5-lite",
   "display_name": "voyage-3.5-lite",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "mongodb/voyage-3.5-lite"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "voyage/voyage-3.5-lite"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2025-05-20",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {},
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mongodb/voyage-3.5-lite",
    "voyage/voyage-3.5-lite"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voyage-3.5-lite"
    }
   ]
  },
  {
   "slug": "voyage/voyage-4",
   "model_name": "voyage-4",
   "display_name": "voyage-4",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "accounts/fireworks/models/voyage-4"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "mongodb/voyage-4"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "voyage/voyage-4"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2026-01-15",
   "max_input_tokens": 32000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {
    "open_weights": true
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/voyage-4",
    "mongodb/voyage-4",
    "voyage/voyage-4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voyage-4"
    }
   ]
  },
  {
   "slug": "voyage/voyage-4-large",
   "model_name": "voyage-4-large",
   "display_name": "voyage-4-large",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "accounts/fireworks/models/voyage-4-large"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "mongodb/voyage-4-large"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "voyage/voyage-4-large"
    }
   ],
   "intro": "Flagship model for demanding analysis, coding, and production agent workflows",
   "released_at": "2026-01-15",
   "max_input_tokens": 32000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {
    "open_weights": true
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/voyage-4-large",
    "mongodb/voyage-4-large",
    "voyage/voyage-4-large"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voyage-4-large"
    }
   ]
  },
  {
   "slug": "voyage/voyage-4-lite",
   "model_name": "voyage-4-lite",
   "display_name": "voyage-4-lite",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "provider_model_id": "accounts/fireworks/models/voyage-4-lite"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "voyage/voyage-4-lite"
    }
   ],
   "intro": "Efficient model for low-latency assistance, extraction, and routine automation",
   "released_at": "2026-01-15",
   "max_input_tokens": 32000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {
    "open_weights": true
   },
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/voyage-4-lite",
    "voyage/voyage-4-lite"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voyage-4-lite"
    }
   ]
  },
  {
   "slug": "voyage/voyage-code-2",
   "model_name": "voyage-code-2",
   "display_name": "voyage-code-2",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "voyage/voyage-code-2"
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2024-01-01",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {},
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "voyage/voyage-code-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voyage-code-2"
    }
   ]
  },
  {
   "slug": "voyage/voyage-code-3",
   "model_name": "voyage-code-3",
   "display_name": "voyage-code-3",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "voyage/voyage-code-3"
    }
   ],
   "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks",
   "released_at": "2024-12-04",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {},
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "voyage/voyage-code-3"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voyage-code-3"
    }
   ]
  },
  {
   "slug": "voyage/voyage-finance-2",
   "model_name": "voyage-finance-2",
   "display_name": "voyage-finance-2",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "voyage/voyage-finance-2"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2024-06-03",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {},
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "voyage/voyage-finance-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voyage-finance-2"
    }
   ]
  },
  {
   "slug": "voyage/voyage-law-2",
   "model_name": "voyage-law-2",
   "display_name": "voyage-law-2",
   "vendor": "voyage",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "voyage/voyage-law-2"
    }
   ],
   "intro": "General-purpose chat model for instruction following, writing, and analysis",
   "released_at": "2024-04-15",
   "max_input_tokens": 8192,
   "max_output_tokens": 1536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "voyage",
   "capabilities": {},
   "model_type": "text_embedding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "voyage/voyage-law-2"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "voyage-law-2"
    }
   ]
  },
  {
   "slug": "xai/grk-3",
   "model_name": "grk-3",
   "display_name": "xAI Grok 3",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "pa/grk-3"
    }
   ],
   "intro": "Excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science. Features function calling, structured outputs, and reasoning capabilities.",
   "knowledge_cutoff": "2024-06",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pa/grk-3"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "xAI Grok 3"
    }
   ]
  },
  {
   "slug": "xai/grk-4",
   "model_name": "grk-4",
   "display_name": "xAI Grok 4",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "helicone",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "pa/grk-4",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "1",
        "web_search": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Latest and greatest flagship model, offering unparalleled performance in natural language, math and reasoning - the perfect jack of all trades. Features function calling, structured outputs, and reasoning capabilities.",
   "knowledge_cutoff": "2024-07",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pa/grk-4"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "xAI Grok 4"
    }
   ]
  },
  {
   "slug": "xai/grok-2",
   "model_name": "grok-2",
   "display_name": "grok-2",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "xai/grok-2"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-2"
   ],
   "intro_i18n": {
    "zh-CN": "Grok 2 是一款前沿模型，具备先进的推理能力，强大的对话、编程和推理表现，在 LMSYS 排名中优于 Claude 3.5 Sonnet 和 GPT-4 Turbo。",
    "zh-TW": "Grok 2 是前沿模型，具備最先進的推理能力，擅長聊天、編碼與推理，在 LMSYS 排名中超越 Claude 3.5 Sonnet 與 GPT-4 Turbo。",
    "ja-JP": "Grok 2は、最先端の推論力、優れたチャット、コーディング、推論性能を備えた先進モデルで、LMSYSにおいてClaude 3.5 SonnetやGPT-4 Turboを上回る評価を得ています。",
    "ru-RU": "Grok 2 — передовая модель с передовыми возможностями рассуждения, чата и программирования, превосходящая Claude 3.5 Sonnet и GPT-4 Turbo по LMSYS."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-2-1212",
   "model_name": "grok-2-1212",
   "display_name": "grok-2-1212",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "x-ai/grok-2-1212"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-2-1212"
   ]
  },
  {
   "slug": "xai/grok-2-image",
   "model_name": "grok-2-image",
   "display_name": "grok-2-image",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-2-image"
    }
   ]
  },
  {
   "slug": "xai/grok-2-image-1212",
   "model_name": "grok-2-image-1212",
   "display_name": "grok-2-image-1212",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-2-image-1212"
    }
   ]
  },
  {
   "slug": "xai/grok-2-image-latest",
   "model_name": "grok-2-image-latest",
   "display_name": "grok-2-image-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.07"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-2-image-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-2-latest",
   "model_name": "grok-2-latest",
   "display_name": "grok-2-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "xai/grok-2-vision",
   "model_name": "grok-2-vision",
   "display_name": "grok-2-vision",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000002"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15.57"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "xai/grok-2-vision"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "xai/grok-2-vision"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-08-20",
   "knowledge_cutoff": "2024-08",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-2-vision"
   ],
   "intro_i18n": {
    "zh-CN": "Grok 2 Vision 擅长视觉任务，在视觉数学推理（MathVista）和文档问答（DocVQA）方面表现卓越，支持文档、图表、截图和照片等多种图像类型。",
    "zh-TW": "Grok 2 Vision 擅長視覺任務，在視覺數學推理（MathVista）與文件問答（DocVQA）上表現領先。可處理文件、圖表、截圖與照片。",
    "ja-JP": "Grok 2 Visionは視覚タスクに優れ、MathVistaによる視覚的数学推論やDocVQAによる文書QAで最先端の性能を発揮します。文書、チャート、グラフ、スクリーンショット、写真を処理可能です。",
    "ru-RU": "Grok 2 Vision превосходно справляется с визуальными задачами, демонстрируя передовые результаты в визуальном математическом рассуждении (MathVista) и вопросах по документам (DocVQA). Обрабатывает документы, диаграммы, графики, скриншоты и фотографии."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "prompt_caching: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "xai/grok-2-vision-1212",
   "model_name": "grok-2-vision-1212",
   "display_name": "grok-2-vision-1212",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000002"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     },
     "provider_model_id": "x-ai/grok-2-vision-1212"
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "deprecated": true,
   "model_type": "vision_understanding",
   "deprecation_date": "2026-02-28",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "web_search": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2024-12-12",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-2-vision-1212"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-2-vision-latest",
   "model_name": "grok-2-vision-latest",
   "display_name": "grok-2-vision-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000002"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "web_search": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "xai/grok-3",
   "model_name": "grok-3",
   "display_name": "grok-3",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+helicone-registry+llmdb+pricetoken+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "azure_ai/global/grok-3"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "xai/grok-3"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.25"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "x-ai/grok-3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "x-ai/grok-3"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "xai/grok-3"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "xai/grok-3"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "xai/grok-3"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "xai/grok-3"
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-05-15",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science. Features function calling, structured outputs, and reasoning capabilities.",
   "knowledge_cutoff": "2024-06",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "released_at": "2025-02-17",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "azure_ai/global/grok-3",
    "x-ai/grok-3",
    "xai/grok-3"
   ],
   "intro_i18n": {
    "zh-CN": "xAI 的 Grok 3 —— 具备强大推理能力的模型。",
    "zh-TW": "xAI Grok 3 —— 擁有強大推理能力。",
    "ja-JP": "xAIのGrok 3は、強力な推論能力を備えています。",
    "ru-RU": "Grok 3 от xAI — модель с высокой способностью к рассуждениям."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-3-beta",
   "model_name": "grok-3-beta",
   "display_name": "grok-3-beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "x-ai/grok-3-beta"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "x-ai/grok-3-beta"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "x-ai/grok-3-beta"
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "deprecated": true,
   "released_at": "2025-04-09",
   "knowledge_cutoff": "2024-11",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-3-beta"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "xai/grok-3-deepsearch",
   "model_name": "grok-3-deepsearch",
   "display_name": "grok-3-deepsearch",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.13"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "grok-3-deepsearch"
    }
   ]
  },
  {
   "slug": "xai/grok-3-fast",
   "model_name": "grok-3-fast",
   "display_name": "Grok 3 Fast",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.77"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "38.88"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "xai/grok-3-fast"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      }
     },
     "provider_model_id": "xai/grok-3-fast"
    }
   ],
   "max_input_tokens": 131072,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "vision": true
   },
   "released_at": "2025-02-17",
   "knowledge_cutoff": "2024-11",
   "max_output_tokens": 8192,
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-3-fast"
   ],
   "intro_i18n": {
    "zh-CN": "xAI 的旗舰模型，擅长企业场景如数据提取、编程和摘要，具备金融、医疗、法律和科学等领域的深度知识。快速版本运行在更快的基础设施上，响应速度更快但每个 token 成本更高。",
    "zh-TW": "xAI 的旗艦模型，擅長企業應用如資料擷取、編碼與摘要，具備金融、醫療、法律與科學等領域的深度知識。快速版本運行於更快基礎設施，回應速度更快但每字成本較高。",
    "ja-JP": "xAIのフラッグシップモデルで、データ抽出、コーディング、要約などのエンタープライズ用途に優れ、金融、医療、法律、科学分野における深い専門知識を備えています。高速バリアントは高速インフラ上で動作し、より迅速な応答を提供します（トークン単価は高め）。",
    "ru-RU": "Флагманская модель xAI, превосходно подходящая для корпоративных задач, таких как извлечение данных, программирование и суммирование, с глубокими знаниями в области финансов, здравоохранения, права и науки. Быстрая версия работает на ускоренной инфраструктуре для более быстрых ответов при более высокой стоимости за токен."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 3 Fast"
    }
   ]
  },
  {
   "slug": "xai/grok-3-fast-beta",
   "model_name": "grok-3-fast-beta",
   "display_name": "grok-3-fast-beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "27.5"
      }
     }
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-3-fast-latest",
   "model_name": "grok-3-fast-latest",
   "display_name": "grok-3-fast-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-02-17",
   "knowledge_cutoff": "2024-11",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-3-latest",
   "model_name": "grok-3-latest",
   "display_name": "grok-3-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-02-17",
   "knowledge_cutoff": "2024-11",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini",
   "model_name": "grok-3-mini",
   "display_name": "grok-3-mini",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+helicone-registry+llmdb+pricetoken+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.27"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.27"
      }
     },
     "provider_model_id": "azure_ai/global/grok-3-mini"
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "github-models",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "xai/grok-3-mini"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "pa/grok-3-mini"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.285"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.475"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "x-ai/grok-3-mini"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "x-ai/grok-3-mini"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "xai/grok-3-mini"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "xai/grok-3-mini"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "xai/grok-3-mini"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "xai/grok-3-mini"
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-02-28",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. Features function calling, structured outputs, and reasoning capabilities.",
   "knowledge_cutoff": "2024-06",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "released_at": "2025-02-17",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "azure_ai/global/grok-3-mini",
    "pa/grok-3-mini",
    "x-ai/grok-3-mini",
    "xai/grok-3-mini"
   ],
   "intro_i18n": {
    "zh-CN": "xAI 的 Grok 3 Mini —— 推理强、响应快的小型模型。",
    "zh-TW": "xAI Grok 3 Mini —— 具備強大推理與快速回應能力。",
    "ja-JP": "xAIのGrok 3 Miniは、強力な推論能力と高速応答を備えています。",
    "ru-RU": "Grok 3 Mini от xAI — модель с сильными возможностями рассуждения и быстрыми ответами."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini-beta",
   "model_name": "grok-3-mini-beta",
   "display_name": "grok-3-mini-beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5511"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "x-ai/grok-3-mini-beta"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      }
     },
     "provider_model_id": "x-ai/grok-3-mini-beta"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "x-ai/grok-3-mini-beta"
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-02-28",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-04-09",
   "knowledge_cutoff": "2024-11",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-3-mini-beta"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini-fast",
   "model_name": "grok-3-mini-fast",
   "display_name": "grok-3-mini-fast",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.93"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.21"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "xai/grok-3-mini-fast"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "xai/grok-3-mini-fast"
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-02-17",
   "knowledge_cutoff": "2024-11",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-3-mini-fast"
   ],
   "intro_i18n": {
    "zh-CN": "xAI 的轻量模型，在回答前进行思考，适用于简单或基于逻辑的任务，无需深度领域知识。提供原始推理轨迹。快速版本运行在更快的基础设施上，响应速度更快但每个 token 成本更高。",
    "zh-TW": "xAI 的輕量模型，在回應前會進行思考，適合簡單或邏輯型任務，不需深度領域知識。提供原始推理軌跡。快速版本運行於更快基礎設施，回應速度更快但每字成本較高。",
    "ja-JP": "xAIの軽量モデルで、応答前に思考を行い、シンプルまたは論理ベースのタスクに最適です。生の推論トレースが利用可能です。高速バリアントは高速インフラ上で動作し、より迅速な応答を提供します（トークン単価は高め）。",
    "ru-RU": "Легковесная модель xAI, которая «думает» перед ответом, идеально подходит для простых или логических задач без необходимости в глубоких знаниях. Доступны необработанные следы рассуждений. Быстрая версия работает на ускоренной инфраструктуре для более быстрых ответов при более высокой стоимости за токен."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini-fast-beta",
   "model_name": "grok-3-mini-fast-beta",
   "display_name": "grok-3-mini-fast-beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.33"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.20011"
      }
     }
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini-fast-high",
   "model_name": "grok-3-mini-fast-high",
   "display_name": "grok-3-mini-fast-high",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-3-mini-fast-high"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini-fast-high-beta",
   "model_name": "grok-3-mini-fast-high-beta",
   "display_name": "grok-3-mini-fast-high-beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-3-mini-fast-high-beta"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini-fast-latest",
   "model_name": "grok-3-mini-fast-latest",
   "display_name": "grok-3-mini-fast-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true,
    "stream": true
   },
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-02-17",
   "knowledge_cutoff": "2024-11",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini-high",
   "model_name": "grok-3-mini-high",
   "display_name": "grok-3-mini-high",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-3-mini-high"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini-high-beta",
   "model_name": "grok-3-mini-high-beta",
   "display_name": "grok-3-mini-high-beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-3-mini-high-beta"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini-latest",
   "model_name": "grok-3-mini-latest",
   "display_name": "grok-3-mini-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.075"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://x.ai/api#pricing",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-02-17",
   "knowledge_cutoff": "2024-11",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini:high",
   "model_name": "grok-3-mini:high",
   "display_name": "xai/grok-3-mini:high",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "xai/grok-3-mini:high"
    }
   ],
   "released_at": "2025-10-16",
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-3-mini:high"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "xai/grok-3-mini:high"
    }
   ]
  },
  {
   "slug": "xai/grok-3-mini:low",
   "model_name": "grok-3-mini:low",
   "display_name": "xai/grok-3-mini:low",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "xai/grok-3-mini:low"
    }
   ],
   "released_at": "2025-10-16",
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-3-mini:low"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "xai/grok-3-mini:low"
    }
   ]
  },
  {
   "slug": "xai/grok-3-reasoner",
   "model_name": "grok-3-reasoner",
   "display_name": "grok-3-reasoner",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.13"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "grok-3-reasoner"
    }
   ]
  },
  {
   "slug": "xai/grok-4",
   "model_name": "grok-4",
   "display_name": "grok-4",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+helicone-registry+llmdb+pricetoken+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "1",
        "web_search": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.825"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "x-ai/grok-4"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "x-ai/grok-4"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "litellm+truefoundry+helicone-registry+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "x-ai/grok-4",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "xai/grok-4"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "xai/grok-4"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "xai/grok-4"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "xai/grok-4"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "x-ai/grok-4"
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Latest and greatest flagship model, offering unparalleled performance in natural language, math and reasoning - the perfect jack of all trades. Features function calling, structured outputs, and reasoning capabilities.",
   "knowledge_cutoff": "2024-07",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "released_at": "2025-07-09",
   "family": "grok",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-4",
    "xai/grok-4"
   ],
   "intro_i18n": {
    "zh-CN": "xAI 最新旗舰模型，在自然语言、数学和推理方面表现卓越，是理想的全能型模型。",
    "zh-TW": "xAI 最新旗艦模型，在自然語言、數學與推理方面表現卓越，是理想的全能型選擇。",
    "ja-JP": "xAIの最新フラッグシップモデルで、自然言語、数学、推論において比類なき性能を発揮する万能モデルです。",
    "ru-RU": "Новейшая флагманская модель xAI с непревзойденной производительностью в области естественного языка, математики и рассуждений — универсальный лидер."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "parallel_function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "xai/grok-4-0709",
   "model_name": "grok-4-0709",
   "display_name": "grok-4-0709",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "13.5"
      }
     }
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-15",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-07-09",
   "knowledge_cutoff": "2025-07",
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "xAI 的 Grok 4，具备强大的推理能力。",
    "zh-TW": "xAI 的 Grok 4，具備強大的推理能力。",
    "ja-JP": "xAI による Grok 4 は、強力な推論能力を備えています。",
    "ru-RU": "Grok 4 от xAI с мощными логическими возможностями."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4-1-fast",
   "model_name": "grok-4-1-fast",
   "display_name": "grok-4-1-fast",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+llmdb+pricetoken",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "grok-4.1-fast",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "x-ai/grok-4.1-fast"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "x-ai/grok-4.1-fast"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "x-ai/grok-4.1-fast"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-4.1-fast"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "x-ai/grok-4.1-fast"
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-11-19",
   "knowledge_cutoff": "2025-07",
   "family": "grok",
   "intro": "Fast Grok model for responsive chat, reasoning, and tool-assisted work",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4.1-fast",
    "x-ai/grok-4.1-fast"
   ],
   "intro_i18n": {
    "zh-CN": "Grok 4 Fast 是 xAI 推出的高吞吐、低成本模型（支持 2M 上下文窗口），适用于高并发和长上下文场景。",
    "zh-TW": "Grok 4.1 Fast 是 xAI 推出的高吞吐、低成本模型（支援 2M 上下文），適用於高併發與長上下文應用場景。",
    "ja-JP": "Grok 4.1 Fastは、xAIによる高スループット・低コストモデルで、2Mのコンテキストウィンドウをサポートし、高並列性および長文コンテキストのユースケースに最適です。",
    "ru-RU": "Grok 4 Fast — это высокопроизводительная, недорогая модель от xAI (поддерживает контекст до 2M), идеально подходящая для сценариев с высокой конкуренцией и длинным контекстом."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "xai/grok-4-1-fast-non-reasoning",
   "model_name": "grok-4-1-fast-non-reasoning",
   "display_name": "grok-4-1-fast-non-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "grok-4.1-fast-non-reasoning"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "grok-4.1-fast-non-reasoning"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "xai/grok-4.1-fast-non-reasoning",
     "region": "global"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19999999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.049999999999999996"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "pa/grok-4-1-fast-non-reasoning"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "perplexity-agent",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "xai/grok-4-1-fast-non-reasoning"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.202"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5051"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0505"
      }
     },
     "provider_model_id": "xai/grok-4.1-fast-non-reasoning"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4-1-fast-non-reasoning"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "xai/grok-4-1-fast-non-reasoning"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "xai/grok-4.1-fast-non-reasoning"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "x-ai/grok-4.1-fast-non-reasoning"
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-15",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "image_output": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "A frontier multimodal model optimized specifically for high-performance agentic tool calling.",
   "knowledge_cutoff": "2025-11",
   "parameters": {
    "supported": [
     "logprobs",
     "max_tokens",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "released_at": "2025-11-19",
   "family": "grok",
   "status": "beta",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4.1-fast-non-reasoning",
    "pa/grok-4-1-fast-non-reasoning",
    "x-ai/grok-4.1-fast-non-reasoning",
    "xai/grok-4-1-fast-non-reasoning",
    "xai/grok-4.1-fast-non-reasoning"
   ],
   "intro_i18n": {
    "zh-CN": "Grok 4 Fast（非推理版）是 xAI 推出的高吞吐、低成本多模态模型（支持 2M 上下文窗口），适用于对延迟和成本敏感但不需要模型内推理的场景。可通过 API 的 reasoning 参数启用推理功能。提示词和生成内容可能被 xAI 或 OpenRouter 用于改进未来模型。",
    "zh-TW": "Grok 4.1 Fast（非推理版）是 xAI 推出的高吞吐、低成本多模態模型（支援 2M 上下文），適用於對延遲與成本敏感但不需模型內推理的場景。可透過 API 的 reasoning 參數啟用推理功能。提示與完成可能被 xAI 或 OpenRouter 用於改進未來模型。",
    "ja-JP": "Grok 4.1 Fast（非推論）は、xAIによる高スループット・低コストのマルチモーダルモデルで、2Mのコンテキストウィンドウをサポートし、レイテンシやコストに敏感な推論不要のシナリオに最適です。必要に応じてAPIのreasoningパラメータで推論を有効化できます。プロンプトと出力は、xAIまたはOpenRouterによって将来のモデル改善に使用される可能性があります。",
    "ru-RU": "Grok 4 Fast (без рассуждений) — это высокопроизводительная, недорогая мультимодальная модель от xAI (поддерживает контекст до 2M), предназначенная для сценариев, чувствительных к задержке и стоимости, не требующих встроенного рассуждения. Рассуждение можно включить через параметр reasoning в API. Подсказки и ответы могут использоваться xAI или OpenRouter для улучшения будущих моделей."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4-1-fast-non-reasoning-latest",
   "model_name": "grok-4-1-fast-non-reasoning-latest",
   "display_name": "grok-4-1-fast-non-reasoning-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-15",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "web_search": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "xai/grok-4-1-fast-reasoning",
   "model_name": "grok-4-1-fast-reasoning",
   "display_name": "grok-4-1-fast-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "1",
        "web_search": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "grok-4.1-fast-reasoning"
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "grok-4.1-fast-reasoning"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "xai/grok-4.1-fast-reasoning",
     "region": "global"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19999999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.049999999999999996"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "pa/grok-4-1-fast-reasoning",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "1",
        "web_search": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.202"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5051"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0505"
      }
     },
     "provider_model_id": "xai/grok-4.1-fast-reasoning"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4-1-fast-reasoning"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "xai/grok-4-1-fast-reasoning"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "xai/grok-4.1-fast-reasoning"
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-15",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "A frontier multimodal model optimized for high-performance agentic tool calling with reasoning capabilities.",
   "knowledge_cutoff": "2025-11",
   "parameters": {
    "supported": [
     "logprobs",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "released_at": "2025-11-19",
   "family": "grok",
   "status": "beta",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4.1-fast-reasoning",
    "pa/grok-4-1-fast-reasoning",
    "x-ai/grok-4.1-fast-reasoning",
    "xai/grok-4-1-fast-reasoning",
    "xai/grok-4.1-fast-reasoning"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4-1-fast-reasoning-latest",
   "model_name": "grok-4-1-fast-reasoning-latest",
   "display_name": "grok-4-1-fast-reasoning-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-15",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "structured_output": true,
    "web_search": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   }
  },
  {
   "slug": "xai/grok-4-128k",
   "model_name": "grok-4-128k",
   "display_name": "Grok 4",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "30"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4"
    }
   ]
  },
  {
   "slug": "xai/grok-4-20",
   "model_name": "grok-4-20",
   "display_name": "Grok 4.20",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+pricetoken+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "grok-4.20"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-4.20"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "x-ai/grok-4.20"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "x-ai/grok-4.20"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.83"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.992958",
        "completion": "2.003534",
        "cache_read": "1.956522"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "max_output_tokens": 128000,
   "family": "grok",
   "knowledge_cutoff": "2025-09",
   "parameters": {
    "supported": [
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4.20",
    "x-ai/grok-4.20"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.20"
    }
   ]
  },
  {
   "slug": "xai/grok-4-20-multi-agent",
   "model_name": "grok-4-20-multi-agent",
   "display_name": "grok-4.20-multi-agent",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "grok-4.20-multi-agent"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "grok-4.20-multi-agent"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-4.20-multi-agent"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "x-ai/grok-4.20-multi-agent"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "x-ai/grok-4.20-multi-agent",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.8",
        "completion": "1.2"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4.20-multi-agent"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.83"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.992958",
        "completion": "2.003534",
        "cache_read": "1.956522"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "xai/grok-4.20-multi-agent",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true,
    "web_search": true
   },
   "released_at": "2026-03-09",
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "max_output_tokens": 2000000,
   "family": "grok",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "knowledge_cutoff": "2025-09",
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4.20-multi-agent",
    "x-ai/grok-4.20-multi-agent",
    "xai/grok-4.20-multi-agent"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-multi-agent"
    }
   ]
  },
  {
   "slug": "xai/grok-4-20-non-reasoning",
   "model_name": "grok-4-20-non-reasoning",
   "display_name": "grok-4.20-non-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "grok-4.20-non-reasoning",
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "grok-4.20-non-reasoning"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "xai/grok-4.20-non-reasoning",
     "region": "global"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "xai/grok-4.20-non-reasoning",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "vision": true,
    "reasoning": true,
    "pdf_input": true,
    "web_search": true
   },
   "released_at": "2026-03-09",
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "max_output_tokens": 2000000,
   "family": "grok",
   "knowledge_cutoff": "2025-09",
   "status": "beta",
   "docs_url": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4.20-non-reasoning",
    "xai/grok-4.20-non-reasoning"
   ],
   "intro_i18n": {
    "zh-CN": "无推理模式版本，适用于简单场景。",
    "zh-TW": "不具推理功能的版本，適用於簡單使用情境。",
    "ja-JP": "単純なユースケース向けの非推論バリアント。",
    "ru-RU": "Вариант без рассуждений для простых задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-non-reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4-20-reasoning",
   "model_name": "grok-4-20-reasoning",
   "display_name": "grok-4.20-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "grok-4.20-reasoning"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "grok-4.20-reasoning"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "xai/grok-4.20-reasoning",
     "region": "global"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "xai/grok-4.20-reasoning",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true,
    "web_search": true
   },
   "released_at": "2026-03-09",
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "max_output_tokens": 2000000,
   "family": "grok",
   "knowledge_cutoff": "2025-09",
   "status": "beta",
   "docs_url": "https://docs.x.ai/docs/models (Vertex AI Model Garden)",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4.20-reasoning",
    "xai/grok-4.20-reasoning"
   ],
   "intro_i18n": {
    "zh-CN": "智能、高速的推理模型，先思考后回答。",
    "zh-TW": "智慧、極速的模型，會先思考再作答。",
    "ja-JP": "応答前に推論する知的で超高速なモデル。",
    "ru-RU": "Интеллектуальная, сверхбыстрая модель, которая размышляет перед тем, как ответить."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4-fast",
   "model_name": "grok-4-fast",
   "display_name": "Grok 4 Fast Reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+helicone-registry+llmdb+llm-prices-www",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "1",
        "web_search": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.38"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "x-ai/grok-4-fast"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "x-ai/grok-4-fast"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "x-ai/grok-4-fast",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4-fast"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "x-ai/grok-4-fast"
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "web_search": true,
    "stream": true,
    "pdf_input": true,
    "audio_input": true,
    "video_input": true
   },
   "intro": "Grok 4 Fast is xAI's latest advancement in cost-efficient reasoning models. Built on xAI’s learnings from Grok 4, Grok 4 Fast delivers frontier-level performance across Enterprise and Consumer domains—with exceptional token efficiency. This model pushes the boundaries for smaller and faster AI, making high-quality reasoning accessible to more users and developers. Grok 4 Fast features state-of-the-art (SOTA) cost-efficiency, cutting-edge web and X search capabilities, a 2M token context window, and a unified architecture that blends reasoning and non-reasoning modes in one model.",
   "knowledge_cutoff": "2025-09",
   "max_output_tokens": 2000000,
   "parameters": {
    "supported": [
     "logprobs",
     "max_tokens",
     "reasoning",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "released_at": "2025-09-19",
   "family": "grok",
   "deprecated": true,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-4-fast",
    "x-ai/grok-4-fast:free",
    "xai/grok-4-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4 Fast Reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4-fast-128k",
   "model_name": "grok-4-fast-128k",
   "display_name": "Grok 4 Fast",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4 Fast"
    }
   ]
  },
  {
   "slug": "xai/grok-4-fast-non-reasoning",
   "model_name": "grok-4-fast-non-reasoning",
   "display_name": "grok-4-fast-non-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19999999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.049999999999999996"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "pa/grok-4-fast-non-reasoning"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "xai/grok-4-fast-non-reasoning"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4-fast-non-reasoning"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "xai/grok-4-fast-non-reasoning"
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-15",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Grok 4 Fast is xAI's latest advancement in cost-efficient reasoning models. Built on xAI’s learnings from Grok 4, Grok 4 Fast delivers frontier-level performance across Enterprise and Consumer domains—with exceptional token efficiency. This model pushes the boundaries for smaller and faster AI, making high-quality reasoning accessible to more users and developers. Grok 4 Fast features state-of-the-art (SOTA) cost-efficiency, cutting-edge web and X search capabilities, a 2M token context window. This non-reasoning model specifically excludes reasoning capabilities.",
   "knowledge_cutoff": "2025-09",
   "parameters": {
    "supported": [
     "logprobs",
     "max_tokens",
     "response_format",
     "seed",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "released_at": "2025-09-21",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pa/grok-4-fast-non-reasoning",
    "x-ai/grok-4-fast-non-reasoning",
    "xai/grok-4-fast-non-reasoning"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4-fast-non-reasoning-latest",
   "model_name": "grok-4-fast-non-reasoning-latest",
   "display_name": "grok-4-fast-non-reasoning-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4-fast-non-reasoning-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4-fast-reasoning",
   "model_name": "grok-4-fast-reasoning",
   "display_name": "grok-4-fast-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+llmdb+llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "models-dev+litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19999999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.049999999999999996"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "25"
      }
     },
     "provider_model_id": "pa/grok-4-fast-reasoning",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "1",
        "web_search": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     }
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "xai/grok-4-fast-reasoning"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "xai/grok-4-fast-reasoning"
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-05-15",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-09-21",
   "knowledge_cutoff": "2024-11",
   "intro": "Fast Grok model for responsive chat, reasoning, and tool-assisted work",
   "family": "grok",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pa/grok-4-fast-reasoning",
    "x-ai/grok-4-fast-reasoning",
    "xai/grok-4-fast-reasoning"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4-fast-reasoning-128k",
   "model_name": "grok-4-fast-reasoning-128k",
   "display_name": "Grok 4 Fast Reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "llm-prices-www",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4 Fast Reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4-fast-reasoning-latest",
   "model_name": "grok-4-fast-reasoning-latest",
   "display_name": "grok-4-fast-reasoning-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4-fast-reasoning-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4-latest",
   "model_name": "grok-4-latest",
   "display_name": "grok-4-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.333333",
        "completion": "0.2"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "web_search": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4.1",
   "model_name": "grok-4.1",
   "display_name": "grok-4.1",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "released_at": "2025-11-18",
   "knowledge_cutoff": "2025-06",
   "max_input_tokens": 200000,
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.1"
    }
   ]
  },
  {
   "slug": "xai/grok-4.2",
   "model_name": "grok-4.2",
   "display_name": "grok-4.2",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.47"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.42"
      }
     }
    }
   ],
   "released_at": "2026-07-09",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "listed",
     "note": "grok-4.2"
    }
   ]
  },
  {
   "slug": "xai/grok-4.2-beta",
   "model_name": "grok-4.2-beta",
   "display_name": "xai/grok-4.2-beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "xai/grok-4.2-beta"
    }
   ],
   "released_at": "2026-03-19",
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-4.2-beta"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "xai/grok-4.2-beta"
    }
   ]
  },
  {
   "slug": "xai/grok-4.2-fast",
   "model_name": "grok-4.2-fast",
   "display_name": "Grok 4.2 Fast",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "x-ai/grok-4.2-fast",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.333333",
        "prompt": "1.333333"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Fast Grok model for responsive chat, reasoning, and tool-assisted work",
   "released_at": "2026-03-20",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 2000000,
   "max_output_tokens": 30000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-4.2-fast"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.2 Fast"
    }
   ]
  },
  {
   "slug": "xai/grok-4.2-fast-non-reasoning",
   "model_name": "grok-4.2-fast-non-reasoning",
   "display_name": "Grok 4.2 Fast Non Reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "x-ai/grok-4.2-fast-non-reasoning",
     "tracks": [
      {
       "label": ">128K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.333333",
        "prompt": "1.333333"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 128000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Fast Grok model for responsive chat, reasoning, and tool-assisted work",
   "released_at": "2026-03-20",
   "knowledge_cutoff": "2025-08",
   "max_input_tokens": 2000000,
   "max_output_tokens": 30000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-4.2-fast-non-reasoning"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.2 Fast Non Reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-0309",
   "model_name": "grok-4.20-0309",
   "display_name": "grok-4.20-0309",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.33"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-0309"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-0309-non-reasoning",
   "model_name": "grok-4.20-0309-non-reasoning",
   "display_name": "Grok 4.20 (Non-Reasoning)",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "models-dev+truefoundry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.7"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4.20-0309-non-reasoning"
    }
   ],
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "released_at": "2026-03-09",
   "max_input_tokens": 1000000,
   "max_output_tokens": 30000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-4.20-0309-non-reasoning"
   ],
   "intro_i18n": {
    "zh-CN": "无推理模式版本，适用于简单场景。",
    "zh-TW": "不具推理功能的版本，適用於簡單使用情境。",
    "ja-JP": "単純なユースケース向けの非推論バリアント。",
    "ru-RU": "Вариант без рассуждений для простых задач."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "tetrate",
     "charge": "completion",
     "old": "6",
     "new": "2.5"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "tetrate",
     "charge": "prompt",
     "old": "2",
     "new": "1.25"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-0309-reasoning",
   "model_name": "grok-4.20-0309-reasoning",
   "display_name": "Grok 4.20 (Reasoning)",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.7"
      }
     }
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4.20-0309-reasoning",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4.20-0309-reasoning"
    }
   ],
   "intro": "Reasoning Grok for document-heavy analysis and long-horizon tool use",
   "released_at": "2026-03-09",
   "max_input_tokens": 1000000,
   "max_output_tokens": 30000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true
   },
   "docs_url": "https://docs.x.ai/docs/models",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-4.20-0309-reasoning"
   ],
   "intro_i18n": {
    "zh-CN": "智能、高速的推理模型，先思考后回答。",
    "zh-TW": "智慧、極速的模型，會先思考再作答。",
    "ja-JP": "応答前に推論する知的で超高速なモデル。",
    "ru-RU": "Интеллектуальная, сверхбыстрая модель, которая размышляет перед тем, как ответить."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "tetrate",
     "charge": "completion",
     "old": "6",
     "new": "2.5"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "tetrate",
     "charge": "prompt",
     "old": "2",
     "new": "1.25"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-beta",
   "model_name": "grok-4.20-beta",
   "display_name": "grok-4.20-beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-4.20-beta"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "x-ai/grok-4.20-beta",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "x-ai/grok-4.20-beta"
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "deprecated": true,
   "max_output_tokens": 0,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-4.20-beta"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-beta"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-beta-0309",
   "model_name": "grok-4.20-beta-0309",
   "display_name": "grok-4.20-beta-0309",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-beta-0309"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-beta-0309-non-reasoning",
   "model_name": "grok-4.20-beta-0309-non-reasoning",
   "display_name": "grok-4.20-beta-0309-non-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.3125",
        "completion": "0.208333"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "grok-4-20-beta-0309-non-reasoning",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.25",
        "completion": "0.833333",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-03-09",
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4-20-beta-0309-non-reasoning"
   ],
   "intro_i18n": {
    "zh-CN": "适用于简单用例的非推理版本",
    "zh-TW": "適用於簡單使用場景的非推理版本",
    "ja-JP": "シンプルなユースケース向けの非推論型バリアント。",
    "ru-RU": "Вариант без рассуждений для простых случаев использования."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "reasoning: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-beta-0309-reasoning",
   "model_name": "grok-4.20-beta-0309-reasoning",
   "display_name": "grok-4.20-beta-0309-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "grok-4-20-beta-0309-reasoning",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.25",
        "completion": "0.833333",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-03-09",
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4-20-beta-0309-reasoning"
   ],
   "intro_i18n": {
    "zh-CN": "智能且极速的模型，在响应前进行推理",
    "zh-TW": "智能且極速的模型，在回應前進行推理",
    "ja-JP": "応答前に推論を行う、知的で超高速なモデル。",
    "ru-RU": "Интеллектуальная, сверхбыстрая модель, которая рассуждает перед ответом."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-beta-latest",
   "model_name": "grok-4.20-beta-latest",
   "display_name": "grok-4.20-beta-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-beta-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-beta-latest-non-reasoning",
   "model_name": "grok-4.20-beta-latest-non-reasoning",
   "display_name": "grok-4.20-beta-latest-non-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "vision": true,
    "reasoning": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-beta-latest-non-reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-beta-latest-reasoning",
   "model_name": "grok-4.20-beta-latest-reasoning",
   "display_name": "grok-4.20-beta-latest-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-beta-latest-reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-beta-non-reasoning",
   "model_name": "grok-4.20-beta-non-reasoning",
   "display_name": "grok-4.20-beta-non-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "vision": true,
    "reasoning": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-beta-non-reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-beta-reasoning",
   "model_name": "grok-4.20-beta-reasoning",
   "display_name": "grok-4.20-beta-reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-beta-reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-experimental-beta-0304",
   "model_name": "grok-4.20-experimental-beta-0304",
   "display_name": "grok-4.20-experimental-beta-0304",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "vision": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-experimental-beta-0304"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-experimental-beta-0304-non-reasoning",
   "model_name": "grok-4.20-experimental-beta-0304-non-reasoning",
   "display_name": "Grok 4.20 (Experimental, Non-Reasoning)",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+llmdb+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "vision": true,
    "stream": true,
    "pdf_input": true,
    "reasoning": true
   },
   "released_at": "2026-03-04",
   "max_output_tokens": 30000,
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.20 (Experimental, Non-Reasoning)"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-experimental-beta-0304-reasoning",
   "model_name": "grok-4.20-experimental-beta-0304-reasoning",
   "display_name": "Grok 4.20 (Experimental, Reasoning)",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+llmdb+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "prompt_caching": true,
    "stream": true,
    "pdf_input": true
   },
   "released_at": "2026-03-04",
   "max_output_tokens": 30000,
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.20 (Experimental, Reasoning)"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-experimental-beta-latest",
   "model_name": "grok-4.20-experimental-beta-latest",
   "display_name": "grok-4.20-experimental-beta-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-experimental-beta-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-experimental-beta-non-reasoning-latest",
   "model_name": "grok-4.20-experimental-beta-non-reasoning-latest",
   "display_name": "grok-4.20-experimental-beta-non-reasoning-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "vision": true,
    "reasoning": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-experimental-beta-non-reasoning-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-experimental-beta-reasoning-latest",
   "model_name": "grok-4.20-experimental-beta-reasoning-latest",
   "display_name": "grok-4.20-experimental-beta-reasoning-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-experimental-beta-reasoning-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-multi-agent-0309",
   "model_name": "grok-4.20-multi-agent-0309",
   "display_name": "Grok 4.20 Multi-Agent",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "models-dev+truefoundry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.7"
      }
     }
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4.20-multi-agent-0309"
    }
   ],
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "released_at": "2026-03-09",
   "max_input_tokens": 1000000,
   "max_output_tokens": 30000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-4.20-multi-agent-0309"
   ],
   "intro_i18n": {
    "zh-CN": "由 4 至 16 个 Agent 组成的团队，擅长科研类任务。目前不支持客户端工具，只支持 xAI 服务器端工具（如 X Search、Web Search）及远程 MCP 工具。",
    "zh-TW": "由 4 或 16 個代理組成的團隊，擅長研究類任務。目前不支援客戶端工具，只支援 xAI 伺服器端工具（如 X Search、Web Search）及遠端 MCP 工具。",
    "ja-JP": "4または16のエージェントチーム。研究ユースケースに優れています。現在、クライアントサイドツールはサポートしていません。xAIサーバーサイドツール（例：X Search、Web Searchツール）およびリモートMCPツールのみをサポートします。",
    "ru-RU": "Команда из 4 или 16 агентов. Превосходна для исследовательских задач. Пока не поддерживает клиентские инструменты. Поддерживает только серверные инструменты xAI (например, X Search, Web Search) и удалённые MCP-инструменты."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "tetrate",
     "charge": "completion",
     "old": "6",
     "new": "2.5"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "tetrate",
     "charge": "prompt",
     "old": "2",
     "new": "1.25"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "function_calling: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-multi-agent-beta",
   "model_name": "grok-4.20-multi-agent-beta",
   "display_name": "Grok 4.20 Multi Agent Beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "x-ai/grok-4.20-multi-agent-beta",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "xai/grok-4.20-multi-agent-beta",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "released_at": "2026-03-11",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true
   },
   "deprecated": true,
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-4.20-multi-agent-beta",
    "xai/grok-4.20-multi-agent-beta"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.20 Multi Agent Beta"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-multi-agent-beta-0309",
   "model_name": "grok-4.20-multi-agent-beta-0309",
   "display_name": "grok-4.20-multi-agent-beta-0309",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "image_output": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-03-09",
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-multi-agent-beta-0309-exp-ma",
   "model_name": "grok-4.20-multi-agent-beta-0309-exp-ma",
   "display_name": "grok-4.20-multi-agent-beta-0309-exp-ma",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-multi-agent-beta-0309-exp-ma"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-multi-agent-beta-latest",
   "model_name": "grok-4.20-multi-agent-beta-latest",
   "display_name": "grok-4.20-multi-agent-beta-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-multi-agent-beta-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-multi-agent-experimental-beta-0304",
   "model_name": "grok-4.20-multi-agent-experimental-beta-0304",
   "display_name": "Grok 4.20 Multi-Agent (Experimental)",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+llmdb+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "stream": true,
    "pdf_input": true
   },
   "released_at": "2026-03-04",
   "max_output_tokens": 30000,
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.20 Multi-Agent (Experimental)"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-multi-agent-experimental-beta-latest",
   "model_name": "grok-4.20-multi-agent-experimental-beta-latest",
   "display_name": "grok-4.20-multi-agent-experimental-beta-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-multi-agent-experimental-beta-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-multi-agent-latest",
   "model_name": "grok-4.20-multi-agent-latest",
   "display_name": "grok-4.20-multi-agent-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-multi-agent-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-non-reasoning-beta",
   "model_name": "grok-4.20-non-reasoning-beta",
   "display_name": "Grok 4.20 Beta Non-Reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "xai/grok-4.20-non-reasoning-beta",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "released_at": "2026-03-11",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "prompt_caching": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-4.20-non-reasoning-beta"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.20 Beta Non-Reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-non-reasoning-gv2",
   "model_name": "grok-4.20-non-reasoning-gv2",
   "display_name": "grok-4.20-non-reasoning-gv2",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "vision": true,
    "reasoning": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-non-reasoning-gv2"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-non-reasoning-latest",
   "model_name": "grok-4.20-non-reasoning-latest",
   "display_name": "grok-4.20-non-reasoning-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "vision": true,
    "reasoning": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-non-reasoning-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-reasoning-beta",
   "model_name": "grok-4.20-reasoning-beta",
   "display_name": "Grok 4.20 Beta Reasoning",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "xai/grok-4.20-reasoning-beta",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "released_at": "2026-03-11",
   "max_input_tokens": 2000000,
   "max_output_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-4.20-reasoning-beta"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.20 Beta Reasoning"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-reasoning-gv2",
   "model_name": "grok-4.20-reasoning-gv2",
   "display_name": "grok-4.20-reasoning-gv2",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     }
    }
   ],
   "max_input_tokens": 2000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-reasoning-gv2"
    }
   ]
  },
  {
   "slug": "xai/grok-4.20-reasoning-latest",
   "model_name": "grok-4.20-reasoning-latest",
   "display_name": "grok-4.20-reasoning-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-03-09",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-4.20-reasoning-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-4.3",
   "model_name": "grok-4.3",
   "display_name": "Grok 4.3",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "models-dev+litellm+truefoundry+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.54"
      }
     }
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-4.3"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "grok-4-3"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     },
     "provider_model_id": "xai/grok-4.3",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "grok-4-3"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-4.3"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3125"
      }
     },
     "provider_model_id": "grok-4-3",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "1.28"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4.3",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-4.3"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "x-ai/grok-4.3",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "grok/grok-4.3",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2626"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5253"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.202"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "xai/grok-4.3"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-4.3"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.25"
      }
     },
     "provider_model_id": "x-ai/grok-4.3"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.42"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.83"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.23"
      }
     },
     "provider_model_id": "grok-4-3",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.992958",
        "completion": "2.003534",
        "cache_read": "1.956522"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "xai/grok-4.3",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "x-ai/grok-4.3",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "xAI's Grok for chat, coding, agentic tools, and lower hallucination risk",
   "released_at": "2026-04-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 30000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "pdf_input": true,
    "image_output": true,
    "web_search": true
   },
   "docs_url": "https://docs.x.ai/docs/models",
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2025-12",
   "benchmarks": {
    "intelligence_index": 37.6,
    "coding_index": 42.2,
    "agentic_index": 24.1
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4-3",
    "grok/grok-4.3",
    "x-ai/grok-4.3",
    "xai/grok-4.3"
   ],
   "intro_i18n": {
    "zh-CN": "世界上最追求真理的大型语言模型",
    "zh-TW": "世界上最追求真理的大型語言模型",
    "ja-JP": "世界で最も真実を追求する大規模言語モデル",
    "ru-RU": "Самая правдолюбивая крупная языковая модель в мире."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "image_output: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4.3-latest",
   "model_name": "grok-4.3-latest",
   "display_name": "grok-4.3-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "cache_read": "2",
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 1000000,
   "max_output_tokens": 1000000,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true
   },
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-04-17",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-4.5",
   "model_name": "grok-4.5",
   "display_name": "Grok 4.5",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "grok-4-5"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "x-ai/grok-4.5"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "x-ai/grok-4.5",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "grok/grok-4.5"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.0202"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.0606"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5051"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "xai/grok-4.5"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "xai/grok-4.5"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "x-ai/grok-4.5"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "grok-4-5",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1.995595",
        "completion": "2",
        "cache_read": "1.982456"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "xai/grok-4.5",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "zenmux",
     "charges": {
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "x-ai/grok-4.5",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "completion": "2",
        "cache_read": "2",
        "prompt": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk",
   "released_at": "2026-07-08",
   "max_input_tokens": 500000,
   "max_output_tokens": 500000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true
   },
   "benchmarks": {
    "intelligence_index": 53.8,
    "coding_index": 72.4,
    "agentic_index": 45.7
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-4-5",
    "grok/grok-4.5",
    "x-ai/grok-4.5",
    "xai/grok-4.5"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "listed",
     "note": "Grok 4.5"
    }
   ]
  },
  {
   "slug": "xai/grok-4.5-latest",
   "model_name": "grok-4.5-latest",
   "display_name": "grok-4.5-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2026-06-29",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "listed",
     "note": "grok-4.5-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-41-fast",
   "model_name": "grok-41-fast",
   "display_name": "Grok 4.1 Fast",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.625"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0625"
      }
     }
    }
   ],
   "released_at": "2025-12-01",
   "knowledge_cutoff": "2025-07",
   "max_input_tokens": 1000000,
   "max_output_tokens": 30720,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "grok",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.1 Fast"
    }
   ]
  },
  {
   "slug": "xai/grok-beta",
   "model_name": "grok-beta",
   "display_name": "grok-beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "x-ai/grok-beta"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "web_search": true
   },
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-beta"
   ]
  },
  {
   "slug": "xai/grok-build-0-1-0616",
   "model_name": "grok-build-0-1-0616",
   "display_name": "Grok Build 0.1 0616",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok Build 0.1 0616"
    }
   ]
  },
  {
   "slug": "xai/grok-build-0.1",
   "model_name": "grok-build-0.1",
   "display_name": "Grok Build 0.1",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "models-dev+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-build-0.1"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "grok-build-0-1"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-build-0.1"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "grok-build-0-1",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-build-0.1"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "x-ai/grok-build-0.1"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "xai/grok-build-0.1"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xai/grok-build-0.1"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "x-ai/grok-build-0.1"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "grok-build-0-1",
     "tracks": [
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "xai/grok-build-0.1",
     "tracks": [
      {
       "label": ">200.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      }
     },
     "provider_model_id": "x-ai/grok-build-0.1"
    }
   ],
   "intro": "Fast Grok coding model tuned for agentic engineering and iterative edits",
   "released_at": "2026-04-16",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok-build",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "benchmarks": {
    "intelligence_index": 39.8,
    "coding_index": 51.5,
    "agentic_index": 28
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "reasoning_config": {
    "mandatory": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-build-0-1",
    "x-ai/grok-build-0.1",
    "xai/grok-build-0.1"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-build-latest",
   "model_name": "grok-build-latest",
   "display_name": "grok-build-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "released_at": "2026-06-29",
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "listed",
     "note": "grok-build-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-code",
   "model_name": "grok-code",
   "display_name": "Grok Code Fast 1",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-08-20",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok Code Fast 1"
    }
   ]
  },
  {
   "slug": "xai/grok-code-fast",
   "model_name": "grok-code-fast",
   "display_name": "grok-code-fast",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "tracks": [
      {
       "label": "batch",
       "factor": "1",
       "charge_factors": {
        "prompt": "0.5",
        "completion": "0.5"
       },
       "triggers": [
        {
         "kind": "endpoint_matches",
         "pattern": "^batch\\."
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "model_type": "text_generation",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-04-16",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-code-fast-1",
   "model_name": "grok-code-fast-1",
   "display_name": "grok-code-fast-1",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+helicone-registry+llmdb+pricetoken+llm-prices-www+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.34"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "azure",
     "official": false,
     "source": "litellm+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "azure-ai-foundry",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "azure-cognitive-services",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "x-ai/grok-code-fast-1"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.19999999999999998"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "pa/grok-code-fast-1"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.18"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.35"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "x-ai/grok-code-fast-1"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "x-ai/grok-code-fast-1"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "xai/grok-code-fast-1"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "xai/grok-code-fast-1"
    },
    {
     "provider": "venice",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "xai/grok-code-fast-1"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "x-ai/grok-code-fast-1"
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-05-15",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "intro": "Speedy and economical reasoning model that excels at agentic coding. Features function calling, structured outputs, and reasoning capabilities.",
   "knowledge_cutoff": "2024-08",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "presence_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_logprobs",
     "top_p"
    ]
   },
   "released_at": "2025-08-28",
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "pa/grok-code-fast-1",
    "x-ai/grok-code-fast-1",
    "xai/grok-code-fast-1"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-code-fast-1-0825",
   "model_name": "grok-code-fast-1-0825",
   "display_name": "grok-code-fast-1-0825",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     }
    }
   ],
   "docs_url": "https://docs.x.ai/docs/models",
   "max_input_tokens": 256000,
   "max_output_tokens": 256000,
   "deprecated": true,
   "model_type": "text_generation",
   "deprecation_date": "2026-05-15",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2026-04-16",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "vision: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-imagine-image",
   "model_name": "grok-imagine-image",
   "display_name": "Grok Imagine Image",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "models-dev+truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.02"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     },
     "provider_model_id": "grok-imagine-image-2026-03-02"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "17.35"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.02"
      }
     },
     "provider_model_id": "xai/grok-imagine-image"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-01-28",
   "max_input_tokens": 8000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "image",
     "pdf"
    ]
   },
   "family": "grok",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true,
    "stream": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-imagine-image-2026-03-02",
    "xai/grok-imagine-image"
   ],
   "intro_i18n": {
    "zh-CN": "通过文本提示生成图像，用自然语言编辑现有图像，或通过多轮对话迭代优化图像。",
    "zh-TW": "從文本提示生成圖像，使用自然語言編輯現有圖像，或通過多輪對話迭代優化圖像。",
    "ja-JP": "テキストプロンプトから画像を生成し、自然言語で既存の画像を編集したり、マルチターン会話を通じて画像を反復的に改良します。",
    "ru-RU": "Создавайте изображения из текстовых подсказок, редактируйте существующие изображения с помощью естественного языка или итеративно улучшайте изображения через многократные диалоги."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "listed",
     "note": "Grok Imagine Image"
    }
   ]
  },
  {
   "slug": "xai/grok-imagine-image-pro",
   "model_name": "grok-imagine-image-pro",
   "display_name": "grok-imagine-image-pro",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.07"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "xai/grok-imagine-image-pro"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-imagine-image-pro"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-imagine-image-pro"
    }
   ]
  },
  {
   "slug": "xai/grok-imagine-image-quality",
   "model_name": "grok-imagine-image-quality",
   "display_name": "Grok Imagine Image Quality",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "models-dev+truefoundry+lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.05"
      }
     },
     "provider_model_id": "grok-imagine-image-quality-20260403"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-04-03",
   "max_input_tokens": 8000,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "image",
     "pdf"
    ]
   },
   "family": "grok",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "model_type": "image_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-imagine-image-quality-20260403"
   ],
   "intro_i18n": {
    "zh-CN": "根据文本提示生成图像，用自然语言编辑现有图像，或通过多轮对话迭代优化图像。",
    "zh-TW": "從文本提示生成圖像，使用自然語言編輯現有圖像，或通過多輪對話迭代優化圖像。",
    "ja-JP": "テキストプロンプトから画像を生成したり、自然言語で既存の画像を編集したり、マルチターン会話を通じて画像を反復的に改良したりします。",
    "ru-RU": "Генерация изображений из текстовых подсказок, редактирование существующих изображений с помощью естественного языка или итеративное улучшение изображений через многократные взаимодействия."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "listed",
     "note": "Grok Imagine Image Quality"
    }
   ]
  },
  {
   "slug": "xai/grok-imagine-image-quality-latest",
   "model_name": "grok-imagine-image-quality-latest",
   "display_name": "grok-imagine-image-quality-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "image_input": {
       "unit": "per_image",
       "price": "0.01"
      },
      "image_output": {
       "unit": "per_image",
       "price": "0.05"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "image"
    ]
   },
   "model_type": "image_generation",
   "capabilities": {
    "vision": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-imagine-image-quality-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-imagine-video",
   "model_name": "grok-imagine-video",
   "display_name": "Grok Imagine Video",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "models-dev+truefoundry+llmdb+lobehub-modelbank",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.05"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "x_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "code_execution": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "document_search": {
       "unit": "per_k_calls",
       "price": "5"
      },
      "collections_search": {
       "unit": "per_k_calls",
       "price": "2.5"
      },
      "video_output": {
       "unit": "per_second",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_480p": {
       "unit": "per_second",
       "price": "0.05"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.07"
      }
     },
     "provider_model_id": "xai/grok-imagine-video"
    }
   ],
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-01-28",
   "max_input_tokens": 1024,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "pdf"
    ],
    "output": [
     "video"
    ]
   },
   "family": "grok",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "model_type": "video_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-imagine-video"
   ],
   "intro_i18n": {
    "zh-CN": "在质量、成本和延迟方面的最先进视频生成技术。",
    "zh-TW": "在質量、成本及延遲方面的最先進影像生成技術。",
    "ja-JP": "品質、コスト、遅延のすべてにおいて最先端のビデオ生成。",
    "ru-RU": "Передовая генерация видео с учетом качества, стоимости и задержки."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "listed",
     "note": "Grok Imagine Video"
    }
   ]
  },
  {
   "slug": "xai/grok-imagine-video-1.5-2026-05-30",
   "model_name": "grok-imagine-video-1.5-2026-05-30",
   "display_name": "Grok Imagine Video 1.5",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.08"
      }
     },
     "provider_model_id": "grok-imagine-video-1.5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_480p": {
       "unit": "per_second",
       "price": "0.08"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.14"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.25"
      }
     },
     "provider_model_id": "xai/grok-imagine-video-1.5"
    }
   ],
   "modalities": {
    "input": [
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-06-22",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "grok-imagine-video-1.5",
    "xai/grok-imagine-video-1.5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok Imagine Video 1.5"
    }
   ]
  },
  {
   "slug": "xai/grok-imagine-video-1.5-preview",
   "model_name": "grok-imagine-video-1.5-preview",
   "display_name": "Grok Imagine Video 1.5 Preview",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry",
     "charges": {
      "audio_output": {
       "unit": "per_second",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "video_output_480p": {
       "unit": "per_second",
       "price": "0.08"
      },
      "video_output_720p": {
       "unit": "per_second",
       "price": "0.14"
      },
      "video_output_1080p": {
       "unit": "per_second",
       "price": "0.25"
      }
     },
     "provider_model_id": "xai/grok-imagine-video-1.5-preview"
    }
   ],
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "video"
    ]
   },
   "model_type": "video_generation",
   "capabilities": {
    "vision": true
   },
   "intro": "Image model for prompt-driven generation, editing, and visual design workflows",
   "released_at": "2026-05-30",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-imagine-video-1.5-preview"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok Imagine Video 1.5 Preview"
    }
   ]
  },
  {
   "slug": "xai/grok-latest",
   "model_name": "grok-latest",
   "display_name": "grok-latest",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "truefoundry+ai-model-directory",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "x-ai/grok-latest"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "~x-ai/grok-latest"
    }
   ],
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "vision_understanding",
   "capabilities": {
    "function_calling": true,
    "parallel_function_calling": true,
    "structured_output": true,
    "prompt_caching": true,
    "reasoning": true,
    "vision": true,
    "pdf_input": true
   },
   "released_at": "2026-04-17",
   "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance",
   "max_output_tokens": 1000000,
   "family": "grok",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-latest",
    "~x-ai/grok-latest"
   ],
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "cache_read",
     "old": "0.2",
     "new": "0.5"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "completion",
     "old": "2.5",
     "new": "6"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "1.25",
     "new": "2"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "grok-latest"
    }
   ]
  },
  {
   "slug": "xai/grok-stt",
   "model_name": "grok-stt",
   "display_name": "Grok STT",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway",
     "charges": {
      "audio_input": {
       "unit": "per_second",
       "price": "0.000028"
      }
     },
     "provider_model_id": "xai/grok-stt"
    }
   ],
   "intro": "Speech transcription model for accurate audio-to-text and captioning workflows",
   "released_at": "2026-03-16",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "audio"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "capabilities": {
    "audio_input": true
   },
   "model_type": "speech_recognition",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-stt"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok STT"
    }
   ]
  },
  {
   "slug": "xai/grok-tts",
   "model_name": "grok-tts",
   "display_name": "Grok TTS",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "speech_input": {
       "unit": "per_M_characters",
       "price": "15"
      }
     },
     "provider_model_id": "xai/grok-tts"
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2026-03-16",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "grok",
   "capabilities": {
    "audio_output": true
   },
   "model_type": "speech_synthesis",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-tts"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok TTS"
    }
   ]
  },
  {
   "slug": "xai/grok-vision-beta",
   "model_name": "grok-vision-beta",
   "display_name": "grok-vision-beta",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "xai",
     "official": true,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      },
      "image_input": {
       "unit": "per_image",
       "price": "0.000005"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "16.8"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "15"
      }
     },
     "provider_model_id": "x-ai/grok-vision-beta"
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "web_search": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": []
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "x-ai/grok-vision-beta"
   ],
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "pdf_input: false→true"
    }
   ]
  },
  {
   "slug": "xai/grok-voice-think-fast-1.0",
   "model_name": "grok-voice-think-fast-1.0",
   "display_name": "Grok Voice Think Fast 1.0",
   "vendor": "xai",
   "pricing": [],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2026-04-23",
   "max_input_tokens": 0,
   "max_output_tokens": 0,
   "modalities": {
    "input": [
     "text",
     "audio"
    ],
    "output": [
     "text",
     "audio"
    ]
   },
   "family": "grok",
   "capabilities": {
    "audio_input": true,
    "audio_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xai/grok-voice-think-fast-1.0"
   ],
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok Voice Think Fast 1.0"
    }
   ]
  },
  {
   "slug": "xai/xai.grok-4.3",
   "model_name": "xai.grok-4.3",
   "display_name": "Grok 4.3",
   "vendor": "xai",
   "pricing": [
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "aws-bedrock-mantle",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5"
      }
     }
    }
   ],
   "intro": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk",
   "released_at": "2026-04-17",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "grok",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Grok 4.3"
    }
   ]
  },
  {
   "slug": "xiaomi/coding-xiaomi-mimo-v2-omni",
   "model_name": "coding-xiaomi-mimo-v2-omni",
   "display_name": "coding-xiaomi-mimo-v2-omni",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-xiaomi-mimo-v2-omni"
    }
   ]
  },
  {
   "slug": "xiaomi/coding-xiaomi-mimo-v2-pro",
   "model_name": "coding-xiaomi-mimo-v2-pro",
   "display_name": "coding-xiaomi-mimo-v2-pro",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-xiaomi-mimo-v2-pro"
    }
   ]
  },
  {
   "slug": "xiaomi/coding-xiaomi-mimo-v2.5",
   "model_name": "coding-xiaomi-mimo-v2.5",
   "display_name": "Coding Xiaomi MiMo-V2.5",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.016"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Open MiMo model for multimodal coding agents and long-context automation",
   "released_at": "2026-04-22",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo-v2.5",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding Xiaomi MiMo-V2.5"
    }
   ]
  },
  {
   "slug": "xiaomi/coding-xiaomi-mimo-v2.5-pro",
   "model_name": "coding-xiaomi-mimo-v2.5-pro",
   "display_name": "Coding Xiaomi MiMo-V2.5-Pro",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
   "released_at": "2026-04-22",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo-v2.5-pro",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding Xiaomi MiMo-V2.5-Pro"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2-flash",
   "model_name": "mimo-v2-flash",
   "display_name": "MiMo-V2-Flash",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "xiaomi",
     "official": true,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1918"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5754"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03836"
      }
     }
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     },
     "provider_model_id": "XiaomiMiMo/MiMo-V2-Flash"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "XiaomiMiMo/MiMo-V2-Flash"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "xiaomimimo/mimo-v2-flash"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.045"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-flash"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "XiaomiMiMo/MiMo-V2-Flash"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-flash"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      }
     },
     "provider_model_id": "xiaomimimo/mimo-v2-flash"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "xiaomimimo/mimo-v2-flash"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2-flash-free"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "litellm+pydantic-prices+truefoundry+computeprices+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-flash"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.101"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.303"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0202"
      }
     }
    },
    {
     "provider": "qiniu-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-flash"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "novita/xiaomimimo/mimo-v2-flash"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.29999999999999993"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.009999999999999998"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-flash"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-flash"
    },
    {
     "provider": "xiaomimimo",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102941"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.010294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-flash"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2025-12-16",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 65536,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "status": "deprecated",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true,
    "parallel_function_calling": true,
    "web_search": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "XiaomiMiMo/MiMo-V2-Flash",
    "mimo-v2-flash-free",
    "novita/xiaomimimo/mimo-v2-flash",
    "xiaomi/mimo-v2-flash",
    "xiaomimimo/mimo-v2-flash"
   ],
   "intro_i18n": {
    "zh-CN": "MiMo-V2-Flash现已正式开源！这是一个专为极致推理效率设计的MoE（专家混合）模型，拥有3090亿总参数（激活参数15亿）。通过在混合注意力架构和多层MTP推理加速方面的创新，它在多个代理基准测试中跻身全球开源模型前二。其编程能力超越所有开源模型，并可媲美领先的闭源模型（如Claude 4.5 Sonnet），推理成本仅为2.5%，生成速度提升2倍——将大模型推理效率推向极限。",
    "zh-TW": "MiMo-V2-Flash 現已正式開源！這是一款專為極致推理效率設計的 MoE（專家混合）模型，擁有 3090 億總參數（啟用 150 億）。通過混合注意力架構和多層 MTP 推理加速的創新技術，它在多個代理基準測試中名列全球開源模型前二。其編碼能力超越所有開源模型，並可媲美領先的封閉源模型（如 Claude 4.5 Sonnet），推理成本僅為其 2.5%，生成速度提升 2 倍，將大型模型推理效率推向極限。",
    "ja-JP": "MiMo-V2-Flashは正式にオープンソース化されました！これは極限の推論効率を目的として設計されたMoE（Mixture-of-Experts）モデルで、総パラメータ数は309B（アクティブ化されたパラメータは15B）です。ハイブリッド注意アーキテクチャと多層MTP推論加速の革新により、複数のエージェントベンチマークスイートで世界トップ2のオープンソースモデルにランクインしています。そのコーディング能力はすべてのオープンソースモデルを凌駕し、Claude 4.5 Sonnetのような主要なクローズドソースモデルに匹敵しますが、推論コストはわずか2.5%で、生成速度は2倍速く、大規模モデル推論効率を限界まで押し上げています。",
    "ru-RU": "MiMo-V2-Flash теперь официально с открытым исходным кодом! Это модель MoE (Mixture-of-Experts), специально созданная для экстремальной эффективности вывода, с общим количеством параметров 309B (15B активированы). Благодаря инновациям в гибридной архитектуре внимания и многослойной MTP-ускоренной обработке, она входит в число двух лучших моделей с открытым исходным кодом в глобальных рейтингах агентных тестов. Ее возможности кодирования превосходят все модели с открытым исходным кодом и сопоставимы с ведущими закрытыми моделями, такими как Claude 4.5 Sonnet, при этом затраты на вывод составляют всего 2,5%, а скорость генерации в 2 раза выше — доводя эффективность вывода больших моделей до предела."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2-Flash"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2-flash-original",
   "model_name": "mimo-v2-flash-original",
   "display_name": "MiMo V2 Flash Original",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-flash-original"
    }
   ],
   "intro": "MiMo flash model for fast multimodal assistance and agent workflows",
   "released_at": "2025-12-17",
   "max_input_tokens": 256000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xiaomi/mimo-v2-flash-original"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo V2 Flash Original"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2-flash-thinking",
   "model_name": "mimo-v2-flash-thinking",
   "display_name": "MiMo V2 Flash (Thinking)",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-flash-thinking"
    }
   ],
   "intro": "MiMo flash model for fast multimodal assistance and agent workflows",
   "released_at": "2025-12-17",
   "max_input_tokens": 256000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xiaomi/mimo-v2-flash-thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo V2 Flash (Thinking)"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2-flash-thinking-original",
   "model_name": "mimo-v2-flash-thinking-original",
   "display_name": "MiMo V2 Flash (Thinking) Original",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.102"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.306"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-flash-thinking-original"
    }
   ],
   "intro": "MiMo flash model for fast multimodal assistance and agent workflows",
   "released_at": "2025-12-17",
   "max_input_tokens": 256000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xiaomi/mimo-v2-flash-thinking-original"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo V2 Flash (Thinking) Original"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2-omni",
   "model_name": "mimo-v2-omni",
   "display_name": "MiMo-V2-Omni",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "xiaomi",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.44"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.088"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-omni"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-omni"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2-omni-free"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-omni"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07999999999999999"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-omni"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-omni"
    }
   ],
   "intro": "Legacy model retained for compatibility with older integrations",
   "released_at": "2026-03-18",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 262144,
   "max_output_tokens": 131072,
   "deprecated": true,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "omni",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "mimo-v2-omni-free",
    "xiaomi/mimo-v2-omni"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2-Omni"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2-pro",
   "model_name": "mimo-v2-pro",
   "display_name": "MiMo-V2-Pro",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "xiaomi",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0036"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.308824"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "xiaomimimo/mimo-v2-pro"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-pro",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-pro"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "xiaomimimo/mimo-v2-pro"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "xiaomimimo/mimo-v2-pro",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2-pro-free"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "truefoundry+computeprices",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-pro"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "novita/xiaomimimo/mimo-v2-pro"
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.088235"
      }
     },
     "provider_model_id": "MiMo-V2-Pro",
     "tracks": [
      {
       "label": ">256000000K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000000000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-pro"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-pro",
     "tracks": [
      {
       "label": ">256.001K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256001,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "xiaomi-token-plan-ams",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomi-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomi-token-plan-sgp",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2-pro",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks",
   "released_at": "2026-03-18",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "status": "deprecated",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiMo-V2-Pro",
    "mimo-v2-pro-free",
    "novita/xiaomimimo/mimo-v2-pro",
    "xiaomi/mimo-v2-pro",
    "xiaomimimo/mimo-v2-pro"
   ],
   "intro_i18n": {
    "zh-CN": "MiMo-V2-Pro 专为真实世界中的高强度智能体工作流设计。其总参数量超过 1 万亿（激活参数 42B），采用创新的混合注意力架构，支持超长上下文长度（最高 100 万 tokens）。基于强大的基础模型，我们持续在更广泛的智能体场景中扩展算力，进一步拓展智能的行动空间，在从编码到真实任务执行（“钳爪”）等方面实现显著泛化。",
    "zh-TW": "MiMo-V2-Pro 專為真實場景中的高強度智能體工作流設計，總參數規模超過 1 兆（啟用參數 42B），採用創新的混合注意力架構，並支援高達 100 萬 token 的超長脈絡。基於強大的基礎模型，我們持續在更多智能體場景擴大計算規模，拓展智能行為空間，並在從編碼到實體任務執行（「claw」）的多領域展現卓越泛化能力。",
    "ja-JP": "MiMo-V2-Pro は実世界の高負荷エージェントワークフロー向けに設計されています。総パラメータは 1 兆超（42B アクティブ）で、革新的なハイブリッドアテンション構造を採用し、最大 100 万トークンの超長コンテキストをサポートします。強力な基盤モデルをもとに、幅広いエージェントシナリオで計算資源を拡張し、知能の行動範囲を拡大して、コーディングから実世界タスク実行（「claw」）まで高い汎化能力を発揮します。",
    "ru-RU": "MiMo-V2-Pro специально создана для высокоинтенсивных агентных рабочих процессов в реальных условиях. Содержит более 1 триллиона общих параметров (42B активных), использует гибридную архитектуру внимания и поддерживает сверхдлинный контекст до 1 миллиона токенов. На основе мощной базовой модели мы постепенно масштабируем вычислительные ресурсы под более широкий спектр агентных сценариев, расширяя пространство действий и достигая значительной обобщающей способности — от кодирования до выполнения реальных задач («claw»)."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2-Pro"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2-tts",
   "model_name": "mimo-v2-tts",
   "display_name": "MiMo-V2-TTS",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "xiaomi-token-plan-ams",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomi-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomi-token-plan-sgp",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2026-03-18",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "audio_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2-TTS"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2.5",
   "model_name": "mimo-v2.5",
   "display_name": "MiMo-V2.5",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "xiaomi",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.85"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.359"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.795"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.09"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "XiaomiMiMo/MiMo-V2.5"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2-5"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "5.714286",
        "completion": "14.285714",
        "cache_read": "57.142857"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "5.714286",
        "completion": "14.285714",
        "cache_read": "57.142857"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.168"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.336"
      }
     },
     "provider_model_id": "xiaomimimo/mimo-v2.5"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2.5-free"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.105"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.028"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "deepinfra/XiaomiMiMo/MiMo-V2.5"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "route/mimo-v2.5",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.444444",
        "completion": "4.444444",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.444444",
        "completion": "4.444444",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07999999999999999"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0028"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5"
    },
    {
     "provider": "xiaomi-token-plan-ams",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomi-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomi-token-plan-sgp",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomimimo",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.002941"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "4.66972"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Open MiMo model for multimodal coding agents and long-context automation",
   "released_at": "2026-04-22",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "XiaomiMiMo/MiMo-V2.5",
    "deepinfra/XiaomiMiMo/MiMo-V2.5",
    "mimo-v2-5",
    "mimo-v2.5-free",
    "route/mimo-v2.5",
    "xiaomi/mimo-v2.5",
    "xiaomi/mimo-v2.5:thinking",
    "xiaomimimo/mimo-v2.5"
   ],
   "intro_i18n": {
    "zh-CN": "MiMo-V2.5 是原生全模态 Agent 基础模型，能够在统一架构下理解图像、视频、音频与文本，具备 100 万上下文窗口。以约 MiMo-V2.5-Pro 一半成本提供接近 Pro 级的 Agent 能力，并在多模态感知上显著优于 MiMo-V2-Omni。其内置 Agent 能力（浏览、理解、推理、执行）与更快推理速度，使其非常适合 OpenClaw 等对延迟敏感的多步 Agent 框架。",
    "zh-TW": "MiMo-V2.5 是原生全模態代理基座模型，以統一架構理解圖片、影片、音訊與文本，具備 100 萬上下文。其代理能力（瀏覽、理解、推理、執行）與更快的推理速度，使其非常適合 OpenClaw 等重視延遲與多步推理的代理框架。",
    "ja-JP": "MiMo-V2.5は、画像、動画、音声、テキストを統一アーキテクチャで理解するネイティブオムニモーダルエージェント基盤モデルであり、1Mコンテキストウィンドウを備えています。MiMo-V2.5-Proの約半分の推論コストでプロレベルのエージェント性能を提供し、MiMo-V2-Omniよりもマルチモーダル認識が向上しています。組み込みのエージェント能力（ブラウジング、理解、推論、実行）と高速な推論により、OpenClawなどのレイテンシーに敏感なマルチステップエージェントフレームワークに適しています。",
    "ru-RU": "MiMo-V2.5 — нативная омнимодальная агентная модель, понимающая изображения, видео, аудио и текст в единой архитектуре с контекстом 1M. Обеспечивает производительность уровня Pro примерно за половину стоимости MiMo-V2.5-Pro и улучшенную мультимодальную перцепцию по сравнению с MiMo-V2-Omni. Благодаря встроенным агентным возможностям (обзор, понимание, рассуждение, выполнение) и более быстрой инференции отлично подходит для сценариев с низкой задержкой и многошаговых агентных фреймворков, таких как OpenClaw."
   },
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "openrouter",
     "charge": "cache_read",
     "old": "0.08",
     "new": "0.028"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2.5"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2.5-pro",
   "model_name": "mimo-v2.5-pro",
   "display_name": "MiMo-V2.5-Pro",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "xiaomi",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0036"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "5",
        "completion": "7.5",
        "cache_read": "133.333333"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "5",
        "completion": "7.5",
        "cache_read": "133.333333"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "XiaomiMiMo/MiMo-V2.5-Pro"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "XiaomiMiMo/MiMo-V2.5-Pro"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6"
      }
     },
     "provider_model_id": "xiaomimimo/mimo-v2.5-pro"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2-5-pro"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5-pro",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0036"
      }
     },
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.597701",
        "completion": "6.896552",
        "cache_read": "111.111111"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.597701",
        "completion": "6.896552",
        "cache_read": "111.111111"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.02991924"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.08975772"
      }
     },
     "provider_model_id": "MiMo-V2.5-Pro"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0036"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5-pro"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.522"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.044"
      }
     },
     "provider_model_id": "xiaomimimo/mimo-v2.5-pro"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.522"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.044"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0043"
      }
     },
     "provider_model_id": "xiaomimimo/mimo-v2.5-pro",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "1",
        "completion": "1",
        "cache_read": "1"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0145"
      }
     }
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0145"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0036"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5-pro"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.0101"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.0303"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "route/mimo-v2.5-pro",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.444444",
        "completion": "4.444444",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.444444",
        "completion": "4.444444",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5-pro"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.435"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0036"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5-pro"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.65"
      }
     },
     "provider_model_id": "XiaomiMiMo/MiMo-V2.5-Pro"
    },
    {
     "provider": "xiaomi-token-plan-ams",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomi-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomi-token-plan-sgp",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomimimo",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.003676"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "4.94318"
      }
     },
     "provider_model_id": "xiaomi/mimo-v2.5-pro",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
   "released_at": "2026-04-22",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "benchmarks": {
    "intelligence_index": 42.2,
    "coding_index": 60.2,
    "agentic_index": 29.1
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "MiMo-V2.5-Pro",
    "XiaomiMiMo/MiMo-V2.5-Pro",
    "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro",
    "mimo-v2-5-pro",
    "route/mimo-v2.5-pro",
    "xiaomi/mimo-v2.5-pro",
    "xiaomi/mimo-v2.5-pro:thinking",
    "xiaomimimo/mimo-v2.5-pro"
   ],
   "intro_i18n": {
    "zh-CN": "MiMo-V2.5-Pro 是小米迄今最强旗舰模型，在通用 Agent 能力、复杂软件工程与长程任务方面大幅提升。延续 1T 总参数 / 42B 激活的混合注意力架构与 100 万上下文窗口，可完成包含上千次工具调用的长链任务。在 ClawEval、GDPVal、SWE-bench Pro 等高难 Agent 基准上表现可比 Claude Opus 4.6。",
    "zh-TW": "MiMo-V2.5-Pro 是小米迄今最強大的旗艦模型，在通用代理能力、複雜軟體工程與長程任務上有重大提升。延續 1T 總參數 / 42B 啟動參數的混合注意力架構與 100 萬上下文，可處理上千次工具調用的長程任務。在 ClawEval、GDPVal、SWE-bench Pro 等高難度代理基準中表現接近 Claude Opus 4.6。",
    "ja-JP": "MiMo-V2.5-Proは、Xiaomiのこれまでで最も能力の高いフラッグシップモデルであり、一般的なエージェント能力、複雑なソフトウェアエンジニアリング、長期的なタスクにおいて大幅な改善を提供します。1T総パラメータ/42Bアクティブハイブリッドアテンションアーキテクチャを維持し、1Mコンテキストウィンドウを備えています。ClawEval、GDPVal、SWE-bench Proなどの要求の厳しいエージェントベンチマークでClaude Opus 4.6に匹敵する性能を発揮します。",
    "ru-RU": "MiMo-V2.5-Pro — самая мощная флагманская модель Xiaomi на сегодняшний день. Существенно улучшены общие агентные способности, сложная разработка ПО и долгосрочные задачи. Она сохраняет гибридную архитектуру с 1T общих / 42B активных параметров и поддержкой контекста 1M. Модель способна выполнять сложные долгосрочные задачи с более чем 1000 вызовов инструментов. Её производительность в сложных агентных бенчмарках (ClawEval, GDPVal, SWE-bench Pro) сопоставима с Claude Opus 4.6."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.09123528",
     "new": "3.08975772"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.03041176",
     "new": "1.02991924"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.09338274",
     "new": "3.09123528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.03112758",
     "new": "1.03041176"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.09664362",
     "new": "3.09338274"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.03221454",
     "new": "1.03112758"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.09727593",
     "new": "3.09664362"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.03242531",
     "new": "1.03221454"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.09617952",
     "new": "3.09727593"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.03205984",
     "new": "1.03242531"
    },
    {
     "date": "2026-07-04",
     "kind": "capability",
     "note": "audio_input: false→true"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "3.09075795",
     "new": "3.09617952"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.03025265",
     "new": "1.03205984"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2.5-Pro"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2.5-pro-6bit",
   "model_name": "mimo-v2.5-pro-6bit",
   "display_name": "MiMo V2.5 Pro 6bit",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.35"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "route/mimo-v2.5-pro-6bit",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.444444",
        "completion": "4.444444",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "4.444444",
        "completion": "4.444444",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
   "released_at": "2026-04-22",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 262144,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "route/mimo-v2.5-pro-6bit"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo V2.5 Pro 6bit"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2.5-pro-ultraspeed",
   "model_name": "mimo-v2.5-pro-ultraspeed",
   "display_name": "MiMo-V2.5-Pro-UltraSpeed",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "xiaomi",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.305"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.61"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0108"
      }
     }
    }
   ],
   "intro": "MiMo pro model for strong multimodal reasoning and agent execution",
   "released_at": "2026-06-08",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "status": "beta",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2.5-Pro-UltraSpeed"
    }
   ]
  },
  {
   "slug": "xiaomi/MiMo-V2.5-tts",
   "model_name": "MiMo-V2.5-tts",
   "display_name": "MiMo-V2.5-TTS",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0"
      }
     },
     "provider_model_id": "XiaomiMiMo/MiMo-V2.5-tts"
    },
    {
     "provider": "xiaomi-token-plan-ams",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2.5-tts"
    },
    {
     "provider": "xiaomi-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2.5-tts"
    },
    {
     "provider": "xiaomi-token-plan-sgp",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2.5-tts"
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2026-04-22",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "audio_output": true,
    "open_weights": true
   },
   "model_type": "speech_synthesis",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "XiaomiMiMo/MiMo-V2.5-tts",
    "mimo-v2.5-tts"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2.5-TTS"
    }
   ]
  },
  {
   "slug": "xiaomi/mimo-v2.5-tts-voiceclone",
   "model_name": "mimo-v2.5-tts-voiceclone",
   "display_name": "MiMo-V2.5-TTS-VoiceClone",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "xiaomi-token-plan-ams",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomi-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "xiaomi-token-plan-sgp",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2026-04-22",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "audio_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "speech_synthesis",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2.5-TTS-VoiceClone"
    }
   ]
  },
  {
   "slug": "xiaomi/MiMo-V2.5-tts-voicedesign",
   "model_name": "MiMo-V2.5-tts-voicedesign",
   "display_name": "MiMo-V2.5-TTS-VoiceDesign",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "speech_input": {
       "unit": "per_M_characters",
       "price": "0"
      }
     },
     "provider_model_id": "XiaomiMiMo/MiMo-V2.5-tts-voicedesign"
    },
    {
     "provider": "xiaomi-token-plan-ams",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2.5-tts-voicedesign"
    },
    {
     "provider": "xiaomi-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2.5-tts-voicedesign"
    },
    {
     "provider": "xiaomi-token-plan-sgp",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "mimo-v2.5-tts-voicedesign"
    }
   ],
   "intro": "Speech generation model for controllable voice, narration, and audio delivery",
   "released_at": "2026-04-22",
   "max_input_tokens": 8192,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "audio"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "audio_output": true,
    "open_weights": true
   },
   "model_type": "speech_synthesis",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "XiaomiMiMo/MiMo-V2.5-tts-voicedesign",
    "mimo-v2.5-tts-voicedesign"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2.5-TTS-VoiceDesign"
    }
   ]
  },
  {
   "slug": "xiaomi/ppio-xiaomimimo-mimo-v2-flash",
   "model_name": "ppio-xiaomimimo-mimo-v2-flash",
   "display_name": "xiaomimimo/mimo-v2-flash",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 262144,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "xiaomimimo/mimo-v2-flash"
    }
   ]
  },
  {
   "slug": "xiaomi/sophnet-MiMo-V2-Flash",
   "model_name": "sophnet-MiMo-V2-Flash",
   "display_name": "sophnet/MiMo-V2-Flash",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2026-01-06",
   "max_input_tokens": 256000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/MiMo-V2-Flash"
    }
   ]
  },
  {
   "slug": "xiaomi/xiaomi-mimo-v2-5",
   "model_name": "xiaomi-mimo-v2-5",
   "display_name": "MiMo-V2.5",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.44"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.088"
      }
     },
     "provider_model_id": "xiaomi-mimo-v2.5",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    }
   ],
   "intro": "Open MiMo model for multimodal coding agents and long-context automation",
   "released_at": "2026-06-11",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 1000000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image",
     "audio",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xiaomi-mimo-v2.5",
    "xiaomi-mimo-v2.5-free"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "MiMo-V2.5"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "cache_read",
     "old": "0.0625",
     "new": "0.05"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "completion",
     "old": "0.35",
     "new": "0.28"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "prompt",
     "old": "0.175",
     "new": "0.14"
    }
   ]
  },
  {
   "slug": "xiaomi/xiaomi-mimo-v2.5-pro-free",
   "model_name": "xiaomi-mimo-v2.5-pro-free",
   "display_name": "Xiaomi MiMo-V2.5-Pro",
   "vendor": "xiaomi",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "xiaomi-mimo-v2.5-pro",
     "tracks": [
      {
       "label": ">256K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 256000,
         "inclusive": false
        }
       ]
      },
      {
       "label": ">200K context",
       "factor": "1",
       "charge_factors": {
        "prompt": "2",
        "completion": "2",
        "cache_read": "2"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 200000,
         "inclusive": false
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
   "released_at": "2026-04-22",
   "knowledge_cutoff": "2024-12",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "mimo-v2.5-pro",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "xiaomi-mimo-v2.5-pro"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Xiaomi MiMo-V2.5-Pro"
    }
   ]
  },
  {
   "slug": "zhipuai/alicloud-glm-4.7",
   "model_name": "alicloud-glm-4.7",
   "display_name": "alicloud-glm-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.41096"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.917785936"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "alicloud-glm-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/alicloud-glm-5",
   "model_name": "alicloud-glm-5",
   "display_name": "alicloud-glm-5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5634"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.5353"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11268"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "alicloud-glm-5"
    }
   ]
  },
  {
   "slug": "zhipuai/alicloud-glm-5.1",
   "model_name": "alicloud-glm-5.1",
   "display_name": "GLM-5.1 (Alibaba Cloud)",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.84"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.169"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.05625"
      }
     }
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-03-27",
   "max_input_tokens": 200000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-5.1 (Alibaba Cloud)"
    }
   ]
  },
  {
   "slug": "zhipuai/autoglm-phone-9b",
   "model_name": "autoglm-phone-9b",
   "display_name": "Z-Ai/Autoglm Phone 9b",
   "vendor": "zhipuai",
   "pricing": [],
   "intro": "GLM vision model for visual reasoning, documents, and multimodal agents",
   "released_at": "2025-12-23",
   "max_input_tokens": 12800,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "z-ai/autoglm-phone-9b"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Z-Ai/Autoglm Phone 9b"
    }
   ]
  },
  {
   "slug": "zhipuai/AutoGLM-Phone-9B-Multilingual",
   "model_name": "AutoGLM-Phone-9B-Multilingual",
   "display_name": "AutoGLM-Phone-9B-Multilingual",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.138"
      }
     },
     "provider_model_id": "zai-org/AutoGLM-Phone-9B-Multilingual"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.051495962"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.205983848"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.138"
      }
     },
     "provider_model_id": "autoglm-phone-9b-multilingual"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.138"
      }
     },
     "provider_model_id": "zai-org/autoglm-phone-9b-multilingual"
    }
   ],
   "intro": "GLM vision model for visual reasoning, documents, and multimodal agents",
   "released_at": "2025-12-10",
   "max_input_tokens": 65536,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "open_weights": true,
    "pdf_input": true
   },
   "model_type": "vision_understanding",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "autoglm-phone-9b-multilingual",
    "zai-org/AutoGLM-Phone-9B-Multilingual",
    "zai-org/autoglm-phone-9b-multilingual"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206082352",
     "new": "0.205983848"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051520588",
     "new": "0.051495962"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206225516",
     "new": "0.206082352"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051556379",
     "new": "0.051520588"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206442908",
     "new": "0.206225516"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051610727",
     "new": "0.051556379"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206485062",
     "new": "0.206442908"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0516212655",
     "new": "0.051610727"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.206411968",
     "new": "0.206485062"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.051602992",
     "new": "0.0516212655"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.20605053",
     "new": "0.206411968"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.0515126325",
     "new": "0.051602992"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "AutoGLM-Phone-9B-Multilingual"
    }
   ]
  },
  {
   "slug": "zhipuai/cbs-glm-4.7",
   "model_name": "cbs-glm-4.7",
   "display_name": "cbs-glm-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.749995"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cbs-glm-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/cc-glm-4.6",
   "model_name": "cc-glm-4.6",
   "display_name": "cc-glm-4.6",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21999996"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-glm-4.6"
    }
   ]
  },
  {
   "slug": "zhipuai/cc-glm-4.7",
   "model_name": "cc-glm-4.7",
   "display_name": "cc-glm-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21999996"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-glm-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/cc-glm-5",
   "model_name": "cc-glm-5",
   "display_name": "cc-glm-5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21999996"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-glm-5"
    }
   ]
  },
  {
   "slug": "zhipuai/cc-glm-5-turbo",
   "model_name": "cc-glm-5-turbo",
   "display_name": "cc-glm-5-turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21999996"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-glm-5-turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/cc-glm-5.1",
   "model_name": "cc-glm-5.1",
   "display_name": "cc-glm-5.1",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21999996"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cc-glm-5.1"
    }
   ]
  },
  {
   "slug": "zhipuai/charglm-3",
   "model_name": "charglm-3",
   "display_name": "CharGLM-3",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "CharGLM-3 专为角色扮演和情感陪伴设计，支持超长多轮记忆和个性化对话。",
    "zh-TW": "CharGLM-3 專為角色扮演與情感陪伴設計，支援超長多輪記憶與個性化對話。",
    "ja-JP": "CharGLM-3は、ロールプレイと感情的な対話を目的に設計されており、超長期のマルチターン記憶とパーソナライズされた会話をサポートします。",
    "ru-RU": "CharGLM-3 создана для ролевых игр и эмоционального общения, поддерживает сверхдолгую многотуровую память и персонализированный диалог."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CharGLM-3"
    }
   ]
  },
  {
   "slug": "zhipuai/charglm-4",
   "model_name": "charglm-4",
   "display_name": "CharGLM-4",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "CharGLM-4 专为角色扮演和情感陪伴设计，支持超长多轮记忆和个性化对话。",
    "zh-TW": "CharGLM-4 專為角色扮演與情感陪伴設計，支援超長多輪記憶與個性化對話。",
    "ja-JP": "CharGLM-4は、ロールプレイと感情的な対話を目的に設計されており、超長期のマルチターン記憶とパーソナライズされた会話をサポートします。",
    "ru-RU": "CharGLM-4 создана для ролевых игр и эмоционального общения, поддерживает сверхдолгую многотуровую память и персонализированный диалог."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CharGLM-4"
    }
   ]
  },
  {
   "slug": "zhipuai/chatglm_lite",
   "model_name": "chatglm_lite",
   "display_name": "chatglm_lite",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2858"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2858"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chatglm_lite"
    }
   ]
  },
  {
   "slug": "zhipuai/chatglm_pro",
   "model_name": "chatglm_pro",
   "display_name": "chatglm_pro",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4286"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chatglm_pro"
    }
   ]
  },
  {
   "slug": "zhipuai/chatglm_std",
   "model_name": "chatglm_std",
   "display_name": "chatglm_std",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7144"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chatglm_std"
    }
   ]
  },
  {
   "slug": "zhipuai/chatglm_turbo",
   "model_name": "chatglm_turbo",
   "display_name": "chatglm_turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7144"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7144"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "chatglm_turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/cloudflare-glm-5.2",
   "model_name": "cloudflare-glm-5.2",
   "display_name": "cloudflare-glm-5.2",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4002"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2604"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cloudflare-glm-5.2"
    }
   ]
  },
  {
   "slug": "zhipuai/codegeex-4",
   "model_name": "codegeex-4",
   "display_name": "CodeGeeX-4",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.014706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.014706"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "CodeGeeX-4 是一款强大的 AI 编程助手，支持多语言问答和代码补全，提升开发者效率。",
    "zh-TW": "CodeGeeX-4 是一款強大的 AI 程式輔助工具，支援多語言問答與程式碼補全，能有效提升開發者的生產力。",
    "ja-JP": "CodeGeeX-4は、開発者の生産性を向上させる多言語対応のAIコーディングアシスタントで、Q&Aやコード補完をサポートします。",
    "ru-RU": "CodeGeeX-4 — мощный AI-помощник для программирования, поддерживающий многоязычные вопросы и автодополнение кода для повышения продуктивности разработчиков."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CodeGeeX-4"
    }
   ]
  },
  {
   "slug": "zhipuai/coding-glm-4.5-air",
   "model_name": "coding-glm-4.5-air",
   "display_name": "coding-glm-4.5-air",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.014"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.084"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-glm-4.5-air"
    }
   ]
  },
  {
   "slug": "zhipuai/coding-glm-4.6",
   "model_name": "coding-glm-4.6",
   "display_name": "coding-glm-4.6",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21999996"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.010998"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-glm-4.6"
    }
   ]
  },
  {
   "slug": "zhipuai/coding-glm-4.7",
   "model_name": "coding-glm-4.7",
   "display_name": "Coding-GLM-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.548"
      }
     }
    }
   ],
   "released_at": "2025-12-22",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding-GLM-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/coding-glm-5",
   "model_name": "coding-glm-5",
   "display_name": "coding-glm-5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21999996"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-glm-5"
    }
   ]
  },
  {
   "slug": "zhipuai/coding-glm-5-turbo",
   "model_name": "coding-glm-5-turbo",
   "display_name": "coding-glm-5-turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21999996"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-glm-5-turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/coding-glm-5.1-free",
   "model_name": "coding-glm-5.1-free",
   "display_name": "Coding GLM 5.1",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.013"
      }
     },
     "provider_model_id": "coding-glm-5.1"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-04-11",
   "max_input_tokens": 200000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "coding-glm-5.1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Coding GLM 5.1"
    }
   ]
  },
  {
   "slug": "zhipuai/coding-glm-5.2",
   "model_name": "coding-glm-5.2",
   "display_name": "coding-glm-5.2",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21999996"
      }
     }
    }
   ],
   "modalities": {
    "input": [
     "text"
    ],
    "output": []
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "coding-glm-5.2"
    }
   ]
  },
  {
   "slug": "zhipuai/cogvideox-2",
   "model_name": "cogvideox-2",
   "display_name": "CogVideoX-2",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.073529"
      }
     }
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "CogVideoX-2是智谱推出的新一代视频生成基础模型，图像转视频能力提升38%。在大规模动作处理、视觉稳定性、指令遵循性、艺术风格和整体视觉美感方面实现了显著增强。",
    "zh-TW": "CogVideoX-2是智譜新一代影像生成基礎模型，影像生成能力提升38%。在大規模動作處理、視覺穩定性、指令遵循性、藝術風格及整體視覺美學方面有顯著增強。",
    "ja-JP": "CogVideoX-2は、Zhipuの新世代ビデオ生成基盤モデルで、画像からビデオへの変換能力が38%向上しました。大規模な動きの処理、視覚的安定性、指示の遵守、芸術的スタイル、全体的な視覚美学において大幅な改善を実現します。",
    "ru-RU": "CogVideoX-2 — новая модель генерации видео от Zhipu, с улучшением возможностей преобразования изображения в видео на 38%. Она обеспечивает значительные улучшения в обработке крупномасштабных движений, визуальной стабильности, следовании инструкциям, художественном стиле и общей визуальной эстетике."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CogVideoX-2"
    }
   ]
  },
  {
   "slug": "zhipuai/cogvideox-3",
   "model_name": "cogvideox-3",
   "display_name": "CogVideoX-3",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0.147059"
      }
     }
    }
   ],
   "released_at": "2025-07-15",
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "CogVideoX-3新增起始帧和结束帧生成功能，大幅提升视觉稳定性和清晰度。支持平滑自然的大规模主体运动，提供更好的指令遵循性和更真实的物理模拟，并进一步提升高清真实感和3D风格场景的表现能力。",
    "zh-TW": "CogVideoX-3新增起始及結束影格生成功能，顯著提升視覺穩定性及清晰度。實現流暢自然的大規模主題動作，提供更好的指令遵循性及更真實的物理模擬，並進一步提升高解析度真實及3D風格場景的性能。",
    "ja-JP": "CogVideoX-3は、開始フレームと終了フレームの生成機能を追加し、視覚的安定性と明瞭性を大幅に向上させます。滑らかで自然な大規模な被写体の動きを可能にし、指示の遵守とより現実的な物理シミュレーションを提供します。高精細なリアルなシーンや3Dスタイルのシーンでのパフォーマンスをさらに向上させます。",
    "ru-RU": "CogVideoX-3 добавляет функцию генерации начальных и конечных кадров, значительно улучшая визуальную стабильность и четкость. Она обеспечивает плавные и естественные крупномасштабные движения объектов, лучшее следование инструкциям и более реалистичную физическую симуляцию, а также улучшает производительность в высококачественных реалистичных и 3D-стилях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CogVideoX-3"
    }
   ]
  },
  {
   "slug": "zhipuai/cogvideox-flash",
   "model_name": "cogvideox-flash",
   "display_name": "CogVideoX-Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "video_output": {
       "unit": "per_request",
       "price": "0"
      }
     }
    }
   ],
   "model_type": "video_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "CogVideoX-Flash是智谱发布的免费视频生成模型，能够生成遵循用户指令的视频，同时实现更高的美学质量评分。",
    "zh-TW": "CogVideoX-Flash是智譜發布的免費影像生成模型，能生成符合用戶指令的影像，同時達到更高的美學質量分數。",
    "ja-JP": "CogVideoX-Flashは、Zhipuがリリースした無料のビデオ生成モデルで、ユーザーの指示に従いながら、より高い美的品質スコアを達成するビデオを生成できます。",
    "ru-RU": "CogVideoX-Flash — бесплатная модель генерации видео от Zhipu, способная создавать видео, следуя инструкциям пользователя, с достижением более высоких оценок эстетического качества."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CogVideoX-Flash"
    }
   ]
  },
  {
   "slug": "zhipuai/cogview-3",
   "model_name": "cogview-3",
   "display_name": "cogview-3",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "35.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "35.5"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cogview-3"
    }
   ]
  },
  {
   "slug": "zhipuai/cogview-3-flash",
   "model_name": "cogview-3-flash",
   "display_name": "CogView-3-Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0"
      }
     }
    }
   ],
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "CogView-3-Flash 是智谱推出的免费图像生成模型。它能够根据用户指令生成与之匹配的图像，同时实现更高的美学质量评分。CogView-3-Flash 主要应用于艺术创作、设计参考、游戏开发和虚拟现实等领域，帮助用户快速将文本描述转化为图像。",
    "zh-TW": "CogView-3-Flash 是智譜推出的免費圖像生成模型。它能根據使用者指令生成符合要求的圖像，同時達到更高的美學品質分數。CogView-3-Flash 主要應用於藝術創作、設計參考、遊戲開發和虛擬現實等領域，幫助使用者快速將文字描述轉換為圖像。",
    "ja-JP": "CogView-3-Flashは、Zhipuが提供する無料の画像生成モデルです。ユーザーの指示に沿った画像を生成し、より高い美的品質スコアを実現します。CogView-3-Flashは主に、芸術的創作、デザインの参考、ゲーム開発、仮想現実などの分野で使用され、テキストの説明を迅速に画像に変換することを支援します。",
    "ru-RU": "CogView-3-Flash — это бесплатная модель генерации изображений, запущенная Zhipu. Она создает изображения, соответствующие инструкциям пользователя, при этом достигая более высоких оценок эстетического качества. CogView-3-Flash в основном используется в таких областях, как художественное творчество, дизайн, разработка игр и виртуальная реальность, помогая пользователям быстро преобразовывать текстовые описания в изображения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CogView-3-Flash"
    }
   ]
  },
  {
   "slug": "zhipuai/cogview-3-plus",
   "model_name": "cogview-3-plus",
   "display_name": "cogview-3-plus",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "10"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "cogview-3-plus"
    }
   ]
  },
  {
   "slug": "zhipuai/cogview-4",
   "model_name": "cogview-4",
   "display_name": "CogView-4",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.008824"
      }
     }
    }
   ],
   "released_at": "2025-03-04",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "CogView-4 是智谱推出的首个支持中文字符生成的开源文生图模型，提升了语义理解、图像质量和中英文文本渲染能力，支持任意长度的中英文提示词，并可在指定范围内生成任意分辨率图像。",
    "zh-TW": "CogView-4 是智譜推出的首款開源文字轉圖像模型，支援中文字符生成。它提升了語意理解、圖像品質與中英文文字渲染能力，支援任意長度的雙語提示詞，並可在指定範圍內生成任意解析度的圖像。",
    "ja-JP": "CogView-4はZhipuが開発した初のオープンソースのテキストから画像への生成モデルであり、中国語の文字生成に対応しています。意味理解、画像品質、中英テキストの描画能力が向上し、任意の長さのバイリンガルプロンプトをサポートし、指定範囲内で任意の解像度の画像を生成できます。",
    "ru-RU": "CogView-4 — первая открытая модель от Zhipu для генерации изображений по тексту с поддержкой китайских иероглифов. Улучшает семантическое понимание, качество изображений и рендеринг текста на китайском и английском языках, поддерживает произвольную длину двуязычных подсказок и может генерировать изображения в любом разрешении в заданных пределах."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "CogView-4"
    }
   ]
  },
  {
   "slug": "zhipuai/e2ee-glm-4-7-p",
   "model_name": "e2ee-glm-4-7-p",
   "display_name": "GLM 4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.15"
      }
     }
    }
   ],
   "released_at": "2026-03-18",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/e2ee-glm-5-1",
   "model_name": "e2ee-glm-5-1",
   "display_name": "GLM 5.1",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.15"
      }
     }
    }
   ],
   "released_at": "2026-04-24",
   "max_input_tokens": 200000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.1"
    }
   ]
  },
  {
   "slug": "zhipuai/e2ee-glm-5-2-p",
   "model_name": "e2ee-glm-5-2-p",
   "display_name": "GLM 5.2",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.75"
      }
     }
    }
   ],
   "released_at": "2026-06-16",
   "max_input_tokens": 524288,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2"
    }
   ]
  },
  {
   "slug": "zhipuai/emohaa",
   "model_name": "emohaa",
   "display_name": "Emohaa",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.205882"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 4000,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "Emohaa 是一款心理健康模型，具备专业咨询能力，帮助用户理解情绪问题。",
    "zh-TW": "Emohaa 是一款心理健康模型，具備專業諮詢能力，協助使用者理解情緒問題。",
    "ja-JP": "Emohaa は、専門的なカウンセリング能力を備えたメンタルヘルスモデルで、ユーザーが感情的な問題を理解するのを支援します。",
    "ru-RU": "Emohaa — модель для поддержки психического здоровья с профессиональными навыками консультирования, помогающая пользователям разобраться в эмоциональных проблемах."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Emohaa"
    }
   ]
  },
  {
   "slug": "zhipuai/fireworks/models/glm-4p7-flash",
   "model_name": "fireworks/models/glm-4p7-flash",
   "display_name": "GLM-4.7 Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "accounts/fireworks/models/glm-4p7-flash"
    }
   ],
   "max_input_tokens": 202752,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/glm-4p7-flash"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.7 Flash"
    }
   ]
  },
  {
   "slug": "zhipuai/fireworks/models/glm-5p2-fp8",
   "model_name": "fireworks/models/glm-5p2-fp8",
   "display_name": "GLM 5.2 FP8",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/glm-5p2-fp8"
    }
   ],
   "max_input_tokens": 1048576,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/glm-5p2-fp8"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2 FP8"
    }
   ]
  },
  {
   "slug": "zhipuai/fireworks/routers/glm-5p2-fast",
   "model_name": "fireworks/routers/glm-5p2-fast",
   "display_name": "GLM 5.2 Fast",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.21"
      }
     },
     "provider_model_id": "accounts/fireworks/routers/glm-5p2-fast"
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2026-06-26",
   "max_input_tokens": 1048575,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/routers/glm-5p2-fast"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2 Fast"
    }
   ]
  },
  {
   "slug": "zhipuai/glm",
   "model_name": "glm",
   "display_name": "glm",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.79914765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.85409875"
      }
     }
    }
   ],
   "released_at": "2026-01-19",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592687",
     "new": "2.85409875"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800595236",
     "new": "0.79914765"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.858164925",
     "new": "2.8592687"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800286179",
     "new": "0.800595236"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.860353575",
     "new": "2.858164925"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800899001",
     "new": "0.800286179"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592021",
     "new": "2.860353575"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800576588",
     "new": "0.800899001"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.859994675",
     "new": "2.8592021"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800798509",
     "new": "0.800576588"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8452425",
     "new": "2.859994675"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.7966679",
     "new": "0.800798509"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-3-turbo",
   "model_name": "glm-3-turbo",
   "display_name": "glm-3-turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.71"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.71"
      }
     }
    }
   ],
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-3-turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4",
   "model_name": "glm-4",
   "display_name": "GLM-4",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.2"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.994"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.994"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-01-16",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4 是 2024 年 1 月发布的旧版旗舰模型，现已由更强的 GLM-4-0520 替代。",
    "zh-TW": "GLM-4 是 2024 年 1 月推出的舊版旗艦模型，現已由更強的 GLM-4-0520 取代。",
    "ja-JP": "GLM-4 は2024年1月にリリースされた旧フラッグシップモデルで、現在はより強力な GLM-4-0520 に置き換えられています。",
    "ru-RU": "GLM-4 — предыдущая флагманская модель, выпущенная в январе 2024 года, теперь заменена более мощной GLM-4-0520."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4_5",
   "model_name": "GLM-4_5",
   "display_name": "GLM-4_5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.51495962"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.05983848"
      }
     }
    }
   ],
   "released_at": "2025-07-29",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.06082352",
     "new": "2.05983848"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.51520588",
     "new": "0.51495962"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.06225516",
     "new": "2.06082352"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.51556379",
     "new": "0.51520588"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.06442908",
     "new": "2.06225516"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.51610727",
     "new": "0.51556379"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.06485062",
     "new": "2.06442908"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.516212655",
     "new": "0.51610727"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.06411968",
     "new": "2.06485062"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.51602992",
     "new": "0.516212655"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.0605053",
     "new": "2.06411968"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.515126325",
     "new": "0.51602992"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4_5"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4_5-Air",
   "model_name": "GLM-4_5-Air",
   "display_name": "GLM-4_5-Air",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14713132"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88278792"
      }
     }
    }
   ],
   "released_at": "2025-07-29",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.88321008",
     "new": "0.88278792"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14720168",
     "new": "0.14713132"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.88382364",
     "new": "0.88321008"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14730394",
     "new": "0.14720168"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.88475532",
     "new": "0.88382364"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14745922",
     "new": "0.14730394"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.88493598",
     "new": "0.88475532"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14748933",
     "new": "0.14745922"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.88462272",
     "new": "0.88493598"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14743712",
     "new": "0.14748933"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.8830737",
     "new": "0.88462272"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.14717895",
     "new": "0.14743712"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4_5-Air"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4_5V",
   "model_name": "GLM-4_5V",
   "display_name": "GLM-4_5V",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.76557584"
      }
     }
    }
   ],
   "released_at": "2025-08-12",
   "max_output_tokens": 64000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76642016",
     "new": "1.76557584"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76764728",
     "new": "1.76642016"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76951064",
     "new": "1.76764728"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58983688",
     "new": "0.58921576"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76987196",
     "new": "1.76951064"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58995732",
     "new": "0.58983688"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.76924544",
     "new": "1.76987196"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58974848",
     "new": "0.58995732"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "1.7661474",
     "new": "1.76924544"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.5887158",
     "new": "0.58974848"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4_5V"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-0520",
   "model_name": "glm-4-0520",
   "display_name": "GLM-4-0520",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4-0520 是最新版本模型，专为处理高度复杂与多样化任务而设计，性能卓越。",
    "zh-TW": "GLM-4-0520 是最新版本模型，專為高度複雜與多樣化任務設計，具備卓越效能。",
    "ja-JP": "GLM-4-0520 は最新バージョンのモデルで、非常に複雑かつ多様なタスクに対応し、優れた性能を発揮します。",
    "ru-RU": "GLM-4-0520 — последняя версия модели, разработанная для сложных и разнообразных задач с отличной производительностью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4-0520"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4-32B",
   "model_name": "GLM-4-32B",
   "display_name": "Z.ai: GLM 4 32B ",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "z-ai/glm-4-32b"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2780781948"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2780781948"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "glm-4-32b"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-07-25",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "open_weights": true,
    "stream": true
   },
   "deprecated": true,
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "glm-4-32b",
    "z-ai/glm-4-32b"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.2782111752",
     "new": "0.2780781948"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2782111752",
     "new": "0.2780781948"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.2784044466",
     "new": "0.2782111752"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2784044466",
     "new": "0.2782111752"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.2786979258",
     "new": "0.2784044466"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2786979258",
     "new": "0.2784044466"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.2787548337",
     "new": "0.2786979258"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2787548337",
     "new": "0.2786979258"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.2786561568",
     "new": "0.2787548337"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2786561568",
     "new": "0.2787548337"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "0.2781682155",
     "new": "0.2786561568"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.2781682155",
     "new": "0.2786561568"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Z.ai: GLM 4 32B "
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4-32B-0414",
   "model_name": "GLM-4-32B-0414",
   "display_name": "GLM 4 32B 0414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "THUDM/GLM-4-32B-0414"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.66"
      }
     },
     "provider_model_id": "zai-org/GLM-4-32B-0414"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "THUDM/GLM-4-32B-0414"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.66"
      }
     },
     "provider_model_id": "thudm/glm-4-32b-0414"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.277941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.277941"
      }
     },
     "provider_model_id": "THUDM/GLM-4-32B-0414"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "THUDM/GLM-4-32B-0414"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-04-14",
   "max_input_tokens": 128000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "THUDM/GLM-4-32B-0414",
    "thudm/glm-4-32b-0414",
    "zai-org/GLM-4-32B-0414"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4-32B-0414是下一代开放GLM模型，拥有32B参数，性能可与OpenAI GPT及DeepSeek V3/R1系列媲美。",
    "zh-TW": "GLM-4-32B-0414 是新一代開源 GLM 模型，擁有 32B 參數，性能可與 OpenAI GPT 與 DeepSeek V3/R1 系列媲美。",
    "ja-JP": "GLM-4-32B-0414は、次世代のオープンGLMモデルで、32Bパラメータを持ち、OpenAI GPTやDeepSeek V3/R1シリーズと同等の性能を発揮します。",
    "ru-RU": "GLM-4-32B-0414 — это модель нового поколения с открытым исходным кодом на базе GLM с 32 миллиардами параметров, сопоставимая по производительности с OpenAI GPT и сериями DeepSeek V3/R1."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4 32B 0414"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-32b-0414-128k",
   "model_name": "glm-4-32b-0414-128k",
   "display_name": "GLM-4 32B (0414-128k)",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "zai/glm-4-32b-0414-128k"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-04-14",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai/glm-4-32b-0414-128k"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4 32B (0414-128k)"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4-9B-0414",
   "model_name": "GLM-4-9B-0414",
   "display_name": "GLM 4 9B 0414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "THUDM/GLM-4-9B-0414"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "THUDM/GLM-4-9B-0414"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "THUDM/GLM-4-9B-0414"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.086"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.086"
      }
     },
     "provider_model_id": "THUDM/GLM-4-9B-0414"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-04-14",
   "max_input_tokens": 32000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "THUDM/GLM-4-9B-0414"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4-9B-0414是9B参数的GLM模型，继承GLM-4-32B技术，部署更轻量，擅长代码生成、网页设计、SVG生成与基于搜索的写作。",
    "zh-TW": "GLM-4-9B-0414 是一款 9B 參數的 GLM 模型，繼承 GLM-4-32B 技術，部署更輕量。其在程式碼生成、網頁設計、SVG 生成與搜尋式寫作方面表現優異。",
    "ja-JP": "GLM-4-9B-0414は、GLM-4-32Bの技術を継承しつつ、軽量なデプロイメントを可能にした9Bモデルです。コード生成、Webデザイン、SVG生成、検索ベースのライティングに優れた性能を発揮します。",
    "ru-RU": "GLM-4-9B-0414 — это модель GLM с 9 миллиардами параметров, унаследовавшая технологии GLM-4-32B и обеспечивающая более лёгкое развертывание. Отлично справляется с генерацией кода, веб-дизайном, созданием SVG и написанием текстов на основе поиска."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4 9B 0414"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-9b-chat",
   "model_name": "glm-4-9b-chat",
   "display_name": "thudm/glm-4-9b-chat",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "ppio",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      }
     },
     "provider_model_id": "thudm/glm-4-9b-chat"
    }
   ],
   "max_input_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "thudm/glm-4-9b-chat"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4-9B-Chat 在语义、数学、推理、编程与知识方面表现强劲，支持网页浏览、代码执行、自定义工具调用与长文本推理，支持包括日语、韩语、德语在内的 26 种语言。",
    "zh-TW": "GLM-4-9B-Chat 在語義、數學、推理、程式與知識方面表現優異，並支援網頁瀏覽、程式執行、自訂工具調用與長文本推理，支援包括日語、韓語、德語在內的 26 種語言。",
    "ja-JP": "GLM-4-9B-Chat は、意味理解、数学、推論、コード、知識において高い性能を発揮します。ウェブ閲覧、コード実行、カスタムツール呼び出し、長文推論をサポートし、日本語、韓国語、ドイツ語を含む26言語に対応しています。",
    "ru-RU": "GLM-4-9B-Chat демонстрирует высокие результаты в семантике, математике, логике, программировании и знаниях. Поддерживает веб-браузинг, выполнение кода, вызов пользовательских инструментов и рассуждение над длинными текстами. Поддерживает 26 языков, включая японский, корейский и немецкий."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "thudm/glm-4-9b-chat"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-air",
   "model_name": "glm-4-air",
   "display_name": "GLM-4 Air",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-06-05",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4-Air 是一款高性价比模型，性能接近 GLM-4，速度快、成本低。",
    "zh-TW": "GLM-4-Air 是一款高性價比選擇，效能接近 GLM-4，速度快且成本低。",
    "ja-JP": "GLM-4-Air は、GLM-4 に近い性能を持ちながら、高速かつ低コストで利用できる高コストパフォーマンスモデルです。",
    "ru-RU": "GLM-4-Air — выгодный вариант с производительностью, близкой к GLM-4, высокой скоростью и низкой стоимостью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4 Air"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-air-0111",
   "model_name": "glm-4-air-0111",
   "display_name": "GLM 4 Air 0111",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1394"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1394"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-01-11",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4 Air 0111"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-air-250414",
   "model_name": "glm-4-air-250414",
   "display_name": "GLM-4-Air-250414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4-Air 是一款高性价比模型，性能接近 GLM-4，速度快、成本低。",
    "zh-TW": "GLM-4-Air 是一款高性價比選擇，效能接近 GLM-4，速度快且成本低。",
    "ja-JP": "GLM-4-Air は、GLM-4 に近い性能を持ちながら、高速かつ低コストで利用できる高コストパフォーマンスモデルです。",
    "ru-RU": "GLM-4-Air — выгодный вариант с производительностью, близкой к GLM-4, высокой скоростью и низкой стоимостью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4-Air-250414"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-airx",
   "model_name": "glm-4-airx",
   "display_name": "GLM-4-AirX",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.006"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "max_output_tokens": 4095,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-06-05",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4-AirX 是 GLM-4-Air 的高效变体，推理速度提升至 2.6 倍。",
    "zh-TW": "GLM-4-AirX 是 GLM-4-Air 的高效版本，推理速度提升至 2.6 倍。",
    "ja-JP": "GLM-4-AirX は、GLM-4-Air のより効率的なバリアントで、最大2.6倍の高速推論を実現します。",
    "ru-RU": "GLM-4-AirX — более эффективный вариант GLM-4-Air с ускорением рассуждений до 2.6 раз."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4-AirX"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-alltools",
   "model_name": "glm-4-alltools",
   "display_name": "GLM-4-AllTools",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.705882"
      }
     }
    }
   ],
   "max_input_tokens": 128000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4-AllTools 是一款多功能智能体模型，优化用于复杂指令规划与工具使用，如网页浏览、代码解释与文本生成，适合多任务执行。",
    "zh-TW": "GLM-4-AllTools 是一款多功能智能體模型，針對複雜指令規劃與工具使用（如網頁瀏覽、程式解釋、文本生成）進行優化，適合多任務執行。",
    "ja-JP": "GLM-4-AllTools は、ウェブ閲覧、コード解説、テキスト生成などのツール使用と複雑な指示計画に最適化された多機能エージェントモデルで、マルチタスク実行に適しています。",
    "ru-RU": "GLM-4-AllTools — универсальная агентная модель, оптимизированная для сложного планирования инструкций и использования инструментов, таких как веб-браузинг, объяснение кода и генерация текста. Подходит для многозадачного выполнения."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4-AllTools"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-flash",
   "model_name": "glm-4-flash",
   "display_name": "GLM-4 Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.1003"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-08-01",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4-Flash 适用于简单任务：速度最快且免费。",
    "zh-TW": "GLM-4-Flash 適合簡單任務：速度最快且免費。",
    "ja-JP": "GLM-4-Flash は、シンプルなタスクに最適：最速かつ無料で利用可能です。",
    "ru-RU": "GLM-4-Flash идеально подходит для простых задач: самая быстрая и бесплатная."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4 Flash"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-flash-250414",
   "model_name": "glm-4-flash-250414",
   "display_name": "GLM-4-Flash-250414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4-Flash 适用于简单任务：速度最快且免费。",
    "zh-TW": "GLM-4-Flash 適合簡單任務：速度最快且免費。",
    "ja-JP": "GLM-4-Flash は、シンプルなタスクに最適：最速かつ無料で利用可能です。",
    "ru-RU": "GLM-4-Flash идеально подходит для простых задач: самая быстрая и бесплатная."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4-Flash-250414"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-flashx",
   "model_name": "glm-4-flashx",
   "display_name": "GLM-4-FlashX-250414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.014706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.014706"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.014706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.014706"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 4095,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4-FlashX 是 Flash 的增强版，具备超快推理能力。",
    "zh-TW": "GLM-4-FlashX 是 Flash 的增強版，具備超快推理能力。",
    "ja-JP": "GLM-4-FlashX は、超高速推論を実現した Flash の強化版です。",
    "ru-RU": "GLM-4-FlashX — улучшенная версия Flash с ультрабыстрым рассуждением."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4-FlashX-250414"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-long",
   "model_name": "glm-4-long",
   "display_name": "GLM-4-Long",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2006"
      }
     }
    }
   ],
   "max_input_tokens": 1024000,
   "max_output_tokens": 4095,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-08-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4-Long 支持超长输入，适用于记忆类任务与大规模文档处理。",
    "zh-TW": "GLM-4-Long 支援超長輸入，適用於記憶型任務與大規模文件處理。",
    "ja-JP": "GLM-4-Long は、記憶型タスクや大規模文書処理のための超長文入力をサポートします。",
    "ru-RU": "GLM-4-Long поддерживает сверхдлинные входные данные для задач, связанных с памятью, и обработки больших документов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4-Long"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-plus",
   "model_name": "glm-4-plus",
   "display_name": "GLM-4-Plus",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.352941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.352941"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.497"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.497"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 4095,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "web_search": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-08-01",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4-Plus 是一款高智能旗舰模型，具备强大的长文本与复杂任务处理能力，整体性能全面升级。",
    "zh-TW": "GLM-4-Plus 是高智能旗艦模型，擅長處理長文本與複雜任務，整體效能全面升級。",
    "ja-JP": "GLM-4-Plus は、高度な知能を備えたフラッグシップモデルで、長文や複雑なタスク処理に強く、全体的な性能が向上しています。",
    "ru-RU": "GLM-4-Plus — флагманская модель с высоким уровнем интеллекта, сильной поддержкой длинных текстов и сложных задач, а также улучшенной общей производительностью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4-Plus"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4-plus-0111",
   "model_name": "glm-4-plus-0111",
   "display_name": "GLM 4 Plus 0111",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "9.996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "9.996"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-02-19",
   "max_input_tokens": 128000,
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4 Plus 0111"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.1v-thinking-flash",
   "model_name": "glm-4.1v-thinking-flash",
   "display_name": "GLM-4.1V-Thinking-Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-07-09",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4.1V-Thinking 是目前已知最强的约 100 亿参数视觉语言模型，覆盖视频理解、图像问答、学科解题、OCR、文档与图表阅读、GUI 智能体、前端编程与视觉定位等 SOTA 任务。通过先进的强化学习，采用思维链推理提升准确性与丰富性，在结果与可解释性方面均优于传统非思考模型。",
    "zh-TW": "GLM-4.1V-Thinking 是目前已知最強的約 10B 視覺語言模型，涵蓋影片理解、圖像問答、學科解題、OCR、文件與圖表閱讀、GUI 智能體、前端編碼與語義對齊等 SOTA 任務。透過先進強化學習與思考鏈推理，提升準確性與豐富度，超越傳統非思考模型的結果與可解釋性。",
    "ja-JP": "GLM-4.1V-Thinking は、既知の中で最も強力な約10Bの視覚言語モデル（VLM）で、動画理解、画像Q&A、科目解答、OCR、文書・チャート読解、GUIエージェント、フロントエンドコーディング、グラウンディングなどの最先端タスクに対応します。Qwen2.5-VL-72B（8倍のサイズ）を多くのタスクで上回ります。高度な強化学習（RL）により、思考の連鎖（Chain-of-Thought）推論を活用し、精度と情報の豊かさを向上させ、従来の非思考モデルを成果と説明性の両面で凌駕します。",
    "ru-RU": "GLM-4.1V-Thinking — самая мощная известная ~10B VLM, охватывающая передовые задачи, такие как понимание видео, визуальные вопросы и ответы, решение предметных задач, OCR, чтение документов и графиков, GUI-агенты, фронтенд-кодирование и привязка. Превосходит даже 8 раз более крупную Qwen2.5-VL-72B по многим задачам. Использует цепочку рассуждений для повышения точности и объяснимости, превосходя традиционные модели без мышления."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.1V-Thinking-Flash"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.1v-thinking-flashx",
   "model_name": "glm-4.1v-thinking-flashx",
   "display_name": "GLM-4.1V-Thinking-FlashX",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "max_input_tokens": 65536,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-07-09",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4.1V-Thinking 是目前已知最强的约 100 亿参数视觉语言模型，覆盖视频理解、图像问答、学科解题、OCR、文档与图表阅读、GUI 智能体、前端编程与视觉定位等 SOTA 任务。通过先进的强化学习，采用思维链推理提升准确性与丰富性，在结果与可解释性方面均优于传统非思考模型。",
    "zh-TW": "GLM-4.1V-Thinking 是目前已知最強的約 10B 視覺語言模型，涵蓋影片理解、圖像問答、學科解題、OCR、文件與圖表閱讀、GUI 智能體、前端編碼與語義對齊等 SOTA 任務。透過先進強化學習與思考鏈推理，提升準確性與豐富度，超越傳統非思考模型的結果與可解釋性。",
    "ja-JP": "GLM-4.1V-Thinking は、既知の中で最も強力な約10Bの視覚言語モデル（VLM）で、動画理解、画像Q&A、科目解答、OCR、文書・チャート読解、GUIエージェント、フロントエンドコーディング、グラウンディングなどの最先端タスクに対応します。Qwen2.5-VL-72B（8倍のサイズ）を多くのタスクで上回ります。高度な強化学習（RL）により、思考の連鎖（Chain-of-Thought）推論を活用し、精度と情報の豊かさを向上させ、従来の非思考モデルを成果と説明性の両面で凌駕します。",
    "ru-RU": "GLM-4.1V-Thinking — самая мощная известная ~10B VLM, охватывающая передовые задачи, такие как понимание видео, визуальные вопросы и ответы, решение предметных задач, OCR, чтение документов и графиков, GUI-агенты, фронтенд-кодирование и привязка. Превосходит даже 8 раз более крупную Qwen2.5-VL-72B по многим задачам. Использует цепочку рассуждений для повышения точности и объяснимости, превосходя традиционные модели без мышления."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.1V-Thinking-FlashX"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.5",
   "model_name": "glm-4.5",
   "display_name": "GLM-4.5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "cache_read_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "cache_read_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "2.058824"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.142"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/glm-4.5"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.058824"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.67"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.46"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "litellm+truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.6"
      }
     },
     "provider_model_id": "GLM-4.5"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0799999993"
      }
     },
     "provider_model_id": "z-ai/glm-4.5"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/glm-4.5"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "z-ai/glm-4.5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai/glm-4.5"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai/glm-4.5"
    },
    {
     "provider": "modelscope",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ZhipuAI/GLM-4.5"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.3"
      }
     },
     "provider_model_id": "zai-org/glm-4.5"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.75"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai-org/glm-4.5"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai-org/glm-4.5"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "z-ai/glm-4.5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-4.5"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.31884"
      }
     }
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "deepinfra/zai-org/GLM-4.5"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai/glm-4.5"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai/glm-4.5"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.54"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-4.5",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.512403",
        "cache_read": "1.664286",
        "prompt": "1.663714"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful",
   "released_at": "2025-07-28",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 98304,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.75
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "GLM-4.5",
    "ZhipuAI/GLM-4.5",
    "deepinfra/zai-org/GLM-4.5",
    "novita/zai-org/glm-4.5",
    "z-ai/glm-4.5",
    "zai-org/GLM-4.5",
    "zai-org/GLM-4.5:thinking",
    "zai-org/glm-4.5",
    "zai/GLM-4.5",
    "zai/glm-4.5"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.5：高性能模型，适用于推理、编程和代理任务。",
    "zh-TW": "GLM-4.5：高性能模型，用於推理、編程和代理任務。",
    "ja-JP": "GLM-4.5: 推論、コーディング、エージェントタスク向けの高性能モデル。",
    "ru-RU": "GLM-4.5: Высокопроизводительная модель для рассуждений, программирования и агентных задач."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.5-air",
   "model_name": "glm-4.5-air",
   "display_name": "GLM-4.5-Air",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.023529"
      },
      "cache_read_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.035294"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "completion_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.84"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      }
     }
    },
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      }
     },
     "provider_model_id": "z-ai/glm-4.5-air"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.87"
      }
     }
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-Air"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.34"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "z-ai/glm-4.5-air"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-Air"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.156667"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.936667"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.078334"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-Air"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1567"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9367"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0783"
      }
     },
     "provider_model_id": "glm-4-5-air"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "z-ai/glm-4.5-air"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "zai/glm-4.5-air"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai/glm-4.5-air"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.12"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-Air"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.25"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-Air"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      }
     },
     "provider_model_id": "zai-org/glm-4.5-air"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "zai-org/glm-4.5-air"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.025"
      }
     },
     "provider_model_id": "z-ai/glm-4.5-air"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-4.5-air"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "deepinfra/zai-org/GLM-4.5-Air"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-Air"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-Air"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-Air"
    },
    {
     "provider": "submodel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-Air"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "glm-4-5-air"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8500000599999998"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02500004"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.13"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.13"
      }
     },
     "provider_model_id": "z-ai/glm-4.5-air"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "zai/glm-4.5-air"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "zai/glm-4.5-air"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.56"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-4.5-air",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "2.079464",
        "cache_read": "1.745",
        "prompt": "1.588182"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zhipuai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Lighter GLM-4.5 variant for fast coding assistance and cheaper agents",
   "released_at": "2025-07-28",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 98304,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm-air",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.75
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/zai-org/GLM-4.5-Air",
    "glm-4-5-air",
    "glm-4.5-air:free",
    "z-ai/glm-4.5-air",
    "z-ai/glm-4.5-air:free",
    "zai-org/GLM-4.5-Air",
    "zai-org/GLM-4.5-Air:thinking",
    "zai-org/glm-4.5-air",
    "zai-org/glm-4.5-air:thinking",
    "zai/glm-4.5-air"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.5-Air：轻量版，响应速度更快。",
    "zh-TW": "GLM-4.5-Air：輕量版，提供快速回應。",
    "ja-JP": "GLM-4.5-Air: 高速応答のための軽量版。",
    "ru-RU": "GLM-4.5-Air: Легковесная версия для быстрых ответов."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "delisted",
     "note": "deprecated"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4.5-Air-FP8",
   "model_name": "GLM-4.5-Air-FP8",
   "display_name": "Glm 4.5 Air Fp8",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-Air-FP8"
    }
   ],
   "docs_url": "https://www.together.ai/models/glm-4-5-air",
   "max_input_tokens": 128000,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "parallel_function_calling": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "released_at": "2025-07-30",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-4.5-Air-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Glm 4.5 Air Fp8"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.5-airx",
   "model_name": "glm-4.5-airx",
   "display_name": "GLM-4.5-AirX",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "cache_read_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.235294"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "completion_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "4.705882"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.714"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.51"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.22"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      }
     },
     "provider_model_id": "zai/glm-4.5-airx"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 98304,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "prompt_caching": true
   },
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-07-29",
   "knowledge_cutoff": "2025-04",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai/glm-4.5-airx"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.5-Air 快速版，响应更快，适用于大规模高速使用场景。",
    "zh-TW": "GLM-4.5-Air 快速版，回應更迅速，適用於大規模高速應用。",
    "ja-JP": "GLM-4.5-Air の高速版で、大規模かつ高速な利用に対応する迅速な応答を実現します。",
    "ru-RU": "GLM-4.5-AirX — ускоренная версия с быстрым откликом для масштабных и высокоскоростных сценариев."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.5-AirX"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.5-flash",
   "model_name": "glm-4.5-flash",
   "display_name": "GLM-4.5-Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2025-07-28",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 131072,
   "max_output_tokens": 98304,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm-flash",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking"
  },
  {
   "slug": "zhipuai/GLM-4.5-FP8",
   "model_name": "GLM-4.5-FP8",
   "display_name": "GLM 4.5 FP8",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-FP8"
    },
    {
     "provider": "submodel",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-FP8"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-07-28",
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-4.5-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.5 FP8"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4.5-TEE",
   "model_name": "GLM-4.5-TEE",
   "display_name": "GLM 4.5 TEE",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.55"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 131072,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-4.5-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.5 TEE"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.5-x",
   "model_name": "glm-4.5-x",
   "display_name": "GLM-4.5-X",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.235294"
      },
      "cache_read_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "0.352941"
      },
      "cache_read_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "0.470588"
      },
      "prompt_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "prompt_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      },
      "prompt_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "completion_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "completion_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "4.705882"
      },
      "completion_0_032_0_128": {
       "unit": "per_M_tokens",
       "price": "9.411765"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.91"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.44"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.45"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.9"
      }
     },
     "provider_model_id": "zai/glm-4.5-x"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 98304,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "prompt_caching": true
   },
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-07-29",
   "knowledge_cutoff": "2025-04",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "status": "beta",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai/glm-4.5-x"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.5 快速版，生成速度高达每秒 100 个 token，性能强劲。",
    "zh-TW": "GLM-4.5 快速版，生成速度高達每秒 100 個 token，效能出色。",
    "ja-JP": "GLM-4.5 の高速版で、最大100トークン/秒の生成速度で高性能を実現します。",
    "ru-RU": "GLM-4.5 Fast — быстрая версия с производительностью до 100 токенов в секунду."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.5-X"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.5v",
   "model_name": "glm-4.5v",
   "display_name": "GLM-4.5V",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.274"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.822"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5V"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "zai-org/glm-4.5v"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "z-ai/glm-4.5v"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "zai/glm-4.5v"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.7999999999999998"
      }
     },
     "provider_model_id": "z-ai/glm-4.5v"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai-org/glm-4.5v"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai-org/glm-4.5v"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "z-ai/glm-4.5v"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5V"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     },
     "provider_model_id": "zai-org/GLM-4.5V"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai/glm-4.5v"
    },
    {
     "provider": "vercelaigateway",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     },
     "provider_model_id": "zai/glm-4.5v"
    },
    {
     "provider": "wenxin",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_032_0_064": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_032_0_064": {
       "unit": "per_M_tokens",
       "price": "1.764706"
      }
     }
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.8"
      }
     }
    }
   ],
   "intro": "GLM vision model for visual reasoning, documents, and multimodal agents",
   "released_at": "2025-08-11",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 64000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "max_tokens",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 0.75
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "z-ai/glm-4.5v",
    "z-ai/glm-4.5v:thinking",
    "zai-org/GLM-4.5V",
    "zai-org/glm-4.5v",
    "zai/glm-4.5v"
   ],
   "intro_i18n": {
    "zh-CN": "智谱下一代 MoE 视觉推理模型，总参数 106B，激活参数 12B，在图像、视频、文档理解与 GUI 任务中，在同规模开源多模态模型中表现领先。",
    "zh-TW": "智譜新一代 MoE 視覺推理模型，總參數 106B，啟用 12B，於圖像、影片、文件理解與 GUI 任務中，在同級開源多模態模型中達到 SOTA 水準。",
    "ja-JP": "智谱の次世代MoE視覚推論モデルで、総パラメータ数106B、アクティブ12B。画像、動画、文書理解、GUIタスクにおいて同規模のオープンソースマルチモーダルモデルの中で最先端の性能を実現します。",
    "ru-RU": "Модель визуального логического вывода нового поколения от Zhipu с архитектурой MoE: 106B параметров, 12B активных. Достигает SOTA среди моделей аналогичного размера в задачах обработки изображений, видео, документов и GUI."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.6",
   "model_name": "glm-4.6",
   "display_name": "GLM-4.6",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "cache_read_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "cache_read_0_032_0_2": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt_0_032_0_2": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "2.058824"
      },
      "completion_0_032_0_2": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.142"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/glm-4.6"
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.058824"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.65"
      }
     }
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "helicone-registry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.79914765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.85409875"
      }
     },
     "provider_model_id": "zai/glm-4.6"
    },
    {
     "provider": "canopywave",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "zai/glm-4.6"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.355"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.553"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.089"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6"
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0799999993"
      }
     },
     "provider_model_id": "z-ai/glm-4.6"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.44999999999999996"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6"
    },
    {
     "provider": "iflowcn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.058824"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "glm-4-6"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.175"
      }
     },
     "provider_model_id": "z-ai/glm-4.6"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai/glm-4.6"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai/glm-4.6"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.51495962"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.05983848"
      }
     },
     "provider_model_id": "GLM-4.6"
    },
    {
     "provider": "modelscope",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "ZhipuAI/GLM-4.6"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "z-ai/glm-4.6"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai-org/glm-4.6"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai-org/glm-4.6"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.74"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "z-ai/glm-4.6"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-4.6"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5556"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2222"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1111"
      }
     },
     "provider_model_id": "novita/glm-4.6"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.058824"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.852941"
      }
     },
     "provider_model_id": "z-ai/glm-4.6"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "novita/zai-org/glm-4.6"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     },
     "provider_model_id": "hf:zai-org/GLM-4.6"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "deepinfra/zai-org/GLM-4.6"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "GLM-4.6"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11000000000000001"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "z-ai/glm-4.6"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai/glm-4.6"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.54"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-4.6",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.512403",
        "cache_read": "1.664286",
        "prompt": "1.663714"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks",
   "released_at": "2025-09-30",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "status": "deprecated",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "docs_url": "https://openrouter.ai/z-ai/glm-4.6",
   "benchmarks": {
    "intelligence_index": 28.7,
    "coding_index": 45.8,
    "agentic_index": 17.7
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "GLM-4.6",
    "ZhipuAI/GLM-4.6",
    "deepinfra/zai-org/GLM-4.6",
    "glm-4-6",
    "glm-4.6:exacto",
    "hf:zai-org/GLM-4.6",
    "novita/glm-4.6",
    "novita/zai-org/glm-4.6",
    "z-ai/glm-4.6",
    "z-ai/glm-4.6:exacto",
    "z-ai/glm-4.6:thinking",
    "zai-org/GLM-4.6",
    "zai-org/glm-4.6",
    "zai-org/glm-4.6:thinking",
    "zai/GLM-4.6",
    "zai/glm-4.6"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.6：上一代模型。",
    "zh-TW": "GLM-4.6：上一代模型。",
    "ja-JP": "GLM-4.6: 前世代モデル。",
    "ru-RU": "GLM-4.6: Модель предыдущего поколения."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592687",
     "new": "2.85409875"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800595236",
     "new": "0.79914765"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.06082352",
     "new": "2.05983848"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.51520588",
     "new": "0.51495962"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.858164925",
     "new": "2.8592687"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800286179",
     "new": "0.800595236"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "llmgateway",
     "charge": "completion",
     "old": "2.007",
     "new": "2.2"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "llmgateway",
     "charge": "prompt",
     "old": "0.431",
     "new": "0.55"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.06225516",
     "new": "2.06082352"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.51556379",
     "new": "0.51520588"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.860353575",
     "new": "2.858164925"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800899001",
     "new": "0.800286179"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.06442908",
     "new": "2.06225516"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.51610727",
     "new": "0.51556379"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592021",
     "new": "2.860353575"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800576588",
     "new": "0.800899001"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.06485062",
     "new": "2.06442908"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.516212655",
     "new": "0.51610727"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.859994675",
     "new": "2.8592021"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800798509",
     "new": "0.800576588"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4.6-Derestricted-v5",
   "model_name": "GLM-4.6-Derestricted-v5",
   "display_name": "GLM 4.6 Derestricted v5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-12-23",
   "max_input_tokens": 131072,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.6 Derestricted v5"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4.6-FP8",
   "model_name": "GLM-4.6-FP8",
   "display_name": "GLM 4.6 FP8",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6-FP8"
    }
   ],
   "released_at": "2026-01-27",
   "max_input_tokens": 202752,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-4.6-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.6 FP8"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.6-original",
   "model_name": "glm-4.6-original",
   "display_name": "GLM 4.6 Original",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "zai-org/glm-4.6-original"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-12-11",
   "max_input_tokens": 256000,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-4.6-original"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.6 Original"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4.6-TEE",
   "model_name": "GLM-4.6-TEE",
   "display_name": "GLM 4.6 TEE",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.35"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 202752,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-4.6-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.6 TEE"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4.6-turbo:thinking",
   "model_name": "GLM-4.6-turbo:thinking",
   "display_name": "GLM 4.6 Turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6-turbo"
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2025-10-02",
   "max_input_tokens": 200000,
   "max_output_tokens": 204800,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-4.6-turbo",
    "zai-org/GLM-4.6-turbo:thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.6 Turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.6v",
   "model_name": "glm-4.6v",
   "display_name": "GLM-4.6V",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.029412"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.145"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.41"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0274"
      }
     }
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6V"
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "truefoundry+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6V"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      }
     }
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.055"
      }
     },
     "provider_model_id": "z-ai/glm-4.6v"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "zai/glm-4.6v"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "zai-org/glm-4.6v"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.055"
      }
     },
     "provider_model_id": "zai-org/glm-4.6v"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.055"
      }
     },
     "provider_model_id": "zai-org/glm-4.6v"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.055"
      }
     },
     "provider_model_id": "z-ai/glm-4.6v"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.303"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9091"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0556"
      }
     },
     "provider_model_id": "novita/glm-4.6v"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6V"
    },
    {
     "provider": "tetrate",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "deepinfra/zai-org/GLM-4.6V"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "z-ai/glm-4.6v"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "zai/glm-4.6v"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-4.6v",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "2.079524",
        "cache_read": "1.94",
        "prompt": "2.079286"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zhipuai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     }
    }
   ],
   "intro": "GLM vision model for visual reasoning, documents, and multimodal agents",
   "released_at": "2025-12-08",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "deepinfra/zai-org/GLM-4.6V",
    "novita/glm-4.6v",
    "z-ai/glm-4.6v",
    "zai-org/GLM-4.6V",
    "zai-org/glm-4.6v",
    "zai/glm-4.6v"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.6V 系列是 GLM 家族在多模态方向上的重要迭代，包括 GLM-4.6V（旗舰版）、GLM-4.6V-FlashX（轻量化高效版）和 GLM-4.6V-Flash（完全免费版）。该系列将训练时间上下文窗口扩展至 128k tokens，在相似参数规模下实现了最先进的视觉理解准确性，并首次将功能调用（工具调用）能力原生集成到视觉模型架构中。这一设计统一了从“视觉感知”到“可执行动作”的流程，为多模态智能体在真实生产场景中的应用提供了稳定的技术基础。",
    "zh-TW": "GLM-4.6V 系列是 GLM 家族在多模態方向上的重要迭代，包括 GLM-4.6V（旗艦版）、GLM-4.6V-FlashX（輕量化且高速版）以及 GLM-4.6V-Flash（完全免費版）。該系列將訓練時間上下文窗口擴展至 128k tokens，在相似參數規模下實現了最先進的視覺理解準確度，並首次將功能調用（工具調用）能力原生整合到視覺模型架構中。這統一了從「視覺感知」到「可執行動作」的流程，為多模態代理在實際生產場景中提供了一致的技術基礎。",
    "ja-JP": "GLM-4.6Vシリーズは、マルチモーダル方向におけるGLMファミリーの主要な進化を表しており、GLM-4.6V（フラッグシップ）、GLM-4.6V-FlashX（軽量かつ高速）、GLM-4.6V-Flash（完全無料）で構成されています。トレーニング時のコンテキストウィンドウを128kトークンに拡張し、同等のパラメータスケールで最先端の視覚理解精度を達成します。また、初めてFunction Call（ツール呼び出し）機能を視覚モデルアーキテクチャにネイティブ統合しました。これにより、「視覚認識」から「実行可能なアクション」までのパイプラインが統一され、実世界の生産シナリオにおけるマルチモーダルエージェントの一貫した技術基盤を提供します。",
    "ru-RU": "Серия GLM-4.6V представляет собой значительную итерацию семейства GLM в мультимодальном направлении, включая GLM-4.6V (флагман), GLM-4.6V-FlashX (легковесная и высокоскоростная версия) и GLM-4.6V-Flash (полностью бесплатная версия). Она расширяет окно контекста времени обучения до 128k токенов, достигает передовой точности визуального восприятия при сопоставимых масштабах параметров и впервые нативно интегрирует возможности Function Call (вызов инструментов) в архитектуру визуальной модели. Это объединяет процесс от «визуального восприятия» до «исполняемых действий», предоставляя единый технический фундамент для мультимодальных агентов в реальных производственных сценариях."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.6v-flash-free",
   "model_name": "glm-4.6v-flash-free",
   "display_name": "GLM-4.6V-Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "glm-4.6v-flash"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "zai-org/GLM-4.6V-Flash"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.02"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.21"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0043"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-4.6v-flash",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "2.079524",
        "cache_read": "1.023256",
        "prompt": "2.185"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "released_at": "2025-12-08",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true,
    "stream": true
   },
   "intro": "GLM vision model for visual reasoning, documents, and multimodal agents",
   "knowledge_cutoff": "2024-10",
   "modalities": {
    "input": [
     "text",
     "image",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "glm-4.6v-flash",
    "z-ai/glm-4.6v-flash",
    "z-ai/glm-4.6v-flash-free",
    "zai-org/GLM-4.6V-Flash",
    "zai/glm-4.6v-flash"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.6V 系列是 GLM 家族在多模态方向上的重要迭代，包括 GLM-4.6V（旗舰版）、GLM-4.6V-FlashX（轻量化高效版）和 GLM-4.6V-Flash（完全免费版）。该系列将训练时间上下文窗口扩展至 128k tokens，在相似参数规模下实现了最先进的视觉理解准确性，并首次将功能调用（工具调用）能力原生集成到视觉模型架构中。这一设计统一了从“视觉感知”到“可执行动作”的流程，为多模态智能体在真实生产场景中的应用提供了稳定的技术基础。",
    "zh-TW": "GLM-4.6V 系列是 GLM 家族在多模態方向上的重要迭代，包括 GLM-4.6V（旗艦版）、GLM-4.6V-FlashX（輕量化且高速版）以及 GLM-4.6V-Flash（完全免費版）。該系列將訓練時間上下文窗口擴展至 128k tokens，在相似參數規模下實現了最先進的視覺理解準確度，並首次將功能調用（工具調用）能力原生整合到視覺模型架構中。這統一了從「視覺感知」到「可執行動作」的流程，為多模態代理在實際生產場景中提供了一致的技術基礎。",
    "ja-JP": "GLM-4.6Vシリーズは、マルチモーダル方向におけるGLMファミリーの主要な進化を表しており、GLM-4.6V（フラッグシップ）、GLM-4.6V-FlashX（軽量かつ高速）、GLM-4.6V-Flash（完全無料）で構成されています。トレーニング時のコンテキストウィンドウを128kトークンに拡張し、同等のパラメータスケールで最先端の視覚理解精度を達成します。また、初めてFunction Call（ツール呼び出し）機能を視覚モデルアーキテクチャにネイティブ統合しました。これにより、「視覚認識」から「実行可能なアクション」までのパイプラインが統一され、実世界の生産シナリオにおけるマルチモーダルエージェントの一貫した技術基盤を提供します。",
    "ru-RU": "Серия GLM-4.6V представляет собой значительную итерацию семейства GLM в мультимодальном направлении, включая GLM-4.6V (флагман), GLM-4.6V-FlashX (легковесная и высокоскоростная версия) и GLM-4.6V-Flash (полностью бесплатная версия). Она расширяет окно контекста времени обучения до 128k токенов, достигает передовой точности визуального восприятия при сопоставимых масштабах параметров и впервые нативно интегрирует возможности Function Call (вызов инструментов) в архитектуру визуальной модели. Это объединяет процесс от «визуального восприятия» до «исполняемых действий», предоставляя единый технический фундамент для мультимодальных агентов в реальных производственных сценариях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.6V-Flash"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.6v-flash-original",
   "model_name": "glm-4.6v-flash-original",
   "display_name": "GLM 4.6V Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "zai-org/glm-4.6v-flash-original"
    }
   ],
   "intro": "GLM vision model for visual reasoning, documents, and multimodal agents",
   "released_at": "2025-12-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 24000,
   "modalities": {
    "input": [
     "text",
     "image",
     "video"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "video_input": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-4.6v-flash-original"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.6V Flash"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.6v-flashx",
   "model_name": "glm-4.6v-flashx",
   "display_name": "GLM-4.6V-FlashX",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.004412"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.004412"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.022059"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.044118"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.004"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "zai/glm-4.6v-flashx"
    }
   ],
   "released_at": "2025-12-08",
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "vision": true,
    "video_input": true,
    "pdf_input": true,
    "prompt_caching": true
   },
   "intro": "GLM vision model for visual reasoning, documents, and multimodal agents",
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai/glm-4.6v-flashx"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.6V 系列是 GLM 家族在多模态方向上的重要迭代，包括 GLM-4.6V（旗舰版）、GLM-4.6V-FlashX（轻量化高效版）和 GLM-4.6V-Flash（完全免费版）。该系列将训练时间上下文窗口扩展至 128k tokens，在相似参数规模下实现了最先进的视觉理解准确性，并首次将功能调用（工具调用）能力原生集成到视觉模型架构中。这一设计统一了从“视觉感知”到“可执行动作”的流程，为多模态智能体在真实生产场景中的应用提供了稳定的技术基础。",
    "zh-TW": "GLM-4.6V 系列是 GLM 家族在多模態方向上的重要迭代，包括 GLM-4.6V（旗艦版）、GLM-4.6V-FlashX（輕量化且高速版）以及 GLM-4.6V-Flash（完全免費版）。該系列將訓練時間上下文窗口擴展至 128k tokens，在相似參數規模下實現了最先進的視覺理解準確度，並首次將功能調用（工具調用）能力原生整合到視覺模型架構中。這統一了從「視覺感知」到「可執行動作」的流程，為多模態代理在實際生產場景中提供了一致的技術基礎。",
    "ja-JP": "GLM-4.6Vシリーズは、マルチモーダル方向におけるGLMファミリーの主要な進化を表しており、GLM-4.6V（フラッグシップ）、GLM-4.6V-FlashX（軽量かつ高速）、GLM-4.6V-Flash（完全無料）で構成されています。トレーニング時のコンテキストウィンドウを128kトークンに拡張し、同等のパラメータスケールで最先端の視覚理解精度を達成します。また、初めてFunction Call（ツール呼び出し）機能を視覚モデルアーキテクチャにネイティブ統合しました。これにより、「視覚認識」から「実行可能なアクション」までのパイプラインが統一され、実世界の生産シナリオにおけるマルチモーダルエージェントの一貫した技術基盤を提供します。",
    "ru-RU": "Серия GLM-4.6V представляет собой значительную итерацию семейства GLM в мультимодальном направлении, включая GLM-4.6V (флагман), GLM-4.6V-FlashX (легковесная и высокоскоростная версия) и GLM-4.6V-Flash (полностью бесплатная версия). Она расширяет окно контекста времени обучения до 128k токенов, достигает передовой точности визуального восприятия при сопоставимых масштабах параметров и впервые нативно интегрирует возможности Function Call (вызов инструментов) в архитектуру визуальной модели. Это объединяет процесс от «визуального восприятия» до «исполняемых действий», предоставляя единый технический фундамент для мультимодальных агентов в реальных производственных сценариях."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.6V-FlashX"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.6v-original",
   "model_name": "glm-4.6v-original",
   "display_name": "GLM 4.6V Original",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.9"
      }
     },
     "provider_model_id": "zai-org/glm-4.6v-original"
    }
   ],
   "intro": "GLM vision model for visual reasoning, documents, and multimodal agents",
   "released_at": "2025-12-08",
   "max_input_tokens": 128000,
   "max_output_tokens": 24000,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-4.6v-original"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.6V Original"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.7",
   "model_name": "glm-4.7",
   "display_name": "GLM-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "cache_read_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "cache_read_0_032_0_2": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "prompt_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt_0_032_0_2": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "2.058824"
      },
      "completion_0_032_0_2": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.142"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/glm-4.7"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.27"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.548"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.058824"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "glm-4-7"
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.77"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7"
    },
    {
     "provider": "bytedance",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "prompt_0_032_0_2_0_infinity": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "2.058824"
      },
      "completion_0_032_0_2_0_infinity": {
       "unit": "per_M_tokens",
       "price": "2.352941"
      },
      "cache_read_0_0_032_0_0_0002": {
       "unit": "per_M_tokens",
       "price": "0.058824"
      },
      "cache_read_0_0_032_0_0002_infinity": {
       "unit": "per_M_tokens",
       "price": "0.088235"
      },
      "cache_read_0_032_0_2_0_infinity": {
       "unit": "per_M_tokens",
       "price": "0.117647"
      },
      "cache_write_1h": {
       "unit": "per_M_tokens",
       "price": "0.0025"
      }
     },
     "provider_model_id": "glm-4-7"
    },
    {
     "provider": "canopywave",
     "official": false,
     "source": "helicone-registry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      }
     },
     "provider_model_id": "zai/glm-4.7"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.23"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.133"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7"
    },
    {
     "provider": "dinference",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.65"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "z-ai/glm-4.7"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/glm-4.7"
    },
    {
     "provider": "helicone",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      }
     }
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7"
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.441176"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.058824"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.864"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.432"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.864"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.24"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.432"
      }
     },
     "provider_model_id": "glm-4-7"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/glm-4.7"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.98"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "z-ai/glm-4.7"
    },
    {
     "provider": "kuae-cloud-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "GLM-4.7"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.98"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.19"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai/glm-4.7"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai/glm-4.7"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     },
     "provider_model_id": "GLM-4.7"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     },
     "provider_model_id": "TEE/glm-4.7"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "litellm+helicone-registry+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai-org/glm-4.7"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai-org/glm-4.7"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "glm-4.7-free"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-4.7"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-4.7"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "lobehub-modelbank+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.465882"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.842353"
      }
     },
     "provider_model_id": "z-ai/glm-4.7"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai/GLM-4.7"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "Pro/zai-org/GLM-4.7"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      }
     },
     "provider_model_id": "hf:zai-org/GLM-4.7"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "litellm+truefoundry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     },
     "provider_model_id": "GLM-4.7"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11000000000000001"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "z-ai/glm-4.7"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "zai/glm-4.7"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.28"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.14"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-4.7",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "2.04307",
        "cache_read": "1.941667",
        "prompt": "2.079643"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zhipuai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Mature GLM model for dependable coding, reasoning, and structured agent tasks",
   "released_at": "2025-12-22",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "web_search": true,
    "assistant_prefill": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "deprecated": true,
   "status": "deprecated",
   "docs_url": "https://www.together.ai/models/glm-4-7",
   "benchmarks": {
    "intelligence_index": 33.7,
    "coding_index": 45.3,
    "agentic_index": 25.4
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "GLM-4.7",
    "Pro/zai-org/GLM-4.7",
    "TEE/glm-4.7",
    "glm-4-7",
    "glm-4.7-free",
    "hf:zai-org/GLM-4.7",
    "novita/glm-4.7",
    "z-ai/glm-4.7",
    "zai-org/GLM-4.7",
    "zai-org/glm-4.7",
    "zai-org/glm-4.7:thinking",
    "zai/GLM-4.7",
    "zai/glm-4.7"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.7是智谱最新旗舰模型，针对代理编程场景进行了增强，具备更强的编程能力、长期任务规划能力以及工具协作能力。",
    "zh-TW": "GLM-4.7 是智譜最新的旗艦模型，針對代理編程場景進行增強，具備改進的編程能力、長期任務規劃和工具協作能力。",
    "ja-JP": "GLM-4.7は智譜の最新フラッグシップモデルで、エージェンティックコーディングシナリオ向けに強化され、コーディング能力、長期タスク計画、ツール連携が向上しています。",
    "ru-RU": "GLM-4.7: Последняя флагманская модель Zhipu, улучшенная для сценариев агентного программирования с расширенными возможностями кодирования, долгосрочного планирования задач и взаимодействия с инструментами."
   },
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.428",
     "new": "0.432"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.222",
     "new": "2.24"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.856",
     "new": "0.864"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.428",
     "new": "0.432"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.222",
     "new": "2.24"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.856",
     "new": "0.864"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.432",
     "new": "0.428"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.24",
     "new": "2.222"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.864",
     "new": "0.856"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.432",
     "new": "0.428"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.24",
     "new": "2.222"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.864",
     "new": "0.856"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.428",
     "new": "0.432"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.222",
     "new": "2.24"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.856",
     "new": "0.864"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.428",
     "new": "0.432"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.222",
     "new": "2.24"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.856",
     "new": "0.864"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.432",
     "new": "0.428"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.24",
     "new": "2.222"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.7-flash",
   "model_name": "glm-4.7-flash",
   "display_name": "GLM-4.7-Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.35"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7-Flash"
    },
    {
     "provider": "cloudflare-ai-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "workers-ai/@cf/zai-org/glm-4.7-flash"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0605"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "@cf/zai-org/glm-4.7-flash"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.09"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.53"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.008"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7-Flash"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7-Flash"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.078875"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.425"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.039438"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7-Flash"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "zai-org/glm-4.7-flash"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "z-ai/glm-4.7-flash"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.15"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "TEE/glm-4.7-flash"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "zai-org/glm-4.7-flash"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "zai-org/glm-4.7-flash"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-4.7-flash"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0707"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.404"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.0101"
      }
     },
     "provider_model_id": "novita/glm-4.7-flash"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "hf:zai-org/GLM-4.7-Flash"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "zai/glm-4.7-flash"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-4.7-flash-free"
    }
   ],
   "intro": "Budget GLM lane for fast coding help, routing, and everyday automation",
   "released_at": "2026-01-19",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 200000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm-flash",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/zai-org/glm-4.7-flash",
    "TEE/glm-4.7-flash",
    "hf:zai-org/GLM-4.7-Flash",
    "novita/glm-4.7-flash",
    "workers-ai/@cf/zai-org/glm-4.7-flash",
    "z-ai/glm-4.7-flash",
    "z-ai/glm-4.7-flash-free",
    "zai-org/GLM-4.7-Flash",
    "zai-org/glm-4.7-flash",
    "zai-org/glm-4.7-flash:thinking",
    "zai/glm-4.7-flash"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.7-Flash 是一款 30B 级别的 SOTA 模型，在性能与效率之间实现平衡。它提升了编程能力、长期任务规划和工具协作能力，适用于 Agentic Coding 场景，在多个当前基准排行榜中，在同体量开源模型中表现领先。在执行复杂智能体任务时，工具调用的指令遵循性更强，进一步提升了 Artifacts 和 Agentic Coding 的前端美学和长期任务完成效率。",
    "zh-TW": "GLM-4.7-Flash 作為 30B 級別的 SOTA 模型，提供在效能與效率間取得平衡的新選擇。它強化了程式能力、長期任務規劃與工具協作，適用於 Agentic Coding 場景，在多項當前基準排行榜中於同級開源模型中表現領先。在執行複雜智慧代理任務時，其工具調用的指令遵循能力更強，並進一步提升 Artifacts 與 Agentic Coding 前端的美學與長期任務完成效率。",
    "ja-JP": "GLM-4.7-Flashは、30BクラスのSOTAモデルとして、性能と効率のバランスを実現する新たな選択肢です。Agentic Codingシナリオにおけるコーディング能力、長期タスク計画、ツール連携を強化し、同規模のオープンソースモデルの中でベンチマーク上位の性能を発揮します。複雑なインテリジェントエージェントタスクの実行時には、ツール呼び出し時の指示遵守が強化され、フロントエンドの美的品質や長期タスク完了効率も向上しています。",
    "ru-RU": "GLM-4.7-Flash — модель уровня 30B SOTA, предлагающая баланс между производительностью и эффективностью. Улучшает программирование, долгосрочное планирование задач и взаимодействие с инструментами в сценариях Agentic Coding, достигая лидирующих результатов среди моделей аналогичного размера с открытым исходным кодом. При выполнении сложных задач интеллектуальных агентов демонстрирует лучшее следование инструкциям при вызове инструментов, а также улучшает эстетику интерфейса и эффективность выполнения долгосрочных задач в Artifacts и Agentic Coding."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "price",
     "provider": "deepinfra",
     "charge": "cache_read",
     "old": "0.0100000002",
     "new": "0.01"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.7-flash-original:thinking",
   "model_name": "glm-4.7-flash-original:thinking",
   "display_name": "GLM 4.7 Flash Original",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "zai-org/glm-4.7-flash-original"
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2026-01-19",
   "max_input_tokens": 200000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-4.7-flash-original",
    "zai-org/glm-4.7-flash-original:thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.7 Flash Original"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.7-flashx",
   "model_name": "glm-4.7-flashx",
   "display_name": "GLM-4.7-FlashX",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.429"
      }
     }
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      }
     },
     "provider_model_id": "zai/glm-4.7-flashx"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai/glm-4.7-flashx"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      }
     },
     "provider_model_id": "zai/glm-4.7-flashx"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.42"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.01"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-4.7-flashx"
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2026-01-19",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 200000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm-flash",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "web_search": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "z-ai/glm-4.7-flashx",
    "zai/glm-4.7-flashx"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-4.7-Flash 是一款 30B 级别的 SOTA 模型，在性能与效率之间实现平衡。它提升了编程能力、长期任务规划和工具协作能力，适用于 Agentic Coding 场景，在多个当前基准排行榜中，在同体量开源模型中表现领先。在执行复杂智能体任务时，工具调用的指令遵循性更强，进一步提升了 Artifacts 和 Agentic Coding 的前端美学和长期任务完成效率。",
    "zh-TW": "GLM-4.7-Flash 作為 30B 級別的 SOTA 模型，提供在效能與效率間取得平衡的新選擇。它強化了程式能力、長期任務規劃與工具協作，適用於 Agentic Coding 場景，在多項當前基準排行榜中於同級開源模型中表現領先。在執行複雜智慧代理任務時，其工具調用的指令遵循能力更強，並進一步提升 Artifacts 與 Agentic Coding 前端的美學與長期任務完成效率。",
    "ja-JP": "GLM-4.7-Flashは、30BクラスのSOTAモデルとして、性能と効率のバランスを実現する新たな選択肢です。Agentic Codingシナリオにおけるコーディング能力、長期タスク計画、ツール連携を強化し、同規模のオープンソースモデルの中でベンチマーク上位の性能を発揮します。複雑なインテリジェントエージェントタスクの実行時には、ツール呼び出し時の指示遵守が強化され、フロントエンドの美的品質や長期タスク完了効率も向上しています。",
    "ru-RU": "GLM-4.7-Flash — модель уровня 30B SOTA, предлагающая баланс между производительностью и эффективностью. Улучшает программирование, долгосрочное планирование задач и взаимодействие с инструментами в сценариях Agentic Coding, достигая лидирующих результатов среди моделей аналогичного размера с открытым исходным кодом. При выполнении сложных задач интеллектуальных агентов демонстрирует лучшее следование инструкциям при вызове инструментов, а также улучшает эстетику интерфейса и эффективность выполнения долгосрочных задач в Artifacts и Agentic Coding."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    },
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "stream: false→true"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4.7-fp4",
   "model_name": "GLM-4.7-fp4",
   "display_name": "GLM-4.7-fp4",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7-fp4"
    }
   ],
   "max_input_tokens": 202752,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-4.7-fp4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.7-fp4"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4.7-FP8",
   "model_name": "GLM-4.7-FP8",
   "display_name": "GLM 4.7 FP8",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.79914765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.85409875"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7-FP8"
    },
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7-FP8"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7-FP8"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7-FP8"
    }
   ],
   "max_input_tokens": 202752,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "stream": true,
    "structured_output": true,
    "open_weights": true
   },
   "released_at": "2026-01-27",
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "knowledge_cutoff": "2025-12",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-4.7-FP8"
   ],
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592687",
     "new": "2.85409875"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800595236",
     "new": "0.79914765"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.858164925",
     "new": "2.8592687"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800286179",
     "new": "0.800595236"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.860353575",
     "new": "2.858164925"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800899001",
     "new": "0.800286179"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592021",
     "new": "2.860353575"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800576588",
     "new": "0.800899001"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.859994675",
     "new": "2.8592021"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800798509",
     "new": "0.800576588"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8452425",
     "new": "2.859994675"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.7966679",
     "new": "0.800798509"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.7 FP8"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.7-h",
   "model_name": "glm-4.7-h",
   "display_name": "GLM-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/glm-4.7-h"
    }
   ],
   "released_at": "2026-01-26",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-4.7-h"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.7-maas",
   "model_name": "glm-4.7-maas",
   "display_name": "GLM-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/glm-4.7-maas"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      }
     },
     "provider_model_id": "zai-org/glm-4.7-maas",
     "region": "global"
    }
   ],
   "intro": "GLM vision model for visual reasoning, documents, and multimodal agents",
   "released_at": "2026-01-06",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 200000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-4.7-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.7-n",
   "model_name": "glm-4.7-n",
   "display_name": "glm-4.7-n",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6061"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2222"
      }
     },
     "provider_model_id": "novita/glm-4.7-n"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-12-22",
   "max_input_tokens": 205000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "novita/glm-4.7-n"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.7-n"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4.7-original:thinking",
   "model_name": "glm-4.7-original:thinking",
   "display_name": "GLM 4.7 Original",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "zai-org/glm-4.7-original"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-12-22",
   "max_input_tokens": 200000,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-4.7-original",
    "zai-org/glm-4.7-original:thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.7 Original"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-4.7-TEE",
   "model_name": "GLM-4.7-TEE",
   "display_name": "GLM 4.7 TEE",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     },
     "provider_model_id": "zai-org/GLM-4.7-TEE"
    }
   ],
   "released_at": "2025-12-29",
   "max_input_tokens": 202752,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-4.7-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.7 TEE"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4p5",
   "model_name": "glm-4p5",
   "display_name": "GLM 4.5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "accounts/fireworks/models/glm-4p5"
    }
   ],
   "docs_url": "https://fireworks.ai/models/fireworks/glm-4p5",
   "max_input_tokens": 128000,
   "max_output_tokens": 96000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true
   },
   "released_at": "2025-07-29",
   "knowledge_cutoff": "2025-04",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/glm-4p5"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.5"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4p5-air",
   "model_name": "glm-4p5-air",
   "display_name": "GLM 4.5 Air",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.22"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     },
     "provider_model_id": "accounts/fireworks/models/glm-4p5-air"
    }
   ],
   "docs_url": "https://artificialanalysis.ai/models/glm-4-5-air",
   "max_input_tokens": 128000,
   "max_output_tokens": 96000,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true
   },
   "released_at": "2025-08-01",
   "knowledge_cutoff": "2025-04",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm-air",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/glm-4p5-air"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.5 Air"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4p5v",
   "model_name": "glm-4p5v",
   "display_name": "GLM-4.5V",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.6"
      }
     },
     "provider_model_id": "accounts/fireworks/models/glm-4p5v"
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 131072,
   "model_type": "deep_thinking",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "pdf_input": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/glm-4p5v"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.5V"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4p6",
   "model_name": "glm-4p6",
   "display_name": "GLM-4.6",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.19"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      }
     },
     "provider_model_id": "accounts/fireworks/models/glm-4p6"
    }
   ],
   "docs_url": "https://fireworks.ai/pricing",
   "max_input_tokens": 202800,
   "max_output_tokens": 202800,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/glm-4p6"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4.6"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4p7",
   "model_name": "glm-4p7",
   "display_name": "Zai GLM-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "litellm+pydantic-prices+helicone-registry+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "accounts/fireworks/models/glm-4p7"
    }
   ],
   "docs_url": "https://fireworks.ai/models/fireworks/glm-4p7",
   "max_input_tokens": 202800,
   "max_output_tokens": 202800,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "stream": true,
    "open_weights": true
   },
   "intro": "Next-generation general-purpose model from Z.ai optimized for coding, reasoning, and agentic workflows. 352B parameter MoE model with advanced thinking controls.",
   "knowledge_cutoff": "2024-12",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "functions",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ]
   },
   "released_at": "2025-12-22",
   "family": "glm",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/glm-4p7"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Zai GLM-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4v",
   "model_name": "glm-4v",
   "display_name": "GLM-4V",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.352941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.352941"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14.2"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7.352941"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7.352941"
      }
     }
    }
   ],
   "max_input_tokens": 4096,
   "max_output_tokens": 1024,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4V 在视觉任务中具备强大的图像理解与推理能力。",
    "zh-TW": "GLM-4V 在各類視覺任務中展現強大的圖像理解與推理能力。",
    "ja-JP": "GLM-4V は、視覚タスクにおける画像理解と推論に優れた性能を発揮します。",
    "ru-RU": "GLM-4V обеспечивает высокое качество понимания изображений и логического вывода в визуальных задачах."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4V"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4v-flash",
   "model_name": "glm-4v-flash",
   "display_name": "GLM-4V-Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "released_at": "2024-12-09",
   "max_input_tokens": 4096,
   "max_output_tokens": 1024,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4V-Flash 专注于高效的单图像理解，适用于实时或批量图像处理等快速分析场景。",
    "zh-TW": "GLM-4V-Flash 專注於單張圖像的高效理解，適用於即時或批次圖像處理等快速分析場景。",
    "ja-JP": "GLM-4V-Flash は、リアルタイムやバッチ画像処理などの高速分析シナリオに適した、単一画像理解に特化したモデルです。",
    "ru-RU": "GLM-4V-Flash ориентирована на эффективное понимание одиночных изображений в сценариях быстрого анализа, таких как обработка изображений в реальном времени или пакетная обработка."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4V-Flash"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4v-plus",
   "model_name": "glm-4v-plus",
   "display_name": "GLM-4V-Plus",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "higress",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     }
    }
   ],
   "max_input_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4V-Plus 支持视频与多图像理解，适用于多模态任务。",
    "zh-TW": "GLM-4V-Plus 能理解影片與多張圖像，適合多模態任務。",
    "ja-JP": "GLM-4V-Plus は、動画や複数画像の理解に対応し、マルチモーダルタスクに適しています。",
    "ru-RU": "GLM-4V-Plus понимает видео и несколько изображений, подходит для мультимодальных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4V-Plus"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-4v-plus-0111",
   "model_name": "glm-4v-plus-0111",
   "display_name": "GLM-4V-Plus-0111",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      }
     }
    }
   ],
   "max_input_tokens": 16000,
   "max_output_tokens": 8192,
   "model_type": "vision_understanding",
   "capabilities": {
    "vision": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-4V-Plus 支持视频与多图像理解，适用于多模态任务。",
    "zh-TW": "GLM-4V-Plus 能理解影片與多張圖像，適合多模態任務。",
    "ja-JP": "GLM-4V-Plus は、動画や複数画像の理解に対応し、マルチモーダルタスクに適しています。",
    "ru-RU": "GLM-4V-Plus понимает видео и несколько изображений, подходит для мультимодальных задач."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-4V-Plus-0111"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5",
   "model_name": "glm-5",
   "display_name": "GLM-5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "zai-org/glm-5"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.82"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "llmdb+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.15"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.15"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-coding-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "amazon-bedrock",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.9"
      }
     }
    },
    {
     "provider": "avian",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.55"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "z-ai/glm-5"
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "zai-org/GLM-5"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.44"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.222"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.48"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.9"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.08"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "zai-org/GLM-5"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     }
    },
    {
     "provider": "dinference",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "z-ai/glm-5"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "accounts/fireworks/models/glm-5"
    },
    {
     "provider": "firmware",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "friendli",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "zai-org/GLM-5"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "zai-org/GLM-5"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.77"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.388"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.385"
      }
     },
     "provider_model_id": "zai-org/GLM-5"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.77"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.388"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.385"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "zai-org/glm-5"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "z-ai/glm-5"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.144"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.88"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "zai/glm-5"
    },
    {
     "provider": "meganova",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.56"
      }
     },
     "provider_model_id": "zai-org/GLM-5"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai/glm-5"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58852528"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.64836376"
      }
     },
     "provider_model_id": "GLM-5"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     },
     "provider_model_id": "TEE/glm-5"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "zai-org/GLM-5"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "zai-org/glm-5"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "zai-org/glm-5"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "glm-5-free"
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.92"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "z-ai/glm-5"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-5"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "novita/glm-5"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57971"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6087"
      }
     },
     "provider_model_id": "z-ai/glm-5"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "novita/GLM-5"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.0547"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "6.2783"
      }
     }
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.55"
      }
     },
     "provider_model_id": "zai-org/GLM-5"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "Pro/zai-org/GLM-5"
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.147059"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.220588"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.588235"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "2.647059"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      }
     },
     "provider_model_id": "GLM-5"
    },
    {
     "provider": "tencent-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+computeprices+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "zai-org/GLM-5"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1"
      }
     },
     "provider_model_id": "z-ai/glm-5"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "zai/glm-5"
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.58"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-5",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.223077",
        "cache_read": "1.571429",
        "prompt": "1.5"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    }
   ],
   "intro": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
   "released_at": "2026-02-11",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "stream": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2026-01",
   "deprecated": true,
   "status": "deprecated",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "docs_url": "https://openrouter.ai/z-ai/glm-5",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "GLM-5",
    "Pro/zai-org/GLM-5",
    "TEE/glm-5",
    "accounts/fireworks/models/glm-5",
    "glm-5-free",
    "novita/GLM-5",
    "novita/glm-5",
    "z-ai/glm-5",
    "zai-org/GLM-5",
    "zai-org/glm-5",
    "zai-org/glm-5:thinking",
    "zai/GLM-5",
    "zai/glm-5"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-5 是智谱面向 Agentic Engineering 打造的下一代旗舰基础模型，可在复杂系统工程与长周期智能体任务中提供可靠生产力。在编码与智能体能力方面，GLM-5 在开源模型中表现领先。在真实编程场景中的使用体验已接近 Claude Opus 4.5。它擅长复杂系统工程与长期智能体任务，是构建通用型智能体助手的理想基础模型。",
    "zh-TW": "GLM-5 是智譜推出的下一代旗艦級基礎模型，專為 Agentic Engineering 打造，能在複雜系統工程與長時序智能體任務中提供可靠效能。在程式能力與智能體表現上位居開源模型最前列，於真實編程情境中的體驗接近 Claude Opus 4.5。其擅長複雜系統工程與長鏈任務，是通用型智能體助手的理想基礎模型。",
    "ja-JP": "GLM-5 は Zhipu の次世代フラッグシップ基盤モデルで、エージェント工学向けに設計されています。複雑なシステムエンジニアリングや長期的なエージェントタスクにおいて高い生産性を発揮します。コーディングやエージェント能力ではオープンソースモデルの中で最先端の性能を示し、実際のプログラミング環境では Claude Opus 4.5 に匹敵するユーザー体験を提供します。汎用エージェントアシスタントの基盤モデルとして理想的です。",
    "ru-RU": "GLM-5 — флагманская модель нового поколения от Zhipu, созданная специально для Agentic Engineering. Обеспечивает надёжную продуктивность в задачах сложной системной инженерии и долгосрочных агентных сценариях. В программировании и агентных возможностях GLM-5 достигает уровня SOTA среди открытых моделей. В реальных условиях кодирования пользовательский опыт приближается к Claude Opus 4.5. Отличается высокой эффективностью в сложной инженерии и длительных агентных задачах, что делает её идеальной базовой моделью для универсальных агент-ассистентов."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.425",
     "new": "0.385"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.72",
     "new": "2.388"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.85",
     "new": "0.77"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.425",
     "new": "0.385"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.72",
     "new": "2.388"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.85",
     "new": "0.77"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.64963024",
     "new": "2.64836376"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58880672",
     "new": "0.58852528"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.43",
     "new": "0.425"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.654",
     "new": "2.72"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.86",
     "new": "0.85"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.43",
     "new": "0.425"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "2.654",
     "new": "2.72"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "0.86",
     "new": "0.85"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "2.65147092",
     "new": "2.64963024"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "0.58921576",
     "new": "0.58880672"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.455",
     "new": "0.43"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "2.844",
     "new": "2.654"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "0.91",
     "new": "0.86"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.455",
     "new": "0.43"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-5-FP4",
   "model_name": "GLM-5-FP4",
   "display_name": "GLM-5-FP4",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "togetherai",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "zai-org/GLM-5-FP4"
    }
   ],
   "max_input_tokens": 202752,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-5-FP4"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-5-FP4"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-5-FP8",
   "model_name": "GLM-5-FP8",
   "display_name": "GLM-5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.92"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.12"
      }
     },
     "provider_model_id": "zai-org/GLM-5-FP8"
    }
   ],
   "intro": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
   "released_at": "2026-02-12",
   "max_input_tokens": 202752,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-5-FP8"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-08",
     "kind": "capability",
     "note": "structured_output: true→false"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-5"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5-maas",
   "model_name": "glm-5-maas",
   "display_name": "GLM-5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "google-vertex",
     "official": false,
     "source": "models-dev+portkey+llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "zai-org/glm-5-maas"
    },
    {
     "provider": "google-vertex",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "zai-org/glm-5-maas",
     "region": "global"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-02-11",
   "max_input_tokens": 202752,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "parallel_function_calling": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-5-maas"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-5"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5-original",
   "model_name": "glm-5-original",
   "display_name": "GLM 5 Original",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "zai-org/glm-5-original"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-02-11",
   "max_input_tokens": 200000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "knowledge_cutoff": "2025-06",
   "model_type": "deep_thinking",
   "family": "glm",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-5-original",
    "zai-org/glm-5-original:thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5 Original"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-5-TEE",
   "model_name": "GLM-5-TEE",
   "display_name": "GLM 5 TEE",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.95"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.55"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.475"
      }
     },
     "provider_model_id": "zai-org/GLM-5-TEE"
    }
   ],
   "intro": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
   "released_at": "2026-02-12",
   "max_input_tokens": 202752,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-5-TEE"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5 TEE"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-5-Turbo",
   "model_name": "GLM-5-Turbo",
   "display_name": "GLM-5-Turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "3.823529"
      }
     },
     "provider_model_id": "glm-5-turbo"
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "glm-5-turbo"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9996"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "glm-5-turbo"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.118"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.308"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.544"
      }
     },
     "provider_model_id": "glm-5-turbo"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "3.823529"
      }
     },
     "provider_model_id": "glm-5-turbo"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "zai-org/glm-5-turbo"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "z-ai/glm-5-turbo"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.216"
      }
     },
     "provider_model_id": "zai/glm-5-turbo"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai/glm-5-turbo"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "z-ai/glm-5-turbo"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "zai-org/glm-5-turbo"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "z-ai/glm-5-turbo"
    },
    {
     "provider": "streamlake",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "3.823529"
      }
     }
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.2"
      }
     },
     "provider_model_id": "z-ai/glm-5-turbo"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "zai/glm-5-turbo"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "glm-5-turbo"
    },
    {
     "provider": "zai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "glm-5-turbo"
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.88"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.174"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-5-turbo",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.083333",
        "cache_read": "1.5",
        "prompt": "1.159091"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zhipuai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "glm-5-turbo"
    }
   ],
   "released_at": "2026-03-15",
   "max_input_tokens": 200000,
   "max_output_tokens": 131072,
   "model_type": "deep_thinking",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true,
    "pdf_input": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "intro": "Faster GLM-5 lane for coding agents that need lower latency",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "knowledge_cutoff": "2025-01",
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "reasoning_config": {
    "mandatory": false
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "glm-5-turbo",
    "z-ai/glm-5-turbo",
    "zai-org/glm-5-turbo",
    "zai/glm-5-turbo"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-5-Turbo 是一款为智能体场景深度优化的基础模型，从训练阶段即面向智能体任务的核心需求进行优化，加强了工具调用、指令遵循与长链执行等关键能力，非常适合构建高性能智能助手。",
    "zh-TW": "GLM-5-Turbo 是針對智能體情境深度優化的基礎模型，自訓練階段便面向智能體任務需求調校，加強工具調用、指令跟隨與長鏈執行等能力，是打造高效能智能體助手的理想選擇。",
    "ja-JP": "GLM-5-Turbo はエージェントシナリオに最適化された基盤モデルです。学習段階からツール呼び出し、コマンド実行、長いタスクチェーン処理など、エージェントに必要な能力を強化しており、高性能なエージェントアシスタントの構築に最適です。",
    "ru-RU": "GLM-5-Turbo — базовая модель, глубоко оптимизированная для агентных сценариев. Специально улучшена под ключевые требования агентных задач ещё на этапе обучения, усиливая такие возможности, как вызов инструментов, следование командам и выполнение длинных цепочек действий. Идеально подходит для создания высокопроизводительных агент-ассистентов."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-5-Turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.1",
   "model_name": "glm-5.1",
   "display_name": "GLM-5.1",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.191176"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "4.117647"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      }
     }
    },
    {
     "provider": "abacus",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/glm-5.1"
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.845"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1831115"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "4.117647"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.87"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.48"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.17"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.031"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.4"
      }
     }
    },
    {
     "provider": "auriko",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "avian",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "z-ai/glm-5.1"
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.31"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.15"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.205"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.975"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "dinference",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.89"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.205000005"
      }
     },
     "provider_model_id": "z-ai/glm-5.1"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "glm-5-1"
    },
    {
     "provider": "friendli",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1"
    },
    {
     "provider": "hpc-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.615"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.46"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.133"
      }
     },
     "provider_model_id": "zai-org/glm-5.1"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1"
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.191176"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "4.117647"
      }
     }
    },
    {
     "provider": "infiniai",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.117647"
      }
     }
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.69"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.69"
      }
     },
     "provider_model_id": "glm-5-1"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "zai-org/glm-5.1"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "glm-5-1"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.96"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "z-ai/glm-5.1"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.931"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.93"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.173"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.96"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.234"
      }
     },
     "provider_model_id": "zai/glm-5.1"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai/glm-5.1"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.17705056"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.11967696"
      }
     },
     "provider_model_id": "GLM-5.1"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "TEE/glm-5.1"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "zai-org/glm-5.1"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.38"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/glm-5.1"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "opencodeCodingPlan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "opencodeZen",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.966"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.036"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1794"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-5.1"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-5.1"
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.86957"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.47826"
      }
     },
     "provider_model_id": "z-ai/glm-5.1"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.205"
      }
     },
     "provider_model_id": "deepinfra/zai-org/GLM-5.1"
    },
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "route/glm-5.1"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.191176"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.882353"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.529412"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "4.117647"
      }
     },
     "provider_model_id": "Pro/zai-org/glm-5.1"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "Pro/zai-org/GLM-5.1"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.49999965"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.525"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.05"
      }
     },
     "provider_model_id": "z-ai/glm-5.1"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai/glm-5.1"
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry+computeprices",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     },
     "provider_model_id": "GLM-5.1"
    },
    {
     "provider": "wafer-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      }
     },
     "provider_model_id": "GLM-5.1"
    },
    {
     "provider": "wafer.ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "GLM-5.1"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.8781"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.5126"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1903"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-5.1",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.166657",
        "cache_read": "1.538098",
        "prompt": "1.333447"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zhipuai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
   "released_at": "2026-03-27",
   "max_input_tokens": 200000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true,
    "parallel_function_calling": true
   },
   "model_type": "deep_thinking",
   "knowledge_cutoff": "2025-04",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "docs_url": "https://openrouter.ai/z-ai/glm-5.1",
   "benchmarks": {
    "intelligence_index": 40.2,
    "coding_index": 55.8,
    "agentic_index": 29.9
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "presence_penalty",
     "reasoning",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "GLM-5.1",
    "Pro/zai-org/GLM-5.1",
    "Pro/zai-org/glm-5.1",
    "TEE/glm-5.1",
    "deepinfra/zai-org/GLM-5.1",
    "fireworks/glm-5.1",
    "glm-5-1",
    "nebius/zai-org/glm-5.1",
    "novita/zai-org/glm-5.1",
    "route/glm-5.1",
    "z-ai/glm-5.1",
    "zai-org/GLM-5.1",
    "zai-org/glm-5.1",
    "zai-org/glm-5.1:thinking",
    "zai/glm-5.1"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-5.1 是智谱最新的旗舰模型，是 GLM-5 的增强迭代版本，具备更强的代理工程能力，能够处理复杂系统工程和长周期任务。",
    "zh-TW": "GLM-5.1 是智譜最新的旗艦模型，是 GLM-5 的增強版，具備更強的代理工程能力，能應對複雜系統工程和長期任務。",
    "ja-JP": "GLM-5.1はZhipuの最新フラッグシップモデルであり、GLM-5の強化版です。複雑なシステムエンジニアリングや長期的なタスクにおけるエージェント工学能力が向上しています。",
    "ru-RU": "GLM-5.1 — это новейшая флагманская модель Zhipu, улучшенная версия GLM-5 с расширенными возможностями агентной инженерии для сложных системных разработок и задач с длинным горизонтом."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "4.12164704",
     "new": "4.11967696"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17761344",
     "new": "1.17705056"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.655",
     "new": "0.69"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "4.2",
     "new": "4.38"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "1.31",
     "new": "1.38"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.655",
     "new": "0.69"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "4.2",
     "new": "4.38"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "1.31",
     "new": "1.38"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "4.12451032",
     "new": "4.12164704"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17843152",
     "new": "1.17761344"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.69",
     "new": "0.655"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "4.38",
     "new": "4.2"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "1.38",
     "new": "1.31"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.69",
     "new": "0.655"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "4.38",
     "new": "4.2"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "1.38",
     "new": "1.31"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "4.12885816",
     "new": "4.12451032"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17967376",
     "new": "1.17843152"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "4.12970124",
     "new": "4.12885816"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17991464",
     "new": "1.17967376"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.1-6bit",
   "model_name": "glm-5.1-6bit",
   "display_name": "GLM 5.1 6bit",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "routing-run",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "route/glm-5.1-6bit"
    }
   ],
   "intro": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
   "released_at": "2026-04-07",
   "max_input_tokens": 202752,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "route/glm-5.1-6bit"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.1 6bit"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-5.1-FP8",
   "model_name": "GLM-5.1-FP8",
   "display_name": "GLM-5.1 FP8",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "ambient",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1-FP8"
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.98"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.08"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.182"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1-FP8"
    },
    {
     "provider": "inceptron",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1-FP8"
    },
    {
     "provider": "nearai",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.17"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1-FP8"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-03-27",
   "max_input_tokens": 202752,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-5.1-FP8"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "limit",
     "old": "200000",
     "new": "202752",
     "note": "max_input_tokens"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-5.1"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-5.1-TEE",
   "model_name": "GLM-5.1-TEE",
   "display_name": "GLM 5.1 TEE",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.98"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.08"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.49"
      }
     },
     "provider_model_id": "zai-org/GLM-5.1-TEE"
    }
   ],
   "intro": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
   "released_at": "2026-04-07",
   "max_input_tokens": 202752,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-5.1-TEE"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.1 TEE"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.1-thinking",
   "model_name": "glm-5.1-thinking",
   "display_name": "GLM 5.1 Thinking TEE",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "TEE/glm-5.1-thinking"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-04-20",
   "max_input_tokens": 202752,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "TEE/glm-5.1-thinking"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.1 Thinking TEE"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.2",
   "model_name": "glm-5.2",
   "display_name": "GLM-5.2",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1268"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9438"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2817"
      }
     }
    },
    {
     "provider": "alibaba",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.117647"
      }
     }
    },
    {
     "provider": "alibaba-cn",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.851"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.275"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "alibaba-token-plan-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "api-airforce",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     }
    },
    {
     "provider": "baseten",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "berget",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "cloudflare-workers-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "@cf/zai-org/glm-5.2"
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.44"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.53"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.39"
      }
     }
    },
    {
     "provider": "crof",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    },
    {
     "provider": "deepinfra",
     "official": false,
     "source": "models-dev+truefoundry+deepinfra+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.93"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "digitalocean",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.21"
      }
     }
    },
    {
     "provider": "fastrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "z-ai/glm-5.2"
    },
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "glm-5-2"
    },
    {
     "provider": "friendli",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "huggingface",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "inceptron",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "io-net",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.538"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.769"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "ionet",
     "official": false,
     "source": "computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.538"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.769"
      }
     },
     "provider_model_id": "glm-5-2"
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "zai-org/glm-5.2"
    },
    {
     "provider": "kenari",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "glm-5-2"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "z-ai/glm-5.2"
    },
    {
     "provider": "lilac",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.27"
      }
     },
     "provider_model_id": "zai-org/glm-5.2"
    },
    {
     "provider": "llmgateway",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.96"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.234"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.26"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.96"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.234"
      }
     },
     "provider_model_id": "zai/glm-5.2"
    },
    {
     "provider": "merge-gateway",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "zai/glm-5.2"
    },
    {
     "provider": "moark",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.17705056"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.11967696"
      }
     },
     "provider_model_id": "GLM-5.2"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.6"
      }
     },
     "provider_model_id": "TEE/glm-5.2"
    },
    {
     "provider": "nebius",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3625"
      }
     }
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "zai-org/glm-5.2"
    },
    {
     "provider": "novita-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/glm-5.2"
    },
    {
     "provider": "nvidia",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "z-ai/glm-5.2"
    },
    {
     "provider": "opencode",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "opencode-go",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "opencode-zen",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.9"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.08"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18"
      }
     },
     "provider_model_id": "z-ai/glm-5.2"
    },
    {
     "provider": "orcarouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     },
     "provider_model_id": "z-ai/glm-5.2"
    },
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4141"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4444"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2626"
      }
     }
    },
    {
     "provider": "qiniu",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.15942"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.05797"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.28986"
      }
     },
     "provider_model_id": "z-ai/glm-5.2"
    },
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "doubleword/glm-5.2"
    },
    {
     "provider": "scaleway",
     "official": false,
     "source": "models-dev+computeprices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.5"
      }
     },
     "provider_model_id": "glm-5-2"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.294118"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.176471"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.117647"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "siliconflow-cn",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "subconscious",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "subconscious/glm-5.2"
    },
    {
     "provider": "synthetic",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     },
     "provider_model_id": "hf:zai-org/GLM-5.2"
    },
    {
     "provider": "tinfoil",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5.25"
      }
     },
     "provider_model_id": "glm-5-2"
    },
    {
     "provider": "togetherai",
     "official": false,
     "source": "models-dev+truefoundry+computeprices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "tokenrouter",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.1429"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2857"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.1429"
      },
      "audio_input": {
       "unit": "per_M_tokens",
       "price": "1.1429"
      },
      "audio_output": {
       "unit": "per_M_tokens",
       "price": "1.1429"
      }
     },
     "provider_model_id": "z-ai/glm-5.2"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai/glm-5.2"
    },
    {
     "provider": "vivgrid",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry+computeprices",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.1"
      }
     },
     "provider_model_id": "GLM-5.2"
    },
    {
     "provider": "wafer-ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "GLM-5.2"
    },
    {
     "provider": "wafer.ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.1"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "GLM-5.2"
    },
    {
     "provider": "wandb",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.39"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-5.2"
    },
    {
     "provider": "zhipuai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open flagship GLM for long-horizon coding agents and million-token context work",
   "released_at": "2026-06-13",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 1
   },
   "model_type": "deep_thinking",
   "benchmarks": {
    "intelligence_index": 51.1,
    "coding_index": 68.8,
    "agentic_index": 43.1
   },
   "parameters": {
    "supported": [
     "frequency_penalty",
     "include_reasoning",
     "logit_bias",
     "logprobs",
     "max_tokens",
     "min_p",
     "parallel_tool_calls",
     "presence_penalty",
     "reasoning",
     "reasoning_effort",
     "repetition_penalty",
     "response_format",
     "seed",
     "stop",
     "structured_outputs",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_logprobs",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "@cf/zai-org/glm-5.2",
    "GLM-5.2",
    "TEE/glm-5.2",
    "TEE/glm-5.2:thinking",
    "doubleword/glm-5.2",
    "fireworks/glm-5.2",
    "glm-5-2",
    "hf:zai-org/GLM-5.2",
    "inceptron/glm-5.2",
    "nebius/glm-5.2",
    "sference/glm-5.2",
    "subconscious/glm-5.2",
    "tensorx/glm-5.2",
    "z-ai/glm-5.2",
    "z-ai/glm-5.2-free",
    "zai-org/GLM-5.2",
    "zai-org/glm-5.2",
    "zai-org/glm-5.2:thinking",
    "zai/glm-5.2"
   ],
   "intro_i18n": {
    "zh-CN": "GLM系列是智谱AI为智能代理打造的混合推理模型，具备思考模式和非思考模式。GLM-5.2是智谱在长周期任务时代的旗舰模型，支持1百万个Token的上下文，并针对长周期规划、复杂编程和代理执行进行了优化。",
    "zh-TW": "GLM 系列是智譜 AI 為代理設計的混合推理模型，具備思考模式和非思考模式。GLM-5.2 是智譜在長期任務時代的旗艦模型，支持 100 萬個 token 的上下文，並針對長期規劃、複雜編程和代理執行進行了優化。",
    "ja-JP": "GLMシリーズは、Zhipu AIがエージェント向けに開発したハイブリッド推論モデルで、思考モードと非思考モードを備えています。GLM-5.2は、長期的なタスクの時代に向けたZhipuのフラッグシップモデルで、100万トークンのコンテキストをサポートし、長期的な計画、複雑なコーディング、エージェントの実行に最適化されています。",
    "ru-RU": "Серия GLM — это гибридная модель рассуждений от Zhipu AI, созданная для агентов, с режимами мышления и немышления. GLM-5.2 является флагманской моделью Zhipu для эпохи задач с длинным горизонтом, поддерживающей контекст на 1 миллион токенов и оптимизированной для долгосрочного планирования, сложного программирования и выполнения задач агентами."
   },
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.929",
     "new": "0.769"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "6.01",
     "new": "4.84"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "1.858",
     "new": "1.538"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "cache_read",
     "old": "0.929",
     "new": "0.769"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "completion",
     "old": "6.01",
     "new": "4.84"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "ionet",
     "charge": "prompt",
     "old": "1.858",
     "new": "1.538"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "4.12164704",
     "new": "4.11967696"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17761344",
     "new": "1.17705056"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "openrouter",
     "charge": "cache_read",
     "old": "0.078",
     "new": "0.18"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "openrouter",
     "charge": "completion",
     "old": "1.32",
     "new": "3.08"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "0.42",
     "new": "0.9"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.883",
     "new": "0.929"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "completion",
     "old": "5.73",
     "new": "6.01"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "io-net",
     "charge": "prompt",
     "old": "1.766",
     "new": "1.858"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "completion",
     "old": "4.12451032",
     "new": "4.12164704"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "moark",
     "charge": "prompt",
     "old": "1.17843152",
     "new": "1.17761344"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "cache_read",
     "old": "0.18",
     "new": "0.078"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "completion",
     "old": "3",
     "new": "1.32"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "openrouter",
     "charge": "prompt",
     "old": "0.93",
     "new": "0.42"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "io-net",
     "charge": "cache_read",
     "old": "0.909",
     "new": "0.883"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.2-el",
   "model_name": "glm-5.2-el",
   "display_name": "GLM-5.2-EL",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "poe",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4141"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4444"
      }
     }
    }
   ],
   "released_at": "2026-06-16",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "parameters": {
    "unsupported": [
     "temperature"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-5.2-EL"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.2-fast",
   "model_name": "glm-5.2-fast",
   "display_name": "GLM 5.2 Fast",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3625"
      }
     }
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     },
     "provider_model_id": "zai/glm-5.2-fast"
    },
    {
     "provider": "wafer",
     "official": false,
     "source": "truefoundry",
     "charges": {
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.5"
      },
      "prompt": {
       "unit": "per_M_tokens",
       "price": "3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "10.25"
      }
     },
     "provider_model_id": "z-ai/glm-5.2-fast"
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2026-06-16",
   "max_input_tokens": 1000000,
   "max_output_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "z-ai/glm-5.2-fast",
    "zai/glm-5.2-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "capability",
     "note": "structured_output: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2 Fast"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.2-flex",
   "model_name": "glm-5.2-flex",
   "display_name": "GLM 5.2 Flex",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.725"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18125"
      }
     }
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-06-17",
   "max_input_tokens": 1048560,
   "max_output_tokens": 1048560,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2 Flex"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-5.2-FP8",
   "model_name": "GLM-5.2-FP8",
   "display_name": "GLM-5.2",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "ambient",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2-FP8"
    },
    {
     "provider": "gmicloud",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.979"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.08"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.182"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2-FP8"
    },
    {
     "provider": "vultr",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.85"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.1"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2-FP8"
    }
   ],
   "intro": "Open flagship GLM for long-horizon coding agents and million-token context work",
   "released_at": "2026-06-13",
   "max_input_tokens": 393216,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-5.2-FP8"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "limit",
     "old": "1000000",
     "new": "393216",
     "note": "max_input_tokens"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-5.2"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.2-short",
   "model_name": "glm-5.2-short",
   "display_name": "GLM 5.2 Short",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3625"
      }
     }
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-06-17",
   "max_input_tokens": 199984,
   "max_output_tokens": 199984,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2 Short"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.2-short-fast",
   "model_name": "glm-5.2-short-fast",
   "display_name": "GLM 5.2 Short Fast",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.45"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3625"
      }
     }
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2026-06-17",
   "max_input_tokens": 199984,
   "max_output_tokens": 199984,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2 Short Fast"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.2-short-fast-flex",
   "model_name": "glm-5.2-short-fast-flex",
   "display_name": "GLM 5.2 Short Fast Flex",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.725"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18125"
      }
     }
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2026-06-17",
   "max_input_tokens": 199984,
   "max_output_tokens": 199984,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2 Short Fast Flex"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.2-short-flex",
   "model_name": "glm-5.2-short-flex",
   "display_name": "GLM 5.2 Short Flex",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "neuralwatt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.725"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.18125"
      }
     }
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-06-17",
   "max_input_tokens": 199984,
   "max_output_tokens": 199984,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2 Short Flex"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-5.2-TEE",
   "model_name": "GLM-5.2-TEE",
   "display_name": "GLM 5.2 TEE",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "chutes",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     },
     "provider_model_id": "zai-org/GLM-5.2-TEE"
    }
   ],
   "intro": "Open flagship GLM for long-horizon coding agents and million-token context work",
   "released_at": "2026-06-13",
   "max_input_tokens": 1048576,
   "max_output_tokens": 65535,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/GLM-5.2-TEE"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2 TEE"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5.2:flex",
   "model_name": "glm-5.2:flex",
   "display_name": "doubleword/glm-5.2:flex",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "requesty",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.3"
      }
     },
     "provider_model_id": "doubleword/glm-5.2:flex"
    }
   ],
   "released_at": "2026-06-23",
   "max_input_tokens": 1048576,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "doubleword/glm-5.2:flex"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "doubleword/glm-5.2:flex"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5p1",
   "model_name": "glm-5p1",
   "display_name": "GLM 5.1",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     },
     "provider_model_id": "accounts/fireworks/models/glm-5p1"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-04-01",
   "max_input_tokens": 202800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/glm-5p1"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.1"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5p1-fast",
   "model_name": "glm-5p1-fast",
   "display_name": "GLM 5.1 Fast",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.8"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "8.8"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.52"
      }
     },
     "provider_model_id": "accounts/fireworks/routers/glm-5p1-fast"
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2026-04-01",
   "max_input_tokens": 202800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/routers/glm-5p1-fast"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.1 Fast"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5p2",
   "model_name": "glm-5p2",
   "display_name": "GLM 5.2",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "fireworks-ai",
     "official": false,
     "source": "models-dev+litellm+pydantic-prices+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     },
     "provider_model_id": "accounts/fireworks/models/glm-5p2"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-06-16",
   "max_input_tokens": 1048575,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "docs_url": "https://docs.fireworks.ai/serverless/pricing",
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "accounts/fireworks/models/glm-5p2"
   ],
   "price_history": [
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "fireworks-ai",
     "charge": "cache_read",
     "old": "0.26",
     "new": "0.14"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-5v-turbo",
   "model_name": "glm-5v-turbo",
   "display_name": "GLM-5V-Turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "models-dev+lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "22"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "3.823529"
      }
     }
    },
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7042"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.09848"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.169008"
      }
     }
    },
    {
     "provider": "cortecs",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.235"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.118"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.308"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "1.544"
      }
     }
    },
    {
     "provider": "hunyuan",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "cache_read_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.176471"
      },
      "cache_read_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "0.264706"
      },
      "prompt_0_0_032": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "prompt_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "1.029412"
      },
      "completion_0_0_032": {
       "unit": "per_M_tokens",
       "price": "3.235294"
      },
      "completion_0_032_infinity": {
       "unit": "per_M_tokens",
       "price": "3.823529"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "zai-org/glm-5v-turbo"
    },
    {
     "provider": "kilo",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "z-ai/glm-5v-turbo"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.216"
      }
     },
     "provider_model_id": "zai/glm-5v-turbo"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "z-ai/glm-5v-turbo"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      }
     },
     "provider_model_id": "zai-org/glm-5v-turbo"
    },
    {
     "provider": "openrouter",
     "official": false,
     "source": "models-dev+pydantic-prices+truefoundry+openrouter+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "z-ai/glm-5v-turbo"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "zai-org/GLM-5V-Turbo"
    },
    {
     "provider": "vercel",
     "official": false,
     "source": "models-dev+vercel-gateway+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "zai/glm-5v-turbo"
    },
    {
     "provider": "zai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    },
    {
     "provider": "zenmux",
     "official": false,
     "source": "models-dev+zenmux+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.726"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.1946"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.1743"
      },
      "web_search": {
       "unit": "per_k_calls",
       "price": "10"
      }
     },
     "provider_model_id": "z-ai/glm-5v-turbo",
     "tracks": [
      {
       "label": ">32K context",
       "factor": "1",
       "charge_factors": {
        "completion": "1.181807",
        "cache_read": "1.499713",
        "prompt": "1.400138"
       },
       "triggers": [
        {
         "kind": "input_tokens_above",
         "threshold": 32000,
         "inclusive": true
        }
       ]
      },
      {
       "label": "standard",
       "factor": "1",
       "triggers": []
      }
     ]
    },
    {
     "provider": "zhipuai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks",
   "released_at": "2026-04-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image",
     "video",
     "pdf"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "audio_input": true,
    "video_input": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true,
    "web_search": true
   },
   "model_type": "deep_thinking",
   "reasoning_config": {
    "mandatory": false,
    "budget_min": 128
   },
   "parameters": {
    "supported": [
     "include_reasoning",
     "max_tokens",
     "reasoning",
     "response_format",
     "temperature",
     "tool_choice",
     "tools",
     "top_k",
     "top_p"
    ],
    "defaults": {
     "temperature": 1,
     "top_p": 0.95
    }
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "z-ai/glm-5v-turbo",
    "z-ai/glm-5v-turbo:thinking",
    "zai-org/GLM-5V-Turbo",
    "zai-org/glm-5v-turbo",
    "zai/glm-5v-turbo"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-5V-Turbo是智谱推出的多模态编码基础模型，专为视觉编程任务设计。它原生支持图像、视频、文本和文件处理，并针对长时间规划、复杂编码和多模态工作流中的代理执行进行了优化。",
    "zh-TW": "GLM-5V-Turbo 是智譜推出的多模態編程基礎模型，專為視覺編程任務設計。它原生支持影像、視頻、文本和文件，並針對長期規劃、複雜編程和代理執行進行優化。",
    "ja-JP": "GLM-5V-Turboは、視覚的プログラミングタスク向けに設計されたZhipuのマルチモーダルコーディング基盤モデルです。画像、動画、テキスト、ファイルをネイティブに処理し、長期的な計画、複雑なコーディング、マルチモーダルワークフローにおけるエージェント実行に最適化されています。",
    "ru-RU": "GLM-5V-Turbo — это мультимодальная модель кодирования от Zhipu для задач визуального программирования. Она нативно обрабатывает изображения, видео, текст и файлы, оптимизирована для долгосрочного планирования, сложного кодирования и выполнения агентных задач в мультимодальных рабочих процессах."
   },
   "price_history": [
    {
     "date": "2026-07-02",
     "kind": "capability",
     "note": "web_search: false→true"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-for-coding",
   "model_name": "glm-for-coding",
   "display_name": "glm-for-coding",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.086"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.343"
      }
     }
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-09-30",
   "max_input_tokens": 200000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-for-coding"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-image",
   "model_name": "glm-image",
   "display_name": "GLM-Image",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "image_output": {
       "unit": "per_image",
       "price": "0.014706"
      }
     }
    }
   ],
   "released_at": "2026-01-14",
   "model_type": "image_generation",
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-Image 是智谱推出的新一代旗舰图像生成模型。该模型基于国产芯片进行端到端训练，采用原创的混合架构，将自回归建模与扩散解码器相结合。这种设计既能实现强大的全局指令理解，又能呈现细腻的局部细节，克服了生成知识密集型内容（如海报、演示文稿和教育图表）中的长期挑战。它代表了向新一代“认知生成”技术范式（以 Nano Banana Pro 为例）的重要探索。",
    "zh-TW": "GLM-Image 是智譜最新的旗艦圖像生成模型。該模型基於國產芯片進行端到端訓練，採用原創的混合架構，結合自回歸建模與擴散解碼器。此設計能夠實現強大的全局指令理解以及細緻的局部細節渲染，克服了生成知識密集型內容（如海報、演示文稿和教育圖表）中的長期挑戰。它代表了向新一代「認知生成」技術範式的重要探索，典範為 Nano Banana Pro。",
    "ja-JP": "GLM-Imageは、Zhipuの新しいフラッグシップ画像生成モデルです。このモデルは国内製のチップでエンドツーエンドでトレーニングされ、自己回帰モデリングと拡散デコーダーを組み合わせた独自のハイブリッドアーキテクチャを採用しています。この設計により、グローバルな指示理解能力と細かい局所的な詳細描写能力を両立し、ポスター、プレゼンテーション、教育用図表などの知識密度の高いコンテンツ生成における長年の課題を克服します。Nano Banana Proに代表される新世代の「認知生成」技術パラダイムへの重要な探求を示しています。",
    "ru-RU": "GLM-Image — это новая флагманская модель генерации изображений от Zhipu. Модель была обучена на отечественных чипах и использует оригинальную гибридную архитектуру, которая сочетает авторегрессионное моделирование с диффузионным декодером. Этот дизайн обеспечивает сильное понимание глобальных инструкций наряду с детальной проработкой локальных элементов, преодолевая давние проблемы в создании контента, насыщенного знаниями, такого как постеры, презентации и образовательные диаграммы. Это представляет собой важное исследование в направлении нового поколения парадигм «когнитивной генерации», примером которых является Nano Banana Pro."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-Image"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-latest",
   "model_name": "glm-latest",
   "display_name": "GLM Latest",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.75"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.15"
      }
     },
     "provider_model_id": "zai-org/glm-latest"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2026-05-03",
   "max_input_tokens": 200000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-latest"
   ],
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM Latest"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-ocr",
   "model_name": "glm-ocr",
   "display_name": "glm-ocr",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0282"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0282"
      }
     }
    },
    {
     "provider": "jiekou",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "zai-org/glm-ocr"
    },
    {
     "provider": "llmtr",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.03"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.03"
      }
     },
     "provider_model_id": "zai/glm-ocr"
    }
   ],
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "image"
    ],
    "output": []
   },
   "capabilities": {
    "vision": true,
    "structured_output": true,
    "pdf_input": true,
    "video_input": true
   },
   "released_at": "2026-02-04",
   "max_output_tokens": 32000,
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-org/glm-ocr",
    "zai/glm-ocr"
   ],
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-06",
     "kind": "capability",
     "note": "video_input: false→true"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-ocr"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-z1-32b",
   "model_name": "glm-z1-32b",
   "display_name": "glm-z1-32b",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices+truefoundry",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     },
     "provider_model_id": "glm-z1-32b:free"
    }
   ],
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "max_input_tokens": 32768,
   "max_output_tokens": 4096,
   "deprecated": true,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "glm-z1-32b:free"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-z1-32b"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-Z1-32B-0414",
   "model_name": "GLM-Z1-32B-0414",
   "display_name": "GLM Z1 32B 0414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.08"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     },
     "provider_model_id": "THUDM/GLM-Z1-32B-0414"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "THUDM/GLM-Z1-32B-0414"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.57"
      }
     },
     "provider_model_id": "THUDM/GLM-Z1-32B-0414"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-04-15",
   "max_input_tokens": 128000,
   "max_output_tokens": 65536,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm-z",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "THUDM/GLM-Z1-32B-0414"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM Z1 32B 0414"
    }
   ]
  },
  {
   "slug": "zhipuai/GLM-Z1-9B-0414",
   "model_name": "GLM-Z1-9B-0414",
   "display_name": "GLM Z1 9B 0414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.05"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.05"
      }
     },
     "provider_model_id": "THUDM/GLM-Z1-9B-0414"
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     },
     "provider_model_id": "THUDM/GLM-Z1-9B-0414"
    },
    {
     "provider": "siliconcloud",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     },
     "provider_model_id": "THUDM/GLM-Z1-9B-0414"
    },
    {
     "provider": "siliconflow",
     "official": false,
     "source": "llmdb",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.086"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.086"
      }
     },
     "provider_model_id": "THUDM/GLM-Z1-9B-0414"
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-04-14",
   "max_input_tokens": 32000,
   "max_output_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm-z",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "stream": true
   },
   "model_type": "text_generation",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "THUDM/GLM-Z1-9B-0414"
   ],
   "intro_i18n": {
    "zh-CN": "GLM-Z1-9B-0414是9B参数的小型GLM模型，保留开源优势，具备强大能力，在数学推理与通用任务上表现出色，在同类开源模型中领先。",
    "zh-TW": "GLM-Z1-9B-0414 是一款小型 9B 參數的 GLM 模型，保留開源優勢並展現出色能力。在數學推理與通用任務上表現強勁，於同級開源模型中領先。",
    "ja-JP": "GLM-Z1-9B-0414は、9Bパラメータの小型GLMモデルで、オープンソースの強みを維持しつつ、優れた性能を発揮します。数学的推論や一般的なタスクに強く、同サイズのオープンモデルの中でトップクラスの性能を誇ります。",
    "ru-RU": "GLM-Z1-9B-0414 — компактная модель GLM с 9 миллиардами параметров, сочетающая открытость и высокую производительность. Демонстрирует отличные результаты в математических рассуждениях и решении общих задач, лидируя среди моделей своего класса."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM Z1 9B 0414"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-z1-air",
   "model_name": "glm-z1-air",
   "display_name": "GLM-Z1-Air",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.073529"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-04-15",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "具备强大推理能力的模型，适用于需要深度推理的任务。",
    "zh-TW": "具備強大推理能力的模型，適用於需要深度推理的任務。",
    "ja-JP": "深い推論が求められるタスクにおいて強力な推論能力を発揮するモデルです。",
    "ru-RU": "Модель логического вывода с высокой точностью для задач, требующих глубокого анализа."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-Z1-Air"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-z1-airx",
   "model_name": "glm-z1-airx",
   "display_name": "GLM-Z1-AirX",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.735294"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    }
   ],
   "max_input_tokens": 32768,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "web_search": true,
    "structured_output": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2025-04-15",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "超快推理，兼具高质量推理表现。",
    "zh-TW": "超高速推理，兼具高品質推理表現。",
    "ja-JP": "高品質な推論を超高速で実現します。",
    "ru-RU": "Ультрабыстрая модель логического вывода с высоким качеством рассуждений."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-Z1-AirX"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-z1-flash",
   "model_name": "glm-z1-flash",
   "display_name": "GLM-Z1-Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-Z1 系列具备强大的复杂推理能力，在逻辑、数学与编程方面表现出色。",
    "zh-TW": "GLM-Z1 系列具備強大的複雜推理能力，擅長邏輯、數學與程式任務。",
    "ja-JP": "GLM-Z1 シリーズは、論理、数学、プログラミングにおいて優れた複雑推論能力を発揮します。",
    "ru-RU": "Серия GLM-Z1 обеспечивает мощный логический вывод, особенно в задачах логики, математики и программирования."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-Z1-Flash"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-z1-flashx",
   "model_name": "glm-z1-flashx",
   "display_name": "GLM-Z1-FlashX",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.014706"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.014706"
      }
     }
    }
   ],
   "max_input_tokens": 131072,
   "max_output_tokens": 32768,
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true,
    "web_search": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "快速且低成本：Flash 增强版，具备超快推理与更高并发能力。",
    "zh-TW": "快速且低成本：Flash 增強版，具備超快推理與高併發能力。",
    "ja-JP": "高速かつ低コスト：Flash による強化で超高速推論と高い同時実行性を実現します。",
    "ru-RU": "Быстрая и экономичная модель: ускоренная версия Flash с ультрабыстрым выводом и высокой параллельностью."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-Z1-FlashX"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-z1-rumination-32b",
   "model_name": "glm-z1-rumination-32b",
   "display_name": "glm-z1-rumination-32b",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "openrouter",
     "official": false,
     "source": "pydantic-prices",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.24"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    }
   ],
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-z1-rumination-32b"
    }
   ]
  },
  {
   "slug": "zhipuai/glm-zero-preview",
   "model_name": "glm-zero-preview",
   "display_name": "GLM-Zero-Preview",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "zhipuai",
     "official": true,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.470588"
      }
     }
    },
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2"
      }
     }
    },
    {
     "provider": "nano-gpt",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.802"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.802"
      }
     }
    }
   ],
   "max_input_tokens": 16384,
   "model_type": "text_generation",
   "capabilities": {
    "reasoning": true
   },
   "intro": "Compact GPT model for low-latency assistance and high-volume workloads",
   "released_at": "2024-12-01",
   "max_output_tokens": 4096,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "intro_i18n": {
    "zh-CN": "GLM-Zero-Preview 具备强大的复杂推理能力，在逻辑、数学与编程方面表现出色。",
    "zh-TW": "GLM-Zero-Preview 具備強大的複雜推理能力，擅長邏輯、數學與程式任務。",
    "ja-JP": "GLM-Zero-Preview は、論理、数学、プログラミングにおいて優れた複雑推論能力を発揮します。",
    "ru-RU": "GLM-Zero-Preview демонстрирует сильные способности к логическому выводу, особенно в логике, математике и программировании."
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM-Zero-Preview"
    }
   ]
  },
  {
   "slug": "zhipuai/glm4.6",
   "model_name": "glm4.6",
   "display_name": "glm4.6",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.79914765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.85409875"
      }
     }
    }
   ],
   "released_at": "2026-01-19",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592687",
     "new": "2.85409875"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800595236",
     "new": "0.79914765"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.858164925",
     "new": "2.8592687"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800286179",
     "new": "0.800595236"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.860353575",
     "new": "2.858164925"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800899001",
     "new": "0.800286179"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592021",
     "new": "2.860353575"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800576588",
     "new": "0.800899001"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.859994675",
     "new": "2.8592021"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800798509",
     "new": "0.800576588"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8452425",
     "new": "2.859994675"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.7966679",
     "new": "0.800798509"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm4.6"
    }
   ]
  },
  {
   "slug": "zhipuai/glm4.7",
   "model_name": "glm4.7",
   "display_name": "glm4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "berget",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.79914765"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.85409875"
      }
     }
    }
   ],
   "released_at": "2026-01-19",
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592687",
     "new": "2.85409875"
    },
    {
     "date": "2026-07-09",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800595236",
     "new": "0.79914765"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.858164925",
     "new": "2.8592687"
    },
    {
     "date": "2026-07-08",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800286179",
     "new": "0.800595236"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.860353575",
     "new": "2.858164925"
    },
    {
     "date": "2026-07-07",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800899001",
     "new": "0.800286179"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8592021",
     "new": "2.860353575"
    },
    {
     "date": "2026-07-06",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800576588",
     "new": "0.800899001"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.859994675",
     "new": "2.8592021"
    },
    {
     "date": "2026-07-05",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.800798509",
     "new": "0.800576588"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "completion",
     "old": "2.8452425",
     "new": "2.859994675"
    },
    {
     "date": "2026-07-04",
     "kind": "price",
     "provider": "berget",
     "charge": "prompt",
     "old": "0.7966679",
     "new": "0.800798509"
    },
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/olafangensan-glm-4.7-flash-heretic",
   "model_name": "olafangensan-glm-4.7-flash-heretic",
   "display_name": "GLM 4.7 Flash Heretic",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.035"
      }
     }
    }
   ],
   "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows",
   "released_at": "2026-02-04",
   "max_input_tokens": 200000,
   "max_output_tokens": 24000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.7 Flash Heretic"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "completion",
     "old": "0.8",
     "new": "0.4"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "prompt",
     "old": "0.14",
     "new": "0.07"
    }
   ]
  },
  {
   "slug": "zhipuai/ppio-zai-org-autoglm-phone-9b-multilingual",
   "model_name": "ppio-zai-org-autoglm-phone-9b-multilingual",
   "display_name": "zai-org/autoglm-phone-9b-multilingual",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.036"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.143"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 65536,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zai-org/autoglm-phone-9b-multilingual"
    }
   ]
  },
  {
   "slug": "zhipuai/ppio-zai-org-glm-4-5",
   "model_name": "ppio-zai-org-glm-4-5",
   "display_name": "zai-org/glm-4.5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.5720000000000001"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.2880000000000003"
      }
     }
    }
   ],
   "released_at": "2025-07-28",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zai-org/glm-4.5"
    }
   ]
  },
  {
   "slug": "zhipuai/ppio-zai-org-glm-4-5v",
   "model_name": "ppio-zai-org-glm-4-5v",
   "display_name": "zai-org/glm-4.5v",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.643"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.86"
      }
     }
    }
   ],
   "released_at": "2025-08-25",
   "max_input_tokens": 65536,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zai-org/glm-4.5v"
    }
   ]
  },
  {
   "slug": "zhipuai/ppio-zai-org-glm-4-6",
   "model_name": "ppio-zai-org-glm-4-6",
   "display_name": "zai-org/glm-4.6",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.57"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2025-10-13",
   "max_input_tokens": 198000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zai-org/glm-4.6"
    }
   ]
  },
  {
   "slug": "zhipuai/ppio-zai-org-glm-4-6v",
   "model_name": "ppio-zai-org-glm-4-6v",
   "display_name": "zai-org/glm-4.6v",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.429"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 131072,
   "modalities": {
    "input": [
     "file",
     "image",
     "text",
     "video"
    ],
    "output": [
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zai-org/glm-4.6v"
    }
   ]
  },
  {
   "slug": "zhipuai/ppio-zai-org-glm-4-7",
   "model_name": "ppio-zai-org-glm-4-7",
   "display_name": "zai-org/glm-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2026-01-08",
   "max_input_tokens": 2048000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zai-org/glm-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/ppio-zai-org-glm-4-7-flash",
   "model_name": "ppio-zai-org-glm-4-7-flash",
   "display_name": "zai-org/glm-4.7-flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.429"
      }
     }
    }
   ],
   "released_at": "2026-01-23",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zai-org/glm-4.7-flash"
    }
   ]
  },
  {
   "slug": "zhipuai/siliconflow-Pro-thudm-glm-4-9b-chat",
   "model_name": "siliconflow-Pro-thudm-glm-4-9b-chat",
   "display_name": "Pro/THUDM/glm-4-9b-chat",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.086"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.086"
      }
     }
    }
   ],
   "released_at": "2024-06-18",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/THUDM/glm-4-9b-chat"
    }
   ]
  },
  {
   "slug": "zhipuai/siliconflow-Pro-zai-org-GLM-4-7",
   "model_name": "siliconflow-Pro-zai-org-GLM-4-7",
   "display_name": "Pro/zai-org/GLM-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2026-01-09",
   "max_input_tokens": 198000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/zai-org/GLM-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/siliconflow-Pro-zai-org-GLM-5",
   "model_name": "siliconflow-Pro-zai-org-GLM-5",
   "display_name": "Pro/zai-org/GLM-5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.58"
      }
     }
    }
   ],
   "released_at": "2026-02-13",
   "max_input_tokens": 198000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Pro/zai-org/GLM-5"
    }
   ]
  },
  {
   "slug": "zhipuai/siliconflow-sf-zai-org-glm-4-5-air",
   "model_name": "siliconflow-sf-zai-org-glm-4-5-air",
   "display_name": "sf/zai-org/GLM-4.5-Air",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.857"
      }
     }
    }
   ],
   "released_at": "2025-07-28",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sf/zai-org/GLM-4.5-Air"
    }
   ]
  },
  {
   "slug": "zhipuai/siliconflow-sf-zai-org-glm-4-5v",
   "model_name": "siliconflow-sf-zai-org-glm-4-5v",
   "display_name": "sf/zai-org/GLM-4.5V",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.857"
      }
     }
    }
   ],
   "released_at": "2025-09-16",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sf/zai-org/GLM-4.5V"
    }
   ]
  },
  {
   "slug": "zhipuai/siliconflow-thudm-glm-4-32b-0414",
   "model_name": "siliconflow-thudm-glm-4-32b-0414",
   "display_name": "THUDM/GLM-4-32B-0414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06999999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06999999999999999"
      }
     }
    }
   ],
   "released_at": "2025-04-15",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "THUDM/GLM-4-32B-0414"
    }
   ]
  },
  {
   "slug": "zhipuai/siliconflow-thudm-glm-z1-32b-0414",
   "model_name": "siliconflow-thudm-glm-z1-32b-0414",
   "display_name": "THUDM/GLM-Z1-32B-0414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.06999999999999999"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.06999999999999999"
      }
     }
    }
   ],
   "released_at": "2025-04-15",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "THUDM/GLM-Z1-32B-0414"
    }
   ]
  },
  {
   "slug": "zhipuai/sophnet-glm-4-6",
   "model_name": "sophnet-glm-4-6",
   "display_name": "sophnet/GLM-4.6",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.143"
      }
     }
    }
   ],
   "released_at": "2025-10-13",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/GLM-4.6"
    }
   ]
  },
  {
   "slug": "zhipuai/sophnet-glm-4-7",
   "model_name": "sophnet-glm-4-7",
   "display_name": "sophnet/GLM-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.143"
      }
     }
    }
   ],
   "released_at": "2026-01-06",
   "max_input_tokens": 202000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/GLM-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/sophnet-glm-4.5v",
   "model_name": "sophnet-glm-4.5v",
   "display_name": "sophnet/GLM-4.5V",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.8572"
      }
     }
    }
   ],
   "released_at": "2025-09-29",
   "max_input_tokens": 66000,
   "modalities": {
    "input": [
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/GLM-4.5V"
    }
   ]
  },
  {
   "slug": "zhipuai/sophnet-glm-5",
   "model_name": "sophnet-glm-5",
   "display_name": "sophnet/GLM-5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.286"
      }
     }
    }
   ],
   "released_at": "2026-02-15",
   "max_input_tokens": 202000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "sophnet/GLM-5"
    }
   ]
  },
  {
   "slug": "zhipuai/THUDM/GLM-4.1V-9B-Thinking",
   "model_name": "THUDM/GLM-4.1V-9B-Thinking",
   "display_name": "GLM 4.1V 9B Thinking",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.04"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.16"
      }
     },
     "provider_model_id": "Pro/THUDM/GLM-4.1V-9B-Thinking"
    },
    {
     "provider": "novita",
     "official": false,
     "source": "lobehub-modelbank",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.035"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.138"
      }
     },
     "provider_model_id": "thudm/glm-4.1v-9b-thinking"
    }
   ],
   "max_input_tokens": 65536,
   "model_type": "deep_thinking",
   "capabilities": {
    "reasoning": true,
    "vision": true,
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "Pro/THUDM/GLM-4.1V-9B-Thinking",
    "thudm/glm-4.1v-9b-thinking"
   ],
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.1V 9B Thinking"
    }
   ]
  },
  {
   "slug": "zhipuai/umans-glm-5.1",
   "model_name": "umans-glm-5.1",
   "display_name": "GLM 5.1",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "umans-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.29"
      }
     }
    },
    {
     "provider": "umans-ai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
   "released_at": "2026-04-07",
   "max_input_tokens": 204800,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.1"
    }
   ]
  },
  {
   "slug": "zhipuai/umans-glm-5.2",
   "model_name": "umans-glm-5.2",
   "display_name": "GLM 5.2",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "umans-ai",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    },
    {
     "provider": "umans-ai-coding-plan",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0"
      },
      "cache_write": {
       "unit": "per_M_tokens",
       "price": "0"
      }
     }
    }
   ],
   "intro": "Open flagship GLM for long-horizon coding agents and million-token context work",
   "released_at": "2026-06-13",
   "max_input_tokens": 405504,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2"
    }
   ]
  },
  {
   "slug": "zhipuai/z-ai-glm-5-turbo",
   "model_name": "z-ai-glm-5-turbo",
   "display_name": "GLM 5 Turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    }
   ],
   "intro": "Faster GLM-5 lane for coding agents that need lower latency",
   "released_at": "2026-03-15",
   "max_input_tokens": 200000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5 Turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/z-ai-glm-5v-turbo",
   "model_name": "z-ai-glm-5v-turbo",
   "display_name": "GLM 5V Turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "5"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "intro": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks",
   "released_at": "2026-04-01",
   "max_input_tokens": 200000,
   "max_output_tokens": 32768,
   "modalities": {
    "input": [
     "text",
     "image"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5V Turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/zai-glm-4.6",
   "model_name": "zai-glm-4.6",
   "display_name": "zai-glm-4.6",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "cerebras",
     "official": false,
     "source": "litellm",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "2.25"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.75"
      }
     }
    }
   ],
   "docs_url": "https://www.cerebras.ai/pricing",
   "max_input_tokens": 128000,
   "max_output_tokens": 128000,
   "deprecated": true,
   "model_type": "deep_thinking",
   "deprecation_date": "2026-01-20",
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zai-glm-4.6"
    }
   ]
  },
  {
   "slug": "zhipuai/zai-glm-5-1",
   "model_name": "zai-glm-5-1",
   "display_name": "Z.AI GLM-5.1",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.845"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.38"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.183112"
      }
     },
     "provider_model_id": "zai-glm-5.1"
    },
    {
     "provider": "frogbot",
     "official": false,
     "source": "models-dev",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    }
   ],
   "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
   "released_at": "2025-01-20",
   "knowledge_cutoff": "2024-10",
   "max_input_tokens": 198000,
   "max_output_tokens": 8192,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "aliases": [
    "zai-glm-5.1"
   ],
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "Z.AI GLM-5.1"
    }
   ]
  },
  {
   "slug": "zhipuai/zai-glm-5-turbo",
   "model_name": "zai-glm-5-turbo",
   "display_name": "zai-glm-5-turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "aihubmix",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.2"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.9996"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.24"
      }
     }
    }
   ],
   "capabilities": {
    "prompt_caching": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "zai-glm-5-turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/zai-org-glm-4.6",
   "model_name": "zai-org-glm-4.6",
   "display_name": "GLM 4.6",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.43"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.75"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.08"
      }
     }
    }
   ],
   "intro": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks",
   "released_at": "2024-04-01",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 198000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.6"
    }
   ]
  },
  {
   "slug": "zhipuai/zai-org-glm-4.7",
   "model_name": "zai-org-glm-4.7",
   "display_name": "GLM 4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.55"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.65"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.11"
      }
     }
    }
   ],
   "intro": "Mature GLM model for dependable coding, reasoning, and structured agent tasks",
   "released_at": "2025-12-24",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 198000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/zai-org-glm-4.7-flash",
   "model_name": "zai-org-glm-4.7-flash",
   "display_name": "GLM 4.7 Flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.125"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.5"
      }
     }
    }
   ],
   "intro": "Budget GLM lane for fast coding help, routing, and everyday automation",
   "released_at": "2026-01-29",
   "knowledge_cutoff": "2025-04",
   "max_input_tokens": 128000,
   "max_output_tokens": 16384,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 4.7 Flash"
    }
   ]
  },
  {
   "slug": "zhipuai/zai-org-glm-5",
   "model_name": "zai-org-glm-5",
   "display_name": "GLM 5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+llmdb+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.2"
      }
     }
    }
   ],
   "intro": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
   "released_at": "2026-02-11",
   "max_input_tokens": 198000,
   "max_output_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true,
    "stream": true
   },
   "model_type": "deep_thinking",
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5"
    }
   ]
  },
  {
   "slug": "zhipuai/zai-org-glm-5-1",
   "model_name": "zai-org-glm-5-1",
   "display_name": "GLM 5.1",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.54"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.84"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    }
   ],
   "intro": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
   "released_at": "2026-04-07",
   "max_input_tokens": 200000,
   "max_output_tokens": 24000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.1"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "cache_read",
     "old": "0.325",
     "new": "0.286"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "completion",
     "old": "5.5",
     "new": "4.84"
    },
    {
     "date": "2026-07-03",
     "kind": "price",
     "provider": "venice",
     "charge": "prompt",
     "old": "1.75",
     "new": "1.54"
    }
   ]
  },
  {
   "slug": "zhipuai/zai-org-glm-5-2",
   "model_name": "zai-org-glm-5-2",
   "display_name": "GLM 5.2",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "venice",
     "official": false,
     "source": "models-dev+ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      },
      "cache_read": {
       "unit": "per_M_tokens",
       "price": "0.26"
      }
     }
    }
   ],
   "intro": "Open flagship GLM for long-horizon coding agents and million-token context work",
   "released_at": "2026-06-16",
   "max_input_tokens": 1000000,
   "max_output_tokens": 131072,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "family": "glm",
   "capabilities": {
    "function_calling": true,
    "reasoning": true,
    "prompt_caching": true,
    "structured_output": true,
    "open_weights": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "GLM 5.2"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-codegeex-4",
   "model_name": "zhipu-codegeex-4",
   "display_name": "codegeex-4",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.014"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.014"
      }
     }
    }
   ],
   "released_at": "2024-07-05",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "codegeex-4"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-0520",
   "model_name": "zhipu-glm-4-0520",
   "display_name": "glm-4-0520",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "14"
      }
     }
    }
   ],
   "released_at": "2024-05-20",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4-0520"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-1v-thinking-flashx",
   "model_name": "zhipu-glm-4-1v-thinking-flashx",
   "display_name": "glm-4.1v-thinking-flashx",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.3"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.3"
      }
     }
    }
   ],
   "released_at": "2025-07-08",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "reasoning": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.1v-thinking-flashx"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-5",
   "model_name": "zhipu-glm-4-5",
   "display_name": "glm-4.5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.143"
      }
     }
    }
   ],
   "released_at": "2025-07-28",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.5"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-5-air",
   "model_name": "zhipu-glm-4-5-air",
   "display_name": "glm-4.5-air",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.1143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.286"
      }
     }
    }
   ],
   "released_at": "2025-07-28",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.5-air"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-5-airx",
   "model_name": "zhipu-glm-4-5-airx",
   "display_name": "glm-4.5-airx",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.572"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.714"
      }
     }
    }
   ],
   "released_at": "2025-07-28",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.5-airx"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-5-x",
   "model_name": "zhipu-glm-4-5-x",
   "display_name": "glm-4.5-x",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.143"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.29"
      }
     }
    }
   ],
   "released_at": "2025-07-28",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.5-x"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-5v",
   "model_name": "zhipu-glm-4-5v",
   "display_name": "glm-4.5v",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.29"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.86"
      }
     }
    }
   ],
   "released_at": "2025-08-12",
   "max_input_tokens": 64000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.5v"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-6",
   "model_name": "zhipu-glm-4-6",
   "display_name": "glm-4.6",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.142"
      }
     }
    }
   ],
   "released_at": "2025-09-30",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.6"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-6v",
   "model_name": "zhipu-glm-4-6v",
   "display_name": "glm-4.6v",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.145"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.43"
      }
     }
    }
   ],
   "released_at": "2025-12-08",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.6v"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-7",
   "model_name": "zhipu-glm-4-7",
   "display_name": "glm-4.7",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.142"
      }
     }
    }
   ],
   "released_at": "2025-12-22",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.7"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-7-flashx",
   "model_name": "zhipu-glm-4-7-flashx",
   "display_name": "glm-4.7-flashx",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0715"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.429"
      }
     }
    }
   ],
   "released_at": "2026-01-20",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4.7-flashx"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-air",
   "model_name": "zhipu-glm-4-air",
   "display_name": "glm-4-air",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    }
   ],
   "released_at": "2025-01-16",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4-air"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-air-250414",
   "model_name": "zhipu-glm-4-air-250414",
   "display_name": "glm-4-air-250414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4-air-250414"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-airx",
   "model_name": "zhipu-glm-4-airx",
   "display_name": "glm-4-airx",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 8000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4-airx"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-flash",
   "model_name": "zhipu-glm-4-flash",
   "display_name": "glm-4-flash",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.014"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.014"
      }
     }
    }
   ],
   "released_at": "2024-08-27",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4-flash"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-flash-250414",
   "model_name": "zhipu-glm-4-flash-250414",
   "display_name": "glm-4-flash-250414",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.0014"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.0014"
      }
     }
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4-flash-250414"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-long",
   "model_name": "zhipu-glm-4-long",
   "display_name": "glm-4-long",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.14"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.14"
      }
     }
    }
   ],
   "released_at": "2024-08-10",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4-long"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4-plus",
   "model_name": "zhipu-glm-4-plus",
   "display_name": "glm-4-plus",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      }
     }
    }
   ],
   "released_at": "2024-08-29",
   "max_input_tokens": 128000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4-plus"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4v",
   "model_name": "zhipu-glm-4v",
   "display_name": "glm-4v",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "7"
      }
     }
    }
   ],
   "released_at": "2024-06-05",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4v"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-4v-plus",
   "model_name": "zhipu-glm-4v-plus",
   "display_name": "glm-4v-plus",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.4"
      }
     }
    }
   ],
   "released_at": "2024-08-29",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "file",
     "image",
     "text"
    ],
    "output": [
     "image",
     "text"
    ]
   },
   "capabilities": {
    "vision": true,
    "pdf_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "vision_understanding",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-4v-plus"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-5",
   "model_name": "zhipu-glm-5",
   "display_name": "glm-5",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.6"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "2.6"
      }
     }
    }
   ],
   "released_at": "2026-02-11",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-5"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-5-1",
   "model_name": "zhipu-glm-5-1",
   "display_name": "glm-5.1",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     }
    }
   ],
   "released_at": "2026-04-10",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-5.1"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-5-2",
   "model_name": "zhipu-glm-5-2",
   "display_name": "glm-5.2",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.4"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "4.4"
      }
     }
    }
   ],
   "released_at": "2026-06-15",
   "max_input_tokens": 1000000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-5.2"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-5-turbo",
   "model_name": "zhipu-glm-5-turbo",
   "display_name": "glm-5-turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     }
    }
   ],
   "released_at": "2026-03-16",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "deep_thinking",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-5-turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-5v-turbo",
   "model_name": "zhipu-glm-5v-turbo",
   "display_name": "glm-5v-turbo",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.72"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "3.2"
      }
     }
    }
   ],
   "released_at": "2026-04-02",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "audio",
     "image",
     "text",
     "video"
    ],
    "output": [
     "audio",
     "image",
     "text",
     "video"
    ]
   },
   "capabilities": {
    "vision": true,
    "function_calling": true,
    "reasoning": true,
    "pdf_input": true,
    "audio_input": true,
    "audio_output": true,
    "video_input": true,
    "image_output": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "omni",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-5v-turbo"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-for-coding",
   "model_name": "zhipu-glm-for-coding",
   "display_name": "glm-for-coding",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.286"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.142"
      }
     }
    }
   ],
   "released_at": "2025-12-18",
   "max_input_tokens": 200000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true,
    "reasoning": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-for-coding"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-z1-air",
   "model_name": "zhipu-glm-z1-air",
   "display_name": "glm-z1-air",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.07"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.07"
      }
     }
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-z1-air"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-z1-airx",
   "model_name": "zhipu-glm-z1-airx",
   "display_name": "glm-z1-airx",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "0.7"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "0.7"
      }
     }
    }
   ],
   "released_at": "2025-04-14",
   "max_input_tokens": 32000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {
    "function_calling": true
   },
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-z1-airx"
    }
   ]
  },
  {
   "slug": "zhipuai/zhipu-glm-zero-preview",
   "model_name": "zhipu-glm-zero-preview",
   "display_name": "glm-zero-preview",
   "vendor": "zhipuai",
   "pricing": [
    {
     "provider": "302ai",
     "official": false,
     "source": "ai-model-directory",
     "charges": {
      "prompt": {
       "unit": "per_M_tokens",
       "price": "1.5"
      },
      "completion": {
       "unit": "per_M_tokens",
       "price": "1.5"
      }
     }
    }
   ],
   "released_at": "2024-12-31",
   "max_input_tokens": 16000,
   "modalities": {
    "input": [
     "text"
    ],
    "output": [
     "text"
    ]
   },
   "capabilities": {},
   "endpoints": {
    "inbound": [
     "openai-compatible",
     "anthropic-messages"
    ],
    "outbound": [
     "openai-compatible"
    ]
   },
   "model_type": "text_generation",
   "price_history": [
    {
     "date": "2026-07-03",
     "kind": "listed",
     "note": "glm-zero-preview"
    }
   ]
  }
 ]
}